CN117912295A - Vehicle data processing method and device, electronic equipment and storage medium - Google Patents
Vehicle data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117912295A CN117912295A CN202311764798.2A CN202311764798A CN117912295A CN 117912295 A CN117912295 A CN 117912295A CN 202311764798 A CN202311764798 A CN 202311764798A CN 117912295 A CN117912295 A CN 117912295A
- Authority
- CN
- China
- Prior art keywords
- collision
- target
- obstacle
- determining
- target vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims description 81
- 238000012545 processing Methods 0.000 claims description 65
- 230000008569 process Effects 0.000 claims description 34
- 230000001133 acceleration Effects 0.000 claims description 31
- 230000008859 change Effects 0.000 claims description 27
- 230000002498 deadly effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 8
- 230000004888 barrier function Effects 0.000 claims 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 8
- 238000004088 simulation Methods 0.000 description 25
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000011156 evaluation Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008447 perception Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Mathematical Physics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a vehicle data processing method, device, electronic equipment and storage medium, relates to the field of artificial intelligence, and in particular relates to the technical fields of automatic driving, intelligent transportation and the like. The specific implementation scheme is as follows: predicting a plurality of first travel tracks of the target vehicle in a target period after the first moment according to the travel state information of the target vehicle at the first moment, and predicting the travel track of each obstacle in the target period according to the travel state information of at least one obstacle in the environment of the target vehicle at the first moment; for any first running track, determining a collision risk coefficient of a target vehicle, which collides according to the first running track, according to the moving track of each obstacle and the first running track; and planning a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks, or determining the safety performance of an automatic driving system of the target vehicle.
Description
Technical Field
The present disclosure relates to the field of AI (ARTIFICIAL INTELLIGENCE ), in particular to the technical fields of automatic driving, intelligent traffic, and the like, and more particularly to a method and apparatus for processing vehicle data, an electronic device, and a storage medium.
Background
The vehicle collision risk assessment is an important component of vehicle safety assessment, and is important for identifying actual driving scenes or simulation scenes with collision risk and potential planning control algorithm problems. For example, the collision risk coefficient between the target vehicle and any obstacle around is evaluated, and a simulation scene with potential collision risk is screened out, so that the reliability and safety of a perception algorithm and a path planning algorithm in an automatic driving system can be improved.
Disclosure of Invention
The present disclosure provides a processing method, apparatus, electronic device, and storage medium for vehicle data.
According to an aspect of the present disclosure, there is provided a vehicle data processing method including:
Acquiring running state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment;
Predicting a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predicting the travel track of each obstacle in the target period according to the travel state information of each obstacle;
For any first running track, determining a collision risk coefficient of the target vehicle, which collides according to the running of any first running track, according to the moving track of each obstacle and any first running track;
And planning a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks, or determining the safety performance of an automatic driving system of the target vehicle.
According to another aspect of the present disclosure, there is provided a processing apparatus of vehicle data, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring running state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment;
A prediction module, configured to predict a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predict a movement track of each obstacle in the target period according to movement state information of each obstacle;
The determining module is used for determining a collision risk coefficient of the target vehicle, which is used for collision according to the moving track of each obstacle and any first running track, aiming at any first running track;
and the processing module is used for planning the path of the target vehicle or determining the safety performance of an automatic driving system of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks.
According to still another aspect of the present disclosure, there is provided an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of processing vehicle data according to the above aspect of the present disclosure.
According to still another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium of computer instructions for causing the computer to execute the processing method of vehicle data set forth in the above aspect of the present disclosure.
According to a further aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of processing vehicle data set forth in the above aspect of the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
Fig. 1 is a flowchart illustrating a method for processing vehicle data according to a first embodiment of the disclosure;
fig. 2 is a flowchart of a method for processing vehicle data according to a second embodiment of the disclosure;
fig. 3 is a flowchart of a method for processing vehicle data according to a third embodiment of the disclosure;
Fig. 4 is a flowchart of a method for processing vehicle data according to a fourth embodiment of the disclosure;
fig. 5 is a flowchart of a method for processing vehicle data according to a fifth embodiment of the disclosure;
Fig. 6 is a flowchart of a method for processing vehicle data according to a sixth embodiment of the disclosure;
fig. 7 is a flowchart of a method for processing vehicle data according to a seventh embodiment of the disclosure;
FIG. 8 is a flow chart of a method for processing vehicle data according to an embodiment of the disclosure;
FIG. 9 is a schematic diagram of a predicted trajectory provided by an embodiment of the present disclosure;
fig. 10 is a schematic structural diagram of a processing device for vehicle data according to a ninth embodiment of the present disclosure;
FIG. 11 illustrates a schematic block diagram of an example electronic device that may be used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Currently, when evaluating collision risk, probability of collision is mainly considered, and comprehensive evaluation on the deadly, severity and the like of collision is lacked, so that reliability of collision risk evaluation is low. For example, in evaluating collision risk in an unmanned vehicle simulation system, it is necessary to distinguish between different degrees of collision risk.
Accordingly, in response to at least one of the above-mentioned problems, the present disclosure proposes a method, apparatus, device, and medium for processing vehicle data.
The following describes a method, apparatus, device, and medium for processing vehicle data according to an embodiment of the present disclosure with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for processing vehicle data according to an embodiment of the disclosure.
The embodiment of the disclosure is exemplified by the vehicle data processing method being configured in a vehicle data processing device, and the vehicle data processing device can be applied to any electronic device, so that the electronic device can execute a vehicle data processing function.
The electronic device may be any device with computing capability, for example, may be a personal computer, a mobile terminal, a server, etc., and the mobile terminal may be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc., which have various operating systems, touch screens, and/or display screens.
As shown in fig. 1, the vehicle data processing method may include the steps of:
Step S101, acquiring driving state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
In the embodiment of the present disclosure, the target vehicle may be a vehicle having an autopilot function.
In the embodiment of the present disclosure, the first time may be any time, for example, the first time may be a current time, a previous time, or the like.
In embodiments of the present disclosure, obstacles include, but are not limited to: vehicles, pedestrians, etc.
In the embodiment of the present disclosure, the driving state information of the target vehicle at the first time may be acquired, where the driving state information may include: information such as the position, speed, heading angle, acceleration, yaw rate, etc. of the target vehicle at the first time.
In the embodiment of the present disclosure, movement state information of at least one obstacle in an environment where a target vehicle is located at a first moment may also be obtained, where the movement state information may include: information such as the position, speed, heading angle, acceleration, yaw rate, and direction angle of the lane in which the obstacle is located at the first time.
It should be noted that, in an actual driving or driving scenario, the driving state information of the target vehicle may be acquired by a related sensor on the target vehicle, and the moving state information of the obstacle may be perceived by a perception module in the target vehicle.
In an automatic driving simulation system (i.e. a simulation scene), the running state information of a target vehicle and the moving state information of an obstacle can be obtained through sensor simulation, for example, the working principles of various sensors can be simulated through a sensor simulation module, and the sensors can receive and process reflection signals, optical signals and the like of the vehicle and the obstacle in a simulation environment, so that the running state information of the vehicle and the moving state information of the obstacle are obtained; or the traveling state information of the target vehicle and the moving state information of the obstacle may be preset or configured, or may be input interactively by a user, etc., which is not limited by the embodiment of the present disclosure.
Step S102, predicting a plurality of first driving tracks of the target vehicle in a target period after a first moment according to the driving state information, and predicting the moving tracks of the obstacles in the target period according to the moving state information of the obstacles.
The duration of the target period may be preset.
In the embodiment of the present disclosure, a plurality of travel tracks (denoted as a first travel track in the present disclosure) of the target vehicle in a target period after the first time may be predicted from travel state information of the target vehicle at the first time.
In the embodiment of the present disclosure, the movement track of each obstacle in the target period after the first time may also be predicted according to the movement state information of each obstacle at the first time.
Step S103, for any first running track, determining a collision risk coefficient of the target vehicle, which collides according to any first running track, according to the moving track of each obstacle and any first running track.
In the embodiment of the disclosure, for any one first travel track, a collision risk coefficient of the target vehicle that collides when traveling according to the first travel track may be calculated according to the movement track of each obstacle and the first travel track.
Step S104, planning a path of the target vehicle or determining the safety performance of an automatic driving system of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks.
In the embodiment of the present disclosure, a path planning may be performed on a target vehicle according to collision risk coefficients corresponding to a plurality of first travel tracks, for example, the target vehicle is taken as an automatic driving vehicle or an unmanned vehicle as an example, and in an actual travel scene of the target vehicle, the first travel track with the smallest collision risk coefficient may be used as a planned path of the target vehicle.
Or the safety performance of the automatic driving system of the target vehicle can be determined according to collision risk coefficients corresponding to the plurality of first driving tracks. For example, in a simulation scenario or a simulation test environment, the safety performance of the autopilot system of the target vehicle may be determined or tested according to the first travel track with the smallest collision risk coefficient.
According to the vehicle data processing method, according to the running state information of the target vehicle at the first moment, a plurality of first running tracks of the target vehicle in a target period after the first moment are predicted, and according to the moving state information of at least one obstacle in the environment of the target vehicle at the first moment, the moving track of each obstacle in the target period is predicted; for any first running track, determining a collision risk coefficient of a target vehicle, which collides according to the first running track, according to the moving track of each obstacle and the first running track; and planning a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks, or determining the safety performance of an automatic driving system of the target vehicle. Therefore, a plurality of first running tracks corresponding to the target vehicle are predicted at the same time, according to the moving tracks of all obstacles in the environment of the target vehicle, the collision risk coefficient of the target vehicle, which is collided when the target vehicle runs according to each first running track, is calculated, the reasonability and reliability of collision risk coefficient evaluation can be improved, so that path planning is performed based on the reliable collision risk coefficient corresponding to the plurality of first running tracks, the running safety of the target vehicle can be improved, or the safety performance of an automatic driving system of the target vehicle is evaluated based on the reliable collision risk coefficient corresponding to the plurality of first running tracks, the accuracy of safety performance evaluation can be improved, so that simulation scenes or algorithm modules possibly having collision risk (such as a perception algorithm, a path planning algorithm possibly abnormal and the like can be determined under the condition that the collision risk coefficient of all the first running tracks is high) can be identified in advance based on the accurate evaluation result, and the reliability of the automatic driving system is improved.
It should be noted that, in the technical solution of the present disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing, etc. of the personal information of the user are all performed on the premise of proving the consent of the user, and all conform to the rules of the related laws and regulations, and do not violate the popular regulations of the public order.
In order to clearly explain how the collision risk coefficient of the collision of the target vehicle according to the first travel track is determined according to the movement track and the first travel track of each obstacle in the above embodiment, the present disclosure also proposes a vehicle data processing method.
Fig. 2 is a flowchart illustrating a method for processing vehicle data according to a second embodiment of the disclosure.
As shown in fig. 2, the processing method of the vehicle data may include the steps of:
Step S201, acquiring driving state information of a target vehicle at a first moment, and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
Step S202, predicting a plurality of first driving tracks of the target vehicle in a target period after a first moment according to the driving state information, and predicting the moving tracks of the obstacles in the target period according to the moving state information of the obstacles.
The explanation of steps S201 to S202 may be referred to the relevant description in any embodiment of the disclosure, and will not be repeated here.
In step S203, for any one of the first travel trajectories, a reference travel trajectory that collides with any one of the first travel trajectories is determined from the travel trajectories of the respective obstacles.
The number of the reference movement tracks may be one or may be plural, which is not limited in the embodiment of the present disclosure.
In the embodiment of the disclosure, for any one first travel track, a reference travel track that collides with the first travel track may be determined from the travel tracks of the respective obstacles, that is, the obstacle may collide with the target vehicle when traveling along the first travel track while moving along the reference travel track.
Step S204, acquiring a collision time and a collision type when the reference movement track collides with any one of the first travel tracks.
The collision time (or referred to as collision occurrence time) refers to a time when the target vehicle collides with an obstacle (referred to as a target obstacle in the present disclosure) corresponding to the reference movement trajectory.
The collision type refers to the collision type of a target vehicle, such as rear-end collision, head-on collision, lateral scratch, collision rollover, pedestrian vehicle collision and the like.
In the embodiment of the present disclosure, a collision time when the reference movement trajectory collides with the first travel trajectory may be determined according to a collision position between the reference movement trajectory and the first travel trajectory (for example, the reference movement trajectory intersects with the first travel trajectory at the collision position, or a distance between a trajectory point at the collision position in the reference movement trajectory and a trajectory point at the collision position in the first travel trajectory is smaller than a set distance threshold value), and a collision type when the target vehicle collides with an obstacle corresponding to the reference movement trajectory (referred to as a target obstacle in the present disclosure) may be determined according to the collision time.
In any of the embodiments of the present disclosure, the manner of determining the collision type may be, for example:
1. And acquiring the relative position relationship between the target vehicle and the target obstacle at the collision moment according to the first running track and the reference moving track.
2. The target class (e.g., vehicle, pedestrian, animal, etc.) to which the target obstacle belongs is obtained.
3. And determining the collision type according to the relative position relation and/or the target type.
Among the collision types include, but are not limited to, the following types: rear-end collision, head-on collision, lateral scratch, collision rollover, pedestrian-vehicle collision, and the like.
For example, when the target type is a pedestrian, it may be determined directly that the collision type is: a pedestrian vehicle collision; when the target type is a vehicle, the target obstacle may be referred to as an obstacle vehicle, and when the relative positional relationship between the target vehicle and the obstacle vehicle is head-to-head, the collision type may be determined as: a head-on collision; when the relative positional relationship between the target vehicle and the obstacle vehicle is head-to-tail, it may be determined that the collision type is: rear-end collision; when the relative positional relationship between the target vehicle and the obstacle vehicle is lateral, it may be determined that the collision type is: side scratch, etc., not explicitly recited herein.
Therefore, the collision type of the target vehicle and the target obstacle is identified by integrating the relative position relation between the target vehicle and the target obstacle at the moment of collision and the target category of the target obstacle, and the accuracy and the reliability of the identification of the collision type can be improved.
Step S205, determining target probability according to the collision time and the collision type, wherein the target probability is used for indicating the deadly probability when collision occurs.
In the embodiment of the present disclosure, the target probability may be determined according to the collision time and the collision type, wherein the target probability is used to indicate the deadly probability when the target vehicle collides with the target obstacle.
In any of the embodiments of the present disclosure, the target probability is determined by, for example:
1. the first predicted speed of the target vehicle at the time of collision may be determined based on the first travel track.
It should be noted that, the first driving track is generated according to predicted driving state information (hereinafter simply referred to as predicted state information) of the target vehicle at a plurality of moments in the target period, for example, track fitting may be performed on the predicted state information at the plurality of moments, where the predicted state information may include a predicted speed of the target vehicle at a corresponding moment.
Accordingly, in the present disclosure, the predicted speed of the target vehicle at the time of collision may be regarded as the first predicted speed.
2. Similarly, a second predicted speed of the target obstacle at the time of collision may be determined based on the reference movement trajectory.
3. And determining the collision speed between the target vehicle and the target obstacle at the moment of collision according to the collision type, the first predicted speed and the second predicted speed.
In the embodiment of the present disclosure, the collision speed between the target vehicle and the target obstacle at the time of collision may be calculated by combining the collision type, the first predicted speed, and the second predicted speed at the same time.
As an example, in the case where the collision type is a rear-end collision, the collision speed=an absolute value of a difference between the first predicted speed and the second predicted speed, that is, the collision speed=an absolute value of a relative speed between the first predicted speed and the second predicted speed.
In the case where the collision type is a head-on collision, the collision speed= (first predicted speed+second predicted speed)/2.
In the case where the collision type is a lateral scratch or a collision rollover, the collision speed=the first predicted speed.
In the case where the collision type is a pedestrian vehicle collision, the collision speed=the first predicted speed.
4. The target probability may be determined from the collision velocity; wherein, the target probability and the collision speed are in positive correlation, namely, the larger the collision speed is, the larger the target probability is, and conversely, the smaller the collision speed is, the smaller the target probability is.
As an example, the correspondence relationship between the collision type, the collision velocity, and the deadly model may be set in advance, and for example, the correspondence relationship may be as shown in table 1.
TABLE 1 correspondence between collision type, collision velocity and deadly model
In the present disclosure, the target probability may be calculated according to the collision velocity and the deadly model, and the head-on collision deadly model is taken as an example for explanation, if the first predicted velocity of the target vehicle at the time of collision is lower than a certain velocity, it may be considered that there is no deadly, at this time, the target probability (or referred to as a deadly level score) may be 0, and if the first predicted velocity of the target vehicle at the time of collision is higher than a certain velocity, the velocity may be processed in intervals, wherein the larger the velocity interval, the higher the target probability, that is, the target probability and the collision velocity are in positive correlation.
As an example, the number of speed intervals is 4, respectively [0,40km/h ], [40km/h,70 km/h), [70km/h,100 km/h), [100km/h, + -infinity) for example, the target probability is calculated in the following manner:
A. The first predicted speed of the target vehicle is less than 40km/h, and the target probability is 0;
B. the first predicted speed of the target vehicle is within the speed interval of [40km/h,70 km/h), the target probability: (v-40): (0.1-0.0)/interval length, wherein interval length = 70-40 = 30km/h;
C. the first predicted speed of the target vehicle is within the speed interval of [70km/h,100 km/h), the target probability: (v-70): (1-0.1)/interval length, wherein interval length = 100-70 = 30km/h;
D. The first predicted speed of the target vehicle is greater than or equal to 100km/h, and the target probability is set to 1.0 directly.
Steps B and C can be understood as steps (0- >0.1- >0.9- > 1.0) corresponding to the velocity intervals of the normalized collision velocity, wherein steps corresponding to the first velocity interval [0,40km/h ] are 0, steps corresponding to the second velocity interval [40km/h,70km/h ] are 0.1, steps corresponding to the third velocity interval [70km/h,100km/h ] are 0.9, and steps corresponding to the fourth velocity interval [100km/h, + ] are 1.
In summary, the collision type of the target vehicle, the first predicted speed of the target vehicle at the collision moment and the second predicted speed of the target obstacle at the collision moment are integrated, the collision speed between the target vehicle and the target obstacle at the collision moment is determined, and the target probability is determined according to the collision speed, so that the rationality and the reliability of the target probability calculation can be improved.
Step S206, according to the target probability, determining a collision risk coefficient of the collision of the target vehicle according to any first driving track.
In the embodiment of the disclosure, a collision risk coefficient of a collision of a target vehicle according to any first driving track may be determined according to a target probability, where the collision risk coefficient and the target probability have a positive correlation, that is, the greater the target probability, the greater the collision risk coefficient, and vice versa, the smaller the target probability, and the smaller the collision risk coefficient.
In step S207, a path planning is performed on the target vehicle according to the collision risk coefficients corresponding to the plurality of first driving trajectories, or the safety performance of the automatic driving system of the target vehicle is determined.
The explanation of step S207 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
According to the vehicle data processing method, the target probability is determined according to the collision time and the collision type when the reference movement track collides with the first movement track, and the target probability is used for evaluating the deadliness or the severity of the collision, so that the collision risk coefficient is calculated according to the target probability, and the accuracy and the rationality of the calculation of the collision risk coefficient can be improved.
In order to clearly explain how the collision risk coefficient of the collision of the target vehicle according to the first driving track is determined according to the target probability in the above embodiment, the present disclosure also proposes a vehicle data processing method.
Fig. 3 is a flowchart illustrating a method for processing vehicle data according to a third embodiment of the disclosure.
As shown in fig. 3, the processing method of the vehicle data may include the steps of:
Step S301, acquiring driving state information of a target vehicle at a first moment, and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
Step S302, predicting a plurality of first driving tracks of the target vehicle in a target period after a first moment according to the driving state information, and predicting the moving track of each obstacle in the target period according to the moving state information of each obstacle.
Step S303, for any one of the first travel tracks, determines a reference travel track that collides with any one of the first travel tracks from among the travel tracks of the respective obstacles.
Wherein the reference movement track is a movement track corresponding to the target obstacle.
Step S304, a collision time and a collision type when the reference movement track collides with any one of the first travel tracks are obtained.
Step S305, determining a target probability according to the collision time and the collision type, wherein the target probability is used for indicating the deadly probability when the collision occurs.
The explanation of steps S301 to S305 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
Step S306, obtaining a collision speed between the target vehicle and the target obstacle corresponding to the reference movement track at the time of collision.
In the embodiment of the present disclosure, for any one first travel track, a first predicted speed of the target vehicle at the time of collision may be determined according to the first travel track, and a second predicted speed of the target obstacle at the time of collision may be determined according to the reference movement track, so that in the present disclosure, the collision speed between the target vehicle and the target obstacle at the time of collision may be determined according to the type of collision, the first predicted speed, and the second predicted speed. The specific implementation principle can be referred to the related description in the above embodiments, and will not be described herein.
Step S307, determining TTC according to the time difference between the collision time and the first time.
In the embodiment of the present disclosure, the time difference between the collision time and the first time may be taken as TTC (Time To Collision, collision time).
Step S308, according to the collision speed, TTC and target probability, determining a collision risk coefficient of the target vehicle, wherein the collision occurs when the target vehicle runs according to any first running track.
The collision risk coefficient and the TTC are in a negative correlation, namely, the smaller the TTC is, the larger the collision risk coefficient is, and conversely, the larger the TTC is, the smaller the collision risk coefficient is.
The collision risk coefficient is in positive correlation with the collision speed and the target probability, namely, the larger the collision speed is, the larger the collision risk coefficient is, otherwise, the smaller the collision speed is, the smaller the collision risk coefficient is, similarly, the larger the target probability is, the larger the collision risk coefficient is, otherwise, the smaller the target probability is, and the smaller the collision risk coefficient is.
In any one of the embodiments of the present disclosure, the determining manner of the collision risk coefficient of the first driving track may be, for example:
1. And acquiring the overlapping area between the first external frame of the target vehicle and the second external frame of the target obstacle corresponding to the reference movement track at the collision moment.
2. And determining the collision contact area of the target vehicle according to the ratio of the overlapping area to the area of the first circumscribed frame.
For example, the ratio of the overlapping area to the area of the first circumscribed frame may be taken as the collision contact area of the target vehicle, that is, the collision contact area is the normalized overlapping area.
3. And determining a collision risk coefficient of the collision of the target vehicle according to the first running track according to the collision contact area, the collision speed, the TTC and the target probability.
The collision risk coefficient and the collision contact area are in positive correlation, namely, the larger the collision contact area is, the larger the collision risk coefficient is, otherwise, the smaller the collision contact area is, and the smaller the collision risk coefficient is.
As an example, taking the number of reference movement trajectories as one example, the collision risk coefficient C j of the j-th first travel trajectory may be calculated using the following formula:
Where α represents a normalized estimated collision area (in this disclosure, denoted as a collision contact area), f represents a target probability, δ v represents a collision relative speed, and the collision speed may be normalized by using the highest running speed of the target vehicle to obtain δ v, that is, δ v =the collision speed/the highest running speed, m i is a power weight configuration parameter, and i=1, 2,3,4.
In summary, the collision risk coefficient is comprehensively calculated by combining multiple items of information (such as collision contact area, collision speed, TTC and target probability), so that the accuracy and reliability of the calculation of the collision risk coefficient can be further improved.
In step S309, a path planning is performed on the target vehicle according to the collision risk coefficients corresponding to the plurality of first driving trajectories, or the safety performance of the automatic driving system of the target vehicle is determined.
The explanation of step S309 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
According to the vehicle data processing method, the collision risk coefficient is calculated based on the target probability for evaluating the deadliness or the severity of the collision, the collision risk coefficient is comprehensively calculated based on the collision time TTC and the collision speed between the target vehicle and the target obstacle at the collision time, and the reliability and the rationality of the collision risk coefficient calculation can be further improved.
In order to clearly illustrate how, according to the target probability, a collision risk coefficient of a collision of a target vehicle traveling according to a first traveling track is determined in any embodiment of the disclosure, the disclosure further provides a vehicle data processing method.
Fig. 4 is a flowchart illustrating a method for processing vehicle data according to a fourth embodiment of the disclosure.
As shown in fig. 4, the processing method of the vehicle data may include the steps of:
Step S401, acquiring driving state information of a target vehicle at a first moment, and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment.
Step S402, predicting a plurality of first driving tracks of the target vehicle in a target period after a first moment according to the driving state information, and predicting the moving tracks of the obstacles in the target period according to the moving state information of the obstacles.
In step S403, for any one of the first travel tracks, a reference travel track that collides with any one of the first travel tracks is determined from the travel tracks of each obstacle, wherein the number of reference travel tracks is a plurality.
Step S404, obtaining a collision time and a collision type when any one of the reference movement tracks collides with any one of the first travel tracks.
Step S405, determining a target probability according to the collision time and the collision type, wherein the target probability is used for indicating the deadly probability when the collision occurs.
The explanation of steps S401 to S405 may be referred to the relevant description in any embodiment of the disclosure, and will not be repeated here.
Step S406, determining a collision risk sub-coefficient between the target vehicle and the target obstacle corresponding to any reference moving track according to the target probability.
In the embodiment of the disclosure, a collision risk sub-coefficient between the target vehicle and the target obstacle corresponding to any one of the above-mentioned reference movement tracks may be determined according to the target probability, where the collision risk sub-coefficient and the target probability have a positive correlation.
Step S407, determining a collision risk coefficient of the target vehicle, which collides according to any first driving track, according to the collision risk sub-coefficients of the target obstacle corresponding to the plurality of reference moving tracks.
In the embodiment of the disclosure, the collision risk coefficient of the target vehicle, which collides according to the first driving track, may be determined according to the collision risk sub-coefficients of the target obstacle corresponding to the plurality of reference movement tracks.
For example, the average value, the weighted sum value, the accumulated sum, and the like of the collision risk sub-coefficients of the target obstacle corresponding to the plurality of reference movement trajectories may be used as the collision risk coefficient of the target vehicle that collides in accordance with the first travel trajectory.
As an example, for each first travel track corresponding to the target vehicle(Wherein,/>Representing a set of first travel trajectories), may calculate/>Trajectory/>, with all obstacles O i e O (where O represents the set of obstacles)Collision risk coefficient/>Accumulation/>Collision risk coefficient with all obstacles as target vehicle per/>The collision risk coefficient of the collision occurring while traveling can be calculated in accordance with/>, for example, using the following formulaCollision risk coefficient of collision during running:
In step S408, a path planning is performed on the target vehicle according to the collision risk coefficients corresponding to the plurality of first driving trajectories, or the safety performance of the automatic driving system of the target vehicle is determined.
The explanation of step S408 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
According to the vehicle data processing method, all the reference movement tracks collided with the first running track are integrated to calculate the collision risk coefficient corresponding to the first running track, and the rationality of collision risk coefficient calculation can be further improved.
In order to clearly illustrate how the path planning is performed on the target vehicle in any embodiment of the disclosure, the disclosure also proposes a vehicle data processing method.
Fig. 5 is a flowchart illustrating a method for processing vehicle data according to a fifth embodiment of the disclosure.
As shown in fig. 5, the processing method of the vehicle data may include the steps of:
step S501, acquiring driving state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
Step S502, predicting a plurality of first driving tracks of the target vehicle in a target period after a first moment according to the driving state information, and predicting the moving tracks of the obstacles in the target period according to the moving state information of the obstacles.
Step S503, for any first driving track, determining a collision risk coefficient of the target vehicle for collision according to any first driving track according to the moving track of each obstacle and any first driving track.
The explanation of steps S501 to S503 may be referred to the relevant description in any embodiment of the present disclosure, and will not be repeated here.
In step S504, a second travel track is determined from the plurality of first travel tracks according to the collision risk coefficients of the plurality of first travel tracks, wherein the collision risk coefficient of the second travel track is the smallest.
In the embodiment of the present disclosure, the first travel locus having the smallest collision risk coefficient may be used as the second travel locus.
In step S505, a path planning is performed on the target vehicle according to the second driving track.
In the embodiment of the disclosure, the path planning may be performed on the target vehicle according to the second travel track, for example, the second travel track may be used as the planned path of the target vehicle.
According to the vehicle data processing method, the path planning is carried out on the target vehicle based on the running track with the minimum collision risk coefficient, so that the probability of collision of the target vehicle can be reduced, and the running safety of the target vehicle is improved.
In order to clearly illustrate how the safety performance of the autopilot system of the target vehicle is determined in any embodiment of the present disclosure, the present disclosure also proposes a method for processing vehicle data.
Fig. 6 is a flowchart of a method for processing vehicle data according to a sixth embodiment of the disclosure.
As shown in fig. 6, the processing method of the vehicle data may include the steps of:
Step S601, acquiring driving state information of a target vehicle at a first moment, and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
Step S602, predicting a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predicting a movement track of each obstacle in the target period according to the movement state information of each obstacle.
Step S603, for any first driving track, determining a collision risk coefficient of the target vehicle for collision according to any first driving track according to the moving track of each obstacle and any first driving track.
The explanation of steps S601 to S603 may be referred to the related description in any embodiment of the present disclosure, and will not be repeated here.
In step S604, a third travel track is determined from the plurality of first travel tracks according to the collision risk coefficients of the plurality of first travel tracks, wherein the collision risk coefficient of the third travel track is the smallest.
In the embodiment of the present disclosure, the first travel locus having the smallest collision risk coefficient may be used as the third travel locus.
Step S605, it is determined whether the collision risk coefficient of the third travel track is smaller than the set coefficient threshold, if yes, step S606 is executed, and if no, step S607 is executed.
Wherein, the coefficient threshold is set as a preset risk coefficient threshold.
It should be noted that, the two implementations of the step S606 and the step S607 are parallel, and only one implementation is needed in actual application.
In step S606, it is determined that the safety performance of the automatic driving system of the target vehicle is higher than the set performance level.
In the embodiment of the disclosure, in the case where the collision risk coefficient of the third travel track is smaller than the set coefficient threshold value, it may be determined that the safety performance of the automated driving system of the target vehicle is relatively high, that is, it is determined that the safety performance of the automated driving system of the target vehicle is higher than the set performance level.
In step S607, it is determined that the safety performance of the automatic driving system is lower than the set performance level.
In the embodiment of the present disclosure, in the case where the collision risk coefficient of the third travel locus is greater than or equal to the set coefficient threshold value, it may be determined that the safety performance of the automated driving system of the target vehicle is relatively low, that is, it is determined that the safety performance of the automated driving system of the target vehicle is lower than the set performance level.
According to the vehicle data processing method, the safety performance of the automatic driving system of the target vehicle is determined based on the running track with the minimum collision risk coefficient, and the rationality and reliability of the determination result can be improved.
In order to clearly explain how to predict a plurality of first travel tracks of a target vehicle in a target period after a first time according to travel state information in any embodiment of the present disclosure, the present disclosure also proposes a vehicle data processing method.
Fig. 7 is a flowchart of a method for processing vehicle data according to a seventh embodiment of the disclosure.
As shown in fig. 7, the processing method of the vehicle data may include the steps of:
Step S701, acquiring driving state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment of the target vehicle at the first moment.
The explanation of step S701 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
Step S702, determining a first variation section of acceleration according to the acceleration in the driving state information.
In the embodiment of the present disclosure, a change interval of acceleration (for example, longitudinal acceleration) may be determined according to acceleration (for example, longitudinal acceleration) in the running state information, and is denoted as a first change interval in the present disclosure.
The longitudinal direction may be a longitudinal axis direction in the world coordinate system, and the corresponding transverse direction may be a transverse axis direction in the world coordinate system.
As an example, if the longitudinal acceleration of the target vehicle at the first time is a (assuming a > 0), and the maximum longitudinal acceleration is set to be a constant b (b > 0), the upper and lower boundaries of the first variation section may be defined as:
The lower boundary is: max (-2.5, -b);
The upper boundary is: min (2.5, a+b).
The first variation section is floated within a certain range of the longitudinal acceleration at the first time, but is not more than ±2.5 (acceleration degree is too steep).
Step S703 of determining the maximum rotation speed of the steering wheel of the target vehicle according to the running speed in the running state information.
In the embodiment of the present disclosure, the maximum rotation speed S of the steering wheel of the target vehicle may be determined according to the running speed (e.g., longitudinal speed) in the running state information.
As an example, a one-dimensional linear lookup table (i.e., a one-to-one discrete value mapping table) between longitudinal speed and maximum steering wheel speed may be provided, such as: (v 1,v2…,v7)->(s1,s2,…,s7), v represents the speed, s represents the maximum steering wheel rotating speed, and a negative correlation is formed between v and s. In the disclosure, according to the longitudinal speed of the target vehicle at the first moment, the mapping relationship between v and S is queried, S corresponding to the longitudinal speed is found, and the S is used as the maximum rotation speed S of the steering wheel of the target vehicle.
If S corresponding to the longitudinal speed cannot be found, the maximum steering wheel rotation speed S corresponding to the longitudinal speed may be calculated by a linear interpolation algorithm.
Step S704, determining a second variation interval of the rotation speed of the steering wheel according to the maximum rotation speed.
In the embodiment of the disclosure, the second variation interval of the rotation speed of the steering wheel may be determined according to the maximum rotation speed. The determining manner of the second variation interval is similar to that of the first variation interval, that is, the second variation interval floats in a certain range above and below the maximum rotation speed S, which is not described herein.
Step S705 predicts a plurality of first travel tracks of the target vehicle in a target period after the first time based on the first change section, the second change section, and the travel state information.
In the embodiment of the disclosure, a plurality of first travel tracks of the target vehicle in a target period after the first time may be predicted according to the first change interval, the second change interval, and the travel state information of the target vehicle at the first time.
As one example, the following steps may be employed to predict a plurality of first travel trajectories of the target vehicle within a target period after a first time instant:
1. The driving state information of the marked target vehicle at the first time (such as time t) is:
Wherein x t represents a lateral position coordinate of the target vehicle, y t represents a longitudinal position coordinate of the target vehicle, θ t represents a heading angle, v tx represents a lateral speed, v ty represents a longitudinal speed, a tx represents a lateral acceleration, a ty represents a longitudinal acceleration,/> Indicating yaw rate. In the present disclosure, the first change interval may be discretized, for example, the first change interval is denoted by [ l a(aty),ua(aty) ], where l a(aty) represents an upper boundary of the first change interval, u a(aty) represents a lower boundary of the first change interval, then the discretized first change interval may be :At=[la(aty),…,la(aty)+Δa*i,…,ua(aty)],, where i is a positive integer, Δ a is a discretization step size, and Δ a is determined according to the number of first travel tracks to be predicted, that is, the shorter the discretization step size, the more points that can be sampled in the first change interval, and the more the number of first travel tracks to be predicted.
2. The second variation section may be subjected to discretization processing, for example, the second variation section is denoted by [ l r(vty,Tv2msr),ur(vty,Tv2msr) ], where l r(vty,Tv2msr) represents an upper boundary of the second variation section, u r(vty,Tv2msr) represents a lower boundary of the second variation section, v ty represents a longitudinal speed of the target vehicle at the first moment, T v2msr represents a one-dimensional linear lookup table between the longitudinal speed and the maximum steering wheel rotation speed in step S703, and the discretized second variation section may be :Rt=[lr(vty,Tv2msr),…,lr(vty,Tv2msr)+Δr*i,…,ur(vty,Tv2msr)], where i is a positive integer, Δ r is a discretization step, and Δ r is determined according to the number of first travel tracks to be predicted.
3. Based on driving state informationAdjusting longitudinal acceleration/>And steering wheel speed/>Selecting a predicted time interval τ (e.g., 0.1 s), a first travel track of the target vehicle over a future target period may be predictedWherein S t represents the running state information at the time t. For example, a simple KBM (KINEMATIC BICYCLE MODEL ) may be applied, and the predicted state information for the target vehicle at the next time to the first time (e.g., time t+1) may be calculated using the following formula:
xt+1=xt+vty*τ*cosθt; (3)
yt+1=yt+vty*τ*sinθt; (4)
Where l f denotes the vehicle wheelbase and sr denotes the vehicle steering gear ratio. Further, the predicted state information of the target vehicle at the time t+2 may be predicted based on the predicted state information of the target vehicle at the time t+1, the predicted state information of the target vehicle at the time t+3 may be predicted based on the predicted state information of the target vehicle at the time t+2, and so on, the predicted state information of the target vehicle at each time in the target period may be obtained, so that the first driving track may be generated according to the predicted state information of each time in the target period.
The lateral speed of the target vehicle in the predicted state information at each time may be kept constant, that is, equal to the lateral speed of the target vehicle in the traveling state information at the first time, and similarly, the lateral acceleration of the target vehicle in the predicted state information at each time may be kept constant, that is, equal to the lateral acceleration of the target vehicle in the traveling state information at the first time.
In summary, a first travel track may be predicted based on each value in the first variation range of the acceleration and each value in the second variation range of the steering wheel rotation speed, so as to obtain a set of travel tracks of the target vehicle predicted at the first moment
Step S706 predicts the movement track of each obstacle in the target period based on the movement state information of each obstacle.
Step S707, for any one of the first travel tracks, determines a collision risk coefficient for the target vehicle to collide according to any one of the first travel tracks according to the movement track of each obstacle and any one of the first travel tracks.
In step S708, a path planning is performed on the target vehicle according to the collision risk coefficients corresponding to the plurality of first driving trajectories, or the safety performance of the automatic driving system of the target vehicle is determined.
The explanation of steps S706 to S708 may be referred to the relevant description in any embodiment of the disclosure, and will not be repeated here.
According to the vehicle data processing method, according to each value in the first change interval of acceleration and each value in the second change interval of steering wheel rotating speed, and according to the running state information of the target vehicle at the first moment, a plurality of first running tracks of the target vehicle in the target period are predicted, and the effectiveness and accuracy of the first running track prediction are improved.
In order to clearly illustrate how to predict the movement track of each obstacle in the target period according to the movement state information of each obstacle in any embodiment of the disclosure, the disclosure also proposes a vehicle data processing method.
Fig. 8 is a flowchart of a method for processing vehicle data according to an embodiment of the disclosure.
As shown in fig. 8, the processing method of the vehicle data may include the steps of:
Step S801, acquiring driving state information of a target vehicle at a first moment, and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment.
Step S802 predicts a plurality of first travel tracks of the target vehicle in a target period after a first time based on the travel state information.
The explanation of steps S801 to S802 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
Step S803, for any obstacle, according to the movement status information of any obstacle, n rounds of iterative prediction processes are performed to obtain n pieces of predicted movement status information at the second moment.
The first round of iterative prediction process comprises the following steps: according to the movement state information of any obstacle, the prediction movement state information obtained by the first-round iterative prediction process is determined, and under the condition that the deviation between the course angle of any obstacle in the movement state information of any obstacle and the direction angle of the lane where any obstacle is located is larger than a set deviation threshold value, the course angle of any obstacle in the prediction movement state information of the first-round iterative prediction process is subjected to deviation correction processing, so that the prediction movement state information of any obstacle at the first second moment is obtained.
The ith round of iterative prediction process comprises the following steps: according to the predicted movement state information of any obstacle at the i-1 th second time, determining predicted movement state information obtained by prediction in the i-1 th round of iterative prediction process, and carrying out deviation correction processing on the course angle of any obstacle in the predicted movement state information of the i-1 th round of iterative prediction process under the condition that the deviation between the course angle of any obstacle in the predicted movement state information of any obstacle and the direction angle of a lane where any obstacle is positioned is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the i-1 th second time; wherein i is an integer greater than 1 and less than or equal to n.
As an example, for the ith obstacle in the obstacle set O to be O i e O, the moving state information of the ith obstacle at the first time (e.g. time t) is marked asWherein/>Represents the lateral position of the i-th obstacle o i,/>Representing the longitudinal position of the i-th obstacle o i,/>Representing the heading angle of the ith obstacle o i,/>Represents the heading angle of the lane in which the i-th obstacle o i is located,/>Represents the longitudinal speed of the i-th obstacle o i,/>Represents the longitudinal acceleration of the i-th obstacle o i,/>The yaw rate of the i-th obstacle o i is indicated.
Can maintain the longitudinal acceleration of the ith obstacle o i at the time tCourse angle/>And yaw rate/>Unchanged and maintain the heading angle/>, of the lane where the i-th obstacle o i is locatedThe following formula is used to calculate the predicted movement state information of the ith obstacle o i at the time next to the first time (e.g., time t+1), without change:
/>
Further, the predicted movement state information of the ith obstacle o i at the time t+1 may be predicted based on the predicted movement state information of the ith obstacle o i at the time t+2, the predicted movement state information of the ith obstacle o i at the time t+3 may be predicted based on the predicted movement state information of the ith obstacle o i at the time t+2, and so on, the predicted movement state information of the ith obstacle o i at each time in the target period may be obtained, so that the movement track of the ith obstacle o i may be generated based on the predicted movement state information of each time in the target period
If the error between the predicted position of the obstacle and the actual position of the obstacle is too large, the trajectory point at the future time may be calculated using the actual traveling direction of the obstacle. In addition, only the heading angle of the obstacle at the time tAngle of orientation with the lane in which the obstacle is located/>And under the condition of larger deviation, the course angle is predicted and corrected by using the formula (10).
Step S804, according to the predicted movement state information of n second moments, generating movement tracks of any obstacle.
In the embodiment of the present disclosure, the movement track of the obstacle may be generated according to the predicted movement state information of the n second moments, for example, the predicted movement state information of the obstacle at the n second moments may be subjected to track fitting, so as to obtain the movement track of the obstacle.
Step S805, for any one of the first travel tracks, determining a collision risk coefficient of the target vehicle that collides according to any one of the first travel tracks according to the movement track of each obstacle and any one of the first travel tracks.
In step S806, a path planning is performed on the target vehicle according to the collision risk coefficients corresponding to the plurality of first driving trajectories, or the safety performance of the automatic driving system of the target vehicle is determined.
The explanation of steps S805 to S806 may be referred to the related description in any embodiment of the disclosure, and will not be repeated here.
According to the vehicle data processing method, the predicted movement state information of the obstacle at a plurality of moments can be predicted based on the iterative updating mode, so that track fitting can be performed according to the predicted movement state information at the plurality of moments, the movement track of the obstacle in the target period can be obtained, and the effectiveness and accuracy of movement track prediction can be improved.
In any one embodiment of the disclosure, the method is applied to an automatic driving simulation system and an obstacle is taken as a vehicle (the target obstacle can be called an obstacle vehicle) for carrying out an exemplary description, the disclosure provides a method for comprehensively and quantitatively evaluating the collision risk of the vehicle in the automatic driving simulation system, based on the current running state information of the target vehicle (or called the target simulation vehicle) and surrounding obstacle vehicles, the running track of the target vehicle and the moving track of the obstacle vehicle are respectively predicted, on the basis of comprehensively considering the collision deadly, the collision intensity and the collision time, the collision risk coefficient is given through a quantitative model, the collision risk between the target vehicle and any surrounding obstacle vehicle is evaluated, the simulation scene with the potential collision risk is screened, the reliability and the safety of a perception algorithm and a path planning algorithm are improved, and a solid foundation is laid for the safety of an unmanned vehicle.
For example, in assessing the risk of a collision, multiple dimensions of collision contact area, collision fatality, collision velocity, collision time, etc. may be considered, and the severity of the collision may be differentiated in greater granularity.
As an example, in the automatic driving simulation system, during the driving process of the target vehicle, a reasonable driving track can be planned for the target vehicle according to the current road environment and surrounding obstacle vehicles, and the obstacle vehicles usually preset the starting and stopping states of the driving through setting models such as position, speed and the like when editing the simulation scene, and generate the moving track of the obstacle vehicles through an algorithm. The key of the collision risk assessment is to predict a plurality of running tracks of the target vehicle within a certain simulation time period in the future based on running state information of the target vehicle of the current simulation step (simulation step), including information of position, course angle, speed, acceleration, yaw rate and the like, and assess the moment point of possible collision, the collision severity and the like between the running track predicted for the target vehicle and the moving track predicted for the obstacle vehicle.
Considering that a driver usually adopts operations such as slightly adjusting acceleration or steering wheel to avoid when estimating that collision risk exists, in the present disclosure, multiple running tracks of a target vehicle can be predicted by changing the acceleration and the steering wheel rotation speed of the target vehicle based on the current running state information of the target vehicle; for an obstacle vehicle, the current acceleration and the orientation angle of the obstacle vehicle can be maintained unchanged, and the movement track of the obstacle vehicle can be predicted; and finally, calculating collision risk coefficients between each running track of the target vehicle and the moving tracks of all surrounding obstacle vehicles, and if the collision risk coefficient of a certain running track in the multiple running tracks of the target vehicle is smaller than a set coefficient threshold value, considering that the target vehicle is not at collision risk in the current state, otherwise, the target vehicle is at collision risk. The method mainly comprises the following three steps:
Step one: and predicting the running track of the target vehicle. For example, a plurality of travel tracks of the target vehicle may be predicted based on formulas (3) - (7), resulting in a travel track set
Step two: and predicting the moving track of the obstacle vehicle. For example, the movement locus of each obstacle vehicle o i can be predicted based on formulas (8) - (11)
As an example, taking the number of first travel tracks as three and the number of obstacle vehicles as one as an example, three first travel tracks of the predicted target vehicle and one movement track of the obstacle vehicle may be as shown in fig. 9.
Step three: and (5) collision risk assessment.
For each predicted travel track of the target vehicleCalculating collision risk coefficients/>, of the collision risk coefficients and the movement tracks of all obstacles O i epsilon OAnd accumulating collision risk coefficients of all obstacles as the collision risk coefficient of the running track. The collision risk coefficient can be quantitatively calculated by using the following model:
Wherein, alpha represents the estimated value of the collision area after normalization, the contact area during collision can be approximately represented by using the maximum overlapping area of the circumscribed polygons of the target vehicle and the obstacle vehicle in the collision process, and the overlooking area of the target vehicle is used for normalization; f represents the corresponding deadly probability of the collision, and is mainly calculated according to the relative speed of the vehicle (the collision speed in the disclosure), the collision position and the collision type (such as side collision, head-on collision, rear-end collision and the like) when the collision occurs; delta v represents the relative collision speed, and the collision speed is obtained by normalizing the highest running speed of the target vehicle; TTC represents the collision time, i.e. the duration of the predicted collision time from the current simulation step starting time; m i is a power weight configuration parameter, i=1, 2,3,4.
Intuitively, the larger the collision contact area at the time of collision, the higher the mortality probability, the larger the relative collision speed, and the shorter the collision time, the higher the collision risk coefficient.
It should be appreciated that different strategies may be devised to determine whether the target vehicle is at risk of collision at the first time based on the collision risk coefficient C j,oi for each travel path of the target vehicle. For example, one can simply consider: if the collision risk coefficient of one running track is smaller than the set coefficient threshold value, no risk exists between the target vehicle and surrounding obstacle vehicles, or if the collision risk coefficient of most running tracks is smaller than the set coefficient threshold value, no risk exists between the target vehicle and surrounding obstacle vehicles; the collision risk elements in the formula (2) may be constrained independently according to actual evaluation requirements, for example, the collision risk coefficient may be calculated according to some of the four parameters.
In conclusion, the method can be deployed on the unmanned vehicle, the collision risk between the target vehicle and surrounding obstacle vehicles is calculated in real time, a basis is provided for a downstream decision-making planning algorithm, and the driving safety of the unmanned vehicle is improved; or the method can be deployed into an automatic driving simulation system offline to serve as a measurement evaluation standard of whether the target vehicle has collision risk, and a scene or an algorithm module which possibly has collision risk can be identified in advance in a simulation test link.
Corresponding to the above-described processing method of the vehicle data provided by the embodiments of fig. 1 to 8, the present disclosure also provides a processing device of the vehicle data, and since the processing device of the vehicle data provided by the embodiments of the present disclosure corresponds to the processing method of the vehicle data provided by the embodiments of fig. 1 to 8, implementation of the processing method of the vehicle data is also applicable to the processing device of the vehicle data provided by the embodiments of the present disclosure, which is not described in detail in the embodiments of the present disclosure.
Fig. 10 is a schematic structural diagram of a processing device for vehicle data according to a ninth embodiment of the present disclosure.
As shown in fig. 10, the processing device 1000 of vehicle data may include: the acquisition module 1010, the prediction module 1020, the determination module 1030, and the processing module 1040.
The acquiring module 1010 is configured to acquire driving status information of a target vehicle at a first moment, and moving status information of at least one obstacle in an environment where the target vehicle is located at the first moment.
The prediction module 1020 is configured to predict a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predict a movement track of each obstacle in the target period according to the movement state information of each obstacle.
The determining module 1030 is configured to determine, for any first driving track, a collision risk coefficient of the target vehicle that collides according to any first driving track according to the movement track of each obstacle and any first driving track.
And the processing module 1040 is configured to plan a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving trajectories, or determine safety performance of an autopilot system of the target vehicle.
In one possible implementation of the embodiment of the disclosure, the determining module 1030 is configured to: determining a reference movement track which collides with any first movement track from the movement tracks of the obstacles aiming at any first movement track; acquiring collision time and collision type when the reference movement track collides with any first driving track; determining target probability according to the collision time and the collision type, wherein the target probability is used for indicating the deadly probability when collision occurs; and determining a collision risk coefficient of the collision of the target vehicle according to any first running track according to the target probability.
In a possible implementation manner of the embodiment of the present disclosure, the reference movement track is a movement track corresponding to the target obstacle, and the determining module 1030 is configured to: determining collision time according to any first driving track and reference movement track; acquiring a relative position relationship between a target vehicle and a target obstacle at the moment of collision; obtaining a target category to which a target obstacle belongs; and determining the collision type according to the relative position relation and/or the target type.
In a possible implementation manner of the embodiment of the present disclosure, the reference movement track is a movement track corresponding to the target obstacle, and the determining module 1030 is configured to: determining a first predicted speed of the target vehicle at the moment of collision according to any first driving track, and determining a second predicted speed of the target obstacle at the moment of collision according to the reference moving track; determining the collision speed between the target vehicle and the target obstacle at the moment of collision according to the collision type, the first predicted speed and the second predicted speed; determining target probability according to the collision speed; wherein the target probability is in positive correlation with the collision velocity.
In one possible implementation of the embodiment of the disclosure, the determining module 1030 is configured to: determining a collision time TTC according to the time difference between the collision time and the first time; according to the collision speed, TTC and target probability, determining a collision risk coefficient of collision of the target vehicle according to any first driving track; the collision risk coefficient and the TTC are in a negative correlation, and the collision risk coefficient, the collision speed and the target probability are in a positive correlation.
In one possible implementation of the embodiment of the disclosure, the determining module 1030 is configured to: acquiring the overlapping area of a first external frame of the target vehicle and a second external frame of the target obstacle corresponding to the reference movement track at the collision moment; determining a collision contact area of the target vehicle according to the ratio of the overlapping area to the area of the first circumscribed frame; and determining a collision risk coefficient of the collision of the target vehicle according to any first driving track according to the collision contact area, the collision speed, the TTC and the target probability.
In one possible implementation manner of the embodiment of the present disclosure, the number of the reference movement tracks is a plurality, and the determining module 1030 is configured to: determining a collision risk sub-coefficient between the target vehicle and a target obstacle corresponding to the reference moving track according to the target probability; and determining a collision risk coefficient of the target vehicle, which collides according to any first running track, according to the collision risk sub-coefficients of the target obstacle corresponding to the target vehicle and the multiple reference moving tracks.
In one possible implementation of the embodiments of the present disclosure, the processing module 1040 is configured to: determining a second running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the second running track is the smallest; and planning a path of the target vehicle according to the second running track.
In one possible implementation of the embodiments of the present disclosure, the processing module 1040 is configured to: determining a third running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the third running track is the smallest; judging whether the collision risk coefficient of the third running track is smaller than a set coefficient threshold value or not; if yes, determining that the safety performance of an automatic driving system of the target vehicle is higher than the set performance level; if not, determining that the safety performance of the automatic driving system is lower than the set performance level.
In one possible implementation of the embodiments of the present disclosure, the prediction module 1020 is configured to: determining a first change interval of acceleration according to the acceleration in the running state information; determining the maximum rotation speed of a steering wheel of the target vehicle according to the running speed in the running state information; determining a second change interval of the rotating speed of the steering wheel according to the maximum rotating speed; and predicting a plurality of first driving tracks of the target vehicle in a target period after the first moment according to the first change interval, the second change interval and the driving state information.
In one possible implementation manner of the embodiment of the present disclosure, the target period includes n second moments, where n is a positive integer, and the prediction module 1020 is configured to: for any obstacle, according to the movement state information of any obstacle, performing n rounds of iterative prediction processes to obtain n pieces of predicted movement state information at second moments; generating a moving track of any obstacle according to the n pieces of predicted moving state information at the second moment; the first round of iterative prediction process comprises the following steps: according to the movement state information of any obstacle, determining the predicted movement state information predicted by the first-round iterative prediction process, and performing deviation correction processing on the course angle of any obstacle in the predicted movement state information of the first-round iterative prediction process under the condition that the deviation between the course angle of any obstacle in the movement state information of any obstacle and the direction angle of a lane where any obstacle is positioned is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the first second moment; the ith round of iterative prediction process comprises the following steps: according to the predicted movement state information of any obstacle at the i-1 th second time, determining predicted movement state information obtained by prediction in the i-1 th round of iterative prediction process, and carrying out deviation correction processing on the course angle of any obstacle in the predicted movement state information of the i-1 th round of iterative prediction process under the condition that the deviation between the course angle of any obstacle in the predicted movement state information of any obstacle and the direction angle of a lane where any obstacle is positioned is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the i-1 th second time; wherein i is an integer greater than 1 and less than or equal to n.
According to the vehicle data processing device, a plurality of first driving tracks of a target vehicle in a target period after a first moment are predicted according to driving state information of the target vehicle in the first moment, and moving tracks of various obstacles in the target period are predicted according to moving state information of at least one obstacle in an environment where the target vehicle is located in the first moment; for any first running track, determining a collision risk coefficient of a target vehicle, which collides according to the first running track, according to the moving track of each obstacle and the first running track; and planning a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks, or determining the safety performance of an automatic driving system of the target vehicle. Therefore, a plurality of first running tracks corresponding to the target vehicle are predicted at the same time, according to the moving tracks of all obstacles in the environment of the target vehicle, the collision risk coefficient of the target vehicle, which is collided when the target vehicle runs according to each first running track, is calculated, the reasonability and reliability of collision risk coefficient evaluation can be improved, so that path planning is performed based on the reliable collision risk coefficient corresponding to the plurality of first running tracks, the running safety of the target vehicle can be improved, or the safety performance of an automatic driving system of the target vehicle is evaluated based on the reliable collision risk coefficient corresponding to the plurality of first running tracks, the accuracy of safety performance evaluation can be improved, so that simulation scenes or algorithm modules possibly having collision risk (such as a perception algorithm, a path planning algorithm possibly abnormal and the like can be determined under the condition that the collision risk coefficient of all the first running tracks is high) can be identified in advance based on the accurate evaluation result, and the reliability of the automatic driving system is improved.
To achieve the above embodiments, the present disclosure also provides an electronic device that may include at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for processing vehicle data according to any one of the above embodiments of the present disclosure.
To achieve the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the processing method of vehicle data set forth in any one of the above embodiments of the present disclosure.
To achieve the above embodiments, the present disclosure further provides a computer program product comprising a computer program which, when executed by a processor, implements the method for processing vehicle data according to any of the above embodiments of the present disclosure.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
FIG. 11 illustrates a schematic block diagram of an example electronic device that may be used to implement embodiments of the present disclosure. The electronic device may include the server and the client in the above embodiments. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 11, the apparatus 1100 includes a computing unit 1101 that can perform various appropriate actions and processes according to a computer program stored in a ROM (read-only memory) 1102 or a computer program loaded from a storage unit 1107 into a RAM (Random Access Memory ) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, ROM 1102, and RAM 1103 are connected to each other by a bus 1104. An I/O (Input/Output) interface 1105 is also connected to bus 1104.
Various components in device 1100 are connected to I/O interface 1105, including: an input unit 1106 such as a keyboard, a mouse, etc.; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108, such as a magnetic disk, optical disk, etc.; and a communication unit 1109 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 1101 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1101 include, but are not limited to, a CPU (Central Processing Unit ), a GPU (Graphic Processing Units, graphics processing unit), various specialized AI (ARTIFICIAL INTELLIGENCE ) computing chips, various computing units running machine learning model algorithms, a DSP (DIGITAL SIGNAL processor ), and any suitable processor, controller, microcontroller, or the like. The calculation unit 1101 performs the respective methods and processes described above, such as the processing method of the vehicle data described above. For example, in some embodiments, the above-described vehicle data processing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1108. In some embodiments, some or all of the computer programs may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the processing method of vehicle data described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the above-described vehicle data processing method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit system, FPGA (Field Programmable GATE ARRAY ), ASIC (application-SPECIFIC INTEGRATED circuit, application-specific integrated circuit), ASSP (application SPECIFIC STANDARD product, application-specific standard product), SOC (system On chip ), CPLD (Complex Programmable Logic Device, complex programmable logic device), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, RAM, ROM, EPROM (ELECTRICALLY PROGRAMMABLE READ-only-memory, erasable programmable read-only memory) or flash memory, an optical fiber, a CD-ROM (Compact Disc Read-only memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., CRT (Cathode-Ray Tube) or LCD (Liquid CRYSTAL DISPLAY) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network ), WAN (Wide Area Network, wide area network), internet and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical hosts and Virtual service (Virtual PRIVATE SERVER, virtual special servers). The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be noted that, artificial intelligence is a subject of studying a certain thought process and intelligent behavior (such as learning, reasoning, thinking, planning, etc.) of a computer to simulate a person, and has a technology at both hardware and software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.
According to the technical scheme of the embodiment of the disclosure, the rationality and reliability of collision risk coefficient evaluation can be improved by simultaneously predicting a plurality of first travel tracks corresponding to the target vehicle and calculating the collision risk coefficient of the target vehicle colliding according to the movement tracks of all obstacles in the environment where the target vehicle is located, so that the safety of the target vehicle traveling can be improved, or the safety performance of an automatic driving system of the target vehicle can be evaluated based on the reliable collision risk coefficients corresponding to the plurality of first travel tracks, the accuracy of the safety performance evaluation can be improved, so that simulation scenes or algorithm modules possibly having collision risks (for example, a perception algorithm, a path planning algorithm possibly abnormal and the like can be determined under the condition that the collision risk coefficients of all the first travel tracks are high) can be identified in advance based on accurate evaluation results, and the reliability of the automatic driving system can be improved.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (25)
1. A method of processing vehicle data, comprising:
Acquiring running state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment;
Predicting a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predicting the travel track of each obstacle in the target period according to the travel state information of each obstacle;
For any first running track, determining a collision risk coefficient of the target vehicle, which collides according to the running of any first running track, according to the moving track of each obstacle and any first running track;
And planning a path of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks, or determining the safety performance of an automatic driving system of the target vehicle.
2. The method of claim 1, wherein the determining, for any one of the first travel trajectories, a collision risk coefficient for the target vehicle to travel according to the any one of the first travel trajectories, based on the movement trajectories of the respective obstacles and the any one of the first travel trajectories, includes:
determining a reference movement track which collides with any first movement track from the movement tracks of the obstacles aiming at any first movement track;
acquiring collision time and collision type when the reference movement track collides with any one of the first running tracks;
determining a target probability according to the collision moment and the collision type, wherein the target probability is used for indicating the deadly probability when collision occurs;
And determining a collision risk coefficient of the target vehicle, which collides according to the running of any one of the first running tracks, according to the target probability.
3. The method according to claim 2, wherein the reference movement trajectory is a movement trajectory corresponding to a target obstacle, and the acquiring a collision time and a collision type when the reference movement trajectory collides with the any one of the first travel trajectories includes:
Determining the collision moment according to any one of the first running tracks and the reference moving track;
Acquiring a relative position relationship between the target vehicle and the target obstacle at the moment of collision;
obtaining a target category to which the target obstacle belongs;
and determining the collision type according to the relative position relation and/or the target type.
4. The method of claim 2, wherein the reference movement trajectory is a movement trajectory corresponding to a target obstacle, and the determining the target probability according to the collision time and the collision type includes:
determining a first predicted speed of the target vehicle at the collision moment according to any one of the first driving tracks, and determining a second predicted speed of the target obstacle at the collision moment according to the reference moving track;
Determining a collision speed between the target vehicle and the target obstacle at the collision time according to the collision type, the first predicted speed and the second predicted speed;
determining the target probability according to the collision speed; wherein the target probability and the collision speed are in positive correlation.
5. The method of claim 4, wherein the determining, according to the target probability, a collision risk coefficient for the target vehicle to collide with traveling along the any one of the first travel tracks includes:
Determining a collision time TTC according to the time difference between the collision time and the first time;
Determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision speed, the TTC and the target probability;
the collision risk coefficient and the TTC are in a negative correlation, and the collision risk coefficient, the collision speed and the target probability are in a positive correlation.
6. The method of claim 5, wherein the determining a collision risk coefficient for the target vehicle to collide with traveling along the any one of the first travel trajectories based on the collision velocity, the TTC, and the target probability comprises:
Acquiring the overlapping area of a first external frame of the target vehicle and a second external frame of the target obstacle corresponding to the reference movement track at the collision moment;
Determining a collision contact area of the target vehicle according to the ratio of the overlapping area to the area of the first circumscribed frame;
And determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision contact area, the collision speed, the TTC and the target probability.
7. The method according to any one of claims 2-6, wherein the number of the reference movement trajectories is a plurality, and the determining, according to the target probability, a collision risk coefficient for the target vehicle to collide with traveling along the any one of the first travel trajectories includes:
determining a collision risk sub-coefficient between the target vehicle and a target obstacle corresponding to the reference movement track according to the target probability;
And determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision risk sub-coefficients of the target vehicle and the target barriers corresponding to the plurality of reference moving tracks.
8. The method of any of claims 1-6, wherein routing the target vehicle according to the collision risk coefficients corresponding to the plurality of first travel trajectories comprises:
Determining a second running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the second running track is the smallest;
and planning a path of the target vehicle according to the second running track.
9. The method of any of claims 1-6, wherein determining the safety performance of the autopilot system of the target vehicle from the collision risk coefficients corresponding to the plurality of first travel trajectories comprises:
Determining a third running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the third running track is the smallest;
Judging whether the collision risk coefficient of the third running track is smaller than a set coefficient threshold value or not;
if yes, determining that the safety performance of an automatic driving system of the target vehicle is higher than a set performance level;
if not, determining that the safety performance of the automatic driving system is lower than the set performance level.
10. The method of any of claims 1-6, wherein the predicting a plurality of first travel trajectories of the target vehicle for a target period of time after the first time based on the travel state information comprises:
Determining a first change interval of the acceleration according to the acceleration in the running state information;
Determining the maximum rotation speed of a steering wheel of the target vehicle according to the running speed in the running state information;
determining a second change interval of the rotating speed of the steering wheel according to the maximum rotating speed;
And predicting a plurality of first driving tracks of the target vehicle in a target period after the first moment according to the first change interval, the second change interval and the driving state information.
11. The method according to any one of claims 1-6, wherein the target period includes n second moments in time, n being a positive integer, the predicting a movement trajectory of each obstacle within the target period according to movement state information of each obstacle, includes:
For any obstacle, performing n rounds of iterative prediction processes according to the movement state information of any obstacle to obtain n pieces of predicted movement state information at second moments;
Generating a moving track of any obstacle according to the n pieces of predicted moving state information at the second moment;
The first round of iterative prediction process comprises the following steps: according to the movement state information of any obstacle, determining the predicted movement state information obtained by the first-round iterative prediction process, and performing deviation correction processing on the course angle of any obstacle in the predicted movement state information of the first-round iterative prediction process under the condition that the deviation between the course angle of any obstacle in the movement state information of any obstacle and the direction angle of a lane where the any obstacle is positioned is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the first second moment;
The ith round of iterative prediction process comprises the following steps: according to the predicted movement state information of any obstacle at the i-1 th second moment, determining predicted movement state information obtained by the i-1 th round of iterative prediction process, and carrying out deviation correction processing on the heading angle of any obstacle in the predicted movement state information of the i-1 th round of iterative prediction process when the deviation between the heading angle of any obstacle in the predicted movement state information of any obstacle at the i-1 th second moment and the heading angle of a lane where the any obstacle is located is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the i-1 th second moment; wherein i is an integer greater than 1 and less than or equal to n.
12. A processing apparatus of vehicle data, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring running state information of a target vehicle at a first moment and moving state information of at least one obstacle in an environment where the target vehicle is located at the first moment;
A prediction module, configured to predict a plurality of first travel tracks of the target vehicle in a target period after the first time according to the travel state information, and predict a movement track of each obstacle in the target period according to movement state information of each obstacle;
The determining module is used for determining a collision risk coefficient of the target vehicle, which is used for collision according to the moving track of each obstacle and any first running track, aiming at any first running track;
and the processing module is used for planning the path of the target vehicle or determining the safety performance of an automatic driving system of the target vehicle according to collision risk coefficients corresponding to the plurality of first driving tracks.
13. The apparatus of claim 12, wherein the means for determining is configured to:
determining a reference movement track which collides with any first movement track from the movement tracks of the obstacles aiming at any first movement track;
acquiring collision time and collision type when the reference movement track collides with any one of the first running tracks;
determining a target probability according to the collision moment and the collision type, wherein the target probability is used for indicating the deadly probability when collision occurs;
And determining a collision risk coefficient of the target vehicle, which collides according to the running of any one of the first running tracks, according to the target probability.
14. The apparatus of claim 13, wherein the reference movement trajectory is a movement trajectory corresponding to a target obstacle, and the determining module is configured to:
Determining the collision moment according to any one of the first running tracks and the reference moving track;
Acquiring a relative position relationship between the target vehicle and the target obstacle at the moment of collision;
obtaining a target category to which the target obstacle belongs;
and determining the collision type according to the relative position relation and/or the target type.
15. The apparatus of claim 13, wherein the reference movement trajectory is a movement trajectory corresponding to a target obstacle, and the determining module is configured to:
determining a first predicted speed of the target vehicle at the collision moment according to any one of the first driving tracks, and determining a second predicted speed of the target obstacle at the collision moment according to the reference moving track;
Determining a collision speed between the target vehicle and the target obstacle at the collision time according to the collision type, the first predicted speed and the second predicted speed;
determining the target probability according to the collision speed; wherein the target probability and the collision speed are in positive correlation.
16. The apparatus of claim 15, wherein the means for determining is configured to:
Determining a collision time TTC according to the time difference between the collision time and the first time;
Determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision speed, the TTC and the target probability;
the collision risk coefficient and the TTC are in a negative correlation, and the collision risk coefficient, the collision speed and the target probability are in a positive correlation.
17. The apparatus of claim 16, wherein the means for determining is configured to:
Acquiring the overlapping area of a first external frame of the target vehicle and a second external frame of the target obstacle corresponding to the reference movement track at the collision moment;
Determining a collision contact area of the target vehicle according to the ratio of the overlapping area to the area of the first circumscribed frame;
And determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision contact area, the collision speed, the TTC and the target probability.
18. The apparatus of any of claims 13-17, wherein the number of reference movement trajectories is a plurality, the determining module to:
determining a collision risk sub-coefficient between the target vehicle and a target obstacle corresponding to the reference movement track according to the target probability;
And determining a collision risk coefficient of the target vehicle, which collides according to any one of the first driving tracks, according to the collision risk sub-coefficients of the target vehicle and the target barriers corresponding to the plurality of reference moving tracks.
19. The apparatus of any of claims 12-17, wherein the processing module is to:
Determining a second running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the second running track is the smallest;
and planning a path of the target vehicle according to the second running track.
20. The apparatus of any of claims 12-17, wherein the processing module is to:
Determining a third running track from the plurality of first running tracks according to the collision risk coefficients of the plurality of first running tracks, wherein the collision risk coefficient of the third running track is the smallest;
Judging whether the collision risk coefficient of the third running track is smaller than a set coefficient threshold value or not;
if yes, determining that the safety performance of an automatic driving system of the target vehicle is higher than a set performance level;
if not, determining that the safety performance of the automatic driving system is lower than the set performance level.
21. The apparatus of any of claims 12-17, wherein the prediction module is to:
Determining a first change interval of the acceleration according to the acceleration in the running state information;
Determining the maximum rotation speed of a steering wheel of the target vehicle according to the running speed in the running state information;
determining a second change interval of the rotating speed of the steering wheel according to the maximum rotating speed;
And predicting a plurality of first driving tracks of the target vehicle in a target period after the first moment according to the first change interval, the second change interval and the driving state information.
22. The apparatus of any one of claims 12-17, wherein the target period includes n second moments in time, n being a positive integer, the prediction module configured to:
For any obstacle, performing n rounds of iterative prediction processes according to the movement state information of any obstacle to obtain n pieces of predicted movement state information at second moments;
Generating a moving track of any obstacle according to the n pieces of predicted moving state information at the second moment;
The first round of iterative prediction process comprises the following steps: according to the movement state information of any obstacle, determining the predicted movement state information obtained by the first-round iterative prediction process, and performing deviation correction processing on the course angle of any obstacle in the predicted movement state information of the first-round iterative prediction process under the condition that the deviation between the course angle of any obstacle in the movement state information of any obstacle and the direction angle of a lane where the any obstacle is positioned is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the first second moment;
The ith round of iterative prediction process comprises the following steps: according to the predicted movement state information of any obstacle at the i-1 th second moment, determining predicted movement state information obtained by the i-1 th round of iterative prediction process, and carrying out deviation correction processing on the heading angle of any obstacle in the predicted movement state information of the i-1 th round of iterative prediction process when the deviation between the heading angle of any obstacle in the predicted movement state information of any obstacle at the i-1 th second moment and the heading angle of a lane where the any obstacle is located is larger than a set deviation threshold value, so as to obtain the predicted movement state information of any obstacle at the i-1 th second moment; wherein i is an integer greater than 1 and less than or equal to n.
23. An electronic device, comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of processing vehicle data of claims 1-11.
24. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the vehicle data processing method according to claims 1-11.
25. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the vehicle data processing method according to claims 1-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311764798.2A CN117912295A (en) | 2023-12-20 | 2023-12-20 | Vehicle data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311764798.2A CN117912295A (en) | 2023-12-20 | 2023-12-20 | Vehicle data processing method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117912295A true CN117912295A (en) | 2024-04-19 |
Family
ID=90692884
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311764798.2A Pending CN117912295A (en) | 2023-12-20 | 2023-12-20 | Vehicle data processing method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117912295A (en) |
-
2023
- 2023-12-20 CN CN202311764798.2A patent/CN117912295A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111736142B (en) | System and method for radar cross traffic tracking and maneuver risk assessment | |
EP4080468A2 (en) | Collision detection method and apparatus, electronic device, medium, and autonomous vehicle | |
US10449956B2 (en) | Object tracking by unsupervised learning | |
CN110632617B (en) | Laser radar point cloud data processing method and device | |
CN110487288A (en) | A kind of estimation method and carriage way estimating system of carriage way | |
CN112526999B (en) | Speed planning method, device, electronic equipment and storage medium | |
Jiao et al. | End-to-end uncertainty-based mitigation of adversarial attacks to automated lane centering | |
CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
CN112116809A (en) | Non-line-of-sight vehicle anti-collision method and device based on V2X technology | |
CN116295496A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
CN116358584A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
CN114137525A (en) | Multi-target detection method and system based on vehicle-mounted millimeter wave radar | |
CN113978465A (en) | Lane-changing track planning method, device, equipment and storage medium | |
US20210398014A1 (en) | Reinforcement learning based control of imitative policies for autonomous driving | |
CN115798261B (en) | Vehicle obstacle avoidance control method, device and equipment | |
CN116890876A (en) | Vehicle control method and device, electronic equipment and automatic driving vehicle | |
CN117912295A (en) | Vehicle data processing method and device, electronic equipment and storage medium | |
CN115782876A (en) | Lane changing track generation method, device and equipment and automatic driving vehicle | |
CN114282776A (en) | Method, device, equipment and medium for cooperatively evaluating automatic driving safety of vehicle and road | |
CN115472040B (en) | Personalized anti-collision early warning method for networked vehicle based on collision probability field | |
US11919546B2 (en) | Systems and methods for estimating cuboids from LiDAR, map and image data | |
US20240161398A1 (en) | Late-to-early temporal fusion for point clouds | |
US20240087136A1 (en) | Dynamic bounding box | |
CN116001819A (en) | Obstacle information processing method and device, electronic equipment and automatic driving vehicle | |
CN118269965A (en) | Collision cost determination method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |