CN113071487A - Automatic driving vehicle control method and device and cloud equipment - Google Patents
Automatic driving vehicle control method and device and cloud equipment Download PDFInfo
- Publication number
- CN113071487A CN113071487A CN202110208312.1A CN202110208312A CN113071487A CN 113071487 A CN113071487 A CN 113071487A CN 202110208312 A CN202110208312 A CN 202110208312A CN 113071487 A CN113071487 A CN 113071487A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- lane
- driving
- target
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000006399 behavior Effects 0.000 claims description 58
- 230000008859 change Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000007499 fusion processing Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/14—Yaw
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
- B60W2554/4026—Cycles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
- B60W2554/4029—Pedestrians
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a control method and device for an automatic driving vehicle and cloud equipment. The method of the invention comprises the following steps: acquiring first running information of a first vehicle and external environment information around the first vehicle under the condition that the first vehicle runs according to a preset running route in an automatic driving state; acquiring a predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants; determining at least one target traffic participant having a collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; and controlling the first vehicle to execute the target driving behavior according to at least one item of the first driving information, the driving information of at least one target traffic participant and the lane information. The invention can more reasonably and intelligently control the driving behavior of the first vehicle, has simple calculation, is applicable to all scenes and has better generalization ability.
Description
Technical Field
The invention relates to the technical field of application of the Internet of things, in particular to a method and a device for controlling an automatic driving vehicle and cloud equipment.
Background
In the current decision-making of the behavior of the automatically-driven vehicle, a vehicle-mounted multi-source sensor (such as a millimeter wave radar, a camera and the like) is mainly adopted to obtain information of surrounding traffic participants (such as vehicles, pedestrians, non-motor vehicles and the like), behaviors of the surrounding traffic participants are predicted by a V2X technology and methods of data collection fusion, deep learning and the like, and the potential risk of collision between the surrounding traffic participants and the vehicle is judged. In the case where there is a potential collision risk, the own vehicle is actively braked or steered to avoid the occurrence of a collision.
In the implementation of the prediction algorithm, the problems that data are acquired only by means of vehicle-mounted equipment, calculation is complex, risk prejudgment execution rules are complex, and applicable scenes are low exist.
Disclosure of Invention
The invention aims to provide a control method and device for an automatic driving vehicle and cloud equipment, which are used for solving the problems of complex calculation, complex risk prejudgment execution rule and low applicable scene of the existing automatic driving vehicle behavior decision.
In order to achieve the above object, the present invention provides an autonomous vehicle control method comprising:
the method comprises the steps that under the condition that a first vehicle runs according to a preset running route in an automatic driving state, first running information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises running information and lane information of M traffic participants;
acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
and controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the lane information.
The obtaining of the predicted driving trajectory of each traffic participant of the N traffic participants according to the driving information of the N traffic participants of the M traffic participants includes:
and respectively inputting the historical driving information of each traffic participant in the N traffic participants as input parameters into a pre-trained prediction model to obtain the predicted driving track of each traffic participant.
Wherein the determining at least one target transportation participant at risk of collision with the first vehicle according to the preset driving route and the predicted driving trajectories of the N transportation participants comprises:
determining traffic participants corresponding to the predicted driving track intersected with the preset driving route as key traffic participants having collision risks with the first vehicle;
determining at least one target traffic participant based on the key traffic participant.
Wherein the determining at least one target traffic participant based on the key traffic participant comprises:
if the number of the key traffic participants is one, determining the key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are all located in front of the first vehicle or are all located behind the first vehicle, determining the key traffic participants, which are closest to the first vehicle, of the multiple key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are respectively located in front of the first vehicle and behind the first vehicle, determining a first key traffic participant and a second key traffic participant as target traffic participants, wherein the first key traffic participant is a key traffic participant located in front of the first vehicle and closest to the first vehicle, and the second key traffic participant is a key traffic participant located behind the first vehicle and closest to the first vehicle.
Wherein the controlling the first vehicle to execute the target driving behavior according to at least one of the first driving information, the driving information of the at least one target traffic participant and the information of the lane where the first vehicle is located includes:
obtaining a first distance value between the target traffic participant and the first vehicle if the number of the target traffic participants is one; controlling the first vehicle to execute a target driving behavior according to the first distance value, or the first distance value and the lane information, wherein the target traffic participant is located in front of the first vehicle or behind the first vehicle, and the first distance value is obtained based on the driving information of the target traffic participant, or is obtained based on the driving information of the target traffic participant and the driving information of the target traffic participant;
and under the condition that the number of the target traffic participants is two, controlling the first vehicle to execute target driving behaviors according to the lane information, wherein one of the two target traffic participants is positioned in front of the first vehicle, and the other target traffic participant is positioned behind the first vehicle.
Wherein the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
Wherein the controlling the first vehicle to perform a target driving behavior in accordance with the first distance value comprises:
controlling the first vehicle to decelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located in front of the first vehicle;
controlling the first vehicle to accelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located behind the first vehicle.
Wherein the controlling the first vehicle to perform a target driving behavior according to the first distance value and the lane information comprises:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located forward of the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid overtaking;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located and a space exists in a second lane based on the lane information, controlling the first vehicle to change lanes or borrow and overtake, wherein the second lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the second lane does not have a space based on the lane information, controlling the first vehicle to brake.
Wherein the controlling the first vehicle to perform a target driving behavior according to the first distance value and the lane information comprises:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located behind the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located based on the lane information, and a third lane exists, controlling the first vehicle to change lanes or borrow lanes to avoid, wherein the third lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the third lane does not have a space based on the lane information, controlling the first vehicle to accelerate.
Wherein the controlling the first vehicle to perform a target driving behavior according to the lane information includes:
if it is determined that a lane-changeable lane exists based on the lane information, controlling the first vehicle to change lanes;
and if it is determined that no lane-variable lane exists based on the lane information, controlling the first vehicle to keep the driving state unchanged.
The present invention also provides an autonomous vehicle control apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring first running information of a first vehicle and external environment information around the first vehicle under the condition that the first vehicle runs according to a preset running route in an automatic driving state, and the external environment information comprises running information and lane information of M traffic participants;
the second acquisition module is used for acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
the processing module is used for determining at least one target traffic participant having collision risk with the first vehicle according to the preset running route and the predicted running tracks of the N traffic participants;
and the control module is used for controlling the first vehicle to execute the target driving behavior according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the lane information.
The invention also provides a cloud device, which comprises a processor and a transceiver, wherein the transceiver receives and sends data under the control of the processor, and the processor is used for executing the following operations:
if a first vehicle runs according to a preset running route in an automatic driving state, acquiring first running information of the first vehicle and external environment information around the first vehicle, wherein the external environment information comprises running information and lane information of M traffic participants;
acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
and controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the information of the lane where the first vehicle is located.
The invention also provides cloud equipment which comprises a memory, a processor and a program which is stored on the memory and can run on the processor; the processor, when executing the program, implements the autonomous vehicle control method as described in the above embodiments.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the autonomous vehicle control method as described in the above embodiments.
The technical scheme of the invention at least has the following beneficial effects:
in the embodiment of the invention, under the condition that a first vehicle runs according to a preset running route in an automatic driving state, first running information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises running information and lane information of M traffic participants; then, according to the driving information of N traffic participants in the M traffic participants, obtaining the predicted driving track of each traffic participant in the N traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer; then, determining at least one target traffic participant having collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; finally, the first vehicle is controlled to execute the target driving behavior according to at least one of the first driving information, the driving information of at least one target traffic participant and the lane information, so that the collision risk is judged based on the prediction of the driving track of the traffic participant, the risk pre-judgment execution rule is simple, the driving behavior of the first vehicle can be more reasonably and intelligently controlled according to at least one of the driving information of the target traffic participant with the collision risk, the first driving information of the first vehicle and the lane information around the first vehicle, namely, the driving behavior is considered from multi-dimensional data, the calculation is simple, the method is applicable to all scenes, and the method has better generalization ability.
Drawings
FIG. 1 shows a schematic flow diagram of an autonomous vehicle control method according to an embodiment of the invention;
FIG. 2 is a schematic flow chart illustrating an autonomous vehicle control decision making process in accordance with an embodiment of the present invention;
FIG. 3 shows a block schematic diagram of an autonomous vehicle control apparatus of an embodiment of the invention;
fig. 4 is a schematic structural diagram of a cloud device according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The invention provides a control method and device for an automatic driving vehicle and cloud equipment, aiming at the problems of complex calculation, complex risk prediction execution rule and low applicable scene of the existing automatic driving vehicle behavior decision.
Fig. 1 is a schematic flow chart of an autonomous vehicle control method according to an embodiment of the present invention. The method specifically comprises the following steps:
it should be noted that the embodiment of the present invention uses the V2X technology, where V2X means Vehicle to X, where X represents Infrastructure (Infrastructure), Vehicle (Vehicle), person (Pedestrian), etc., and X may be any possible "person or thing" (everting). The V2X is mainly used for improving road safety and improving wireless technology of Traffic management, is a key technology of a future Intelligent Traffic System (ITS), and can implement mutual communication between vehicles, between vehicles and roadside facilities, between vehicles and the internet, thereby obtaining a series of Traffic information such as real-time road conditions, road information, pedestrian information, and the like, improving driving safety, reducing congestion, and improving Traffic efficiency.
In this step, all vehicles having the preset driving route may be the first vehicle. The preset running route may be understood as a fixed running route, i.e., a running route in which the number of times the vehicle runs exceeds a preset number of times.
Here, the first vehicle may be a sightseeing bus, a regular bus of an organization or business, or the like. For example, if the first vehicle is a sightseeing vehicle, the preset driving route is a preset sightseeing route.
Here, the preset driving route may be determined by a selection input by a user, or may be determined by a control instruction sent by the cloud device, and is not specifically limited herein.
It should be noted that the first travel information includes, but is not limited to: geographic location information, vehicle speed, and heading angle of the first vehicle. Travel information for a traffic participant includes, but is not limited to: the geographical position information, the speed, the heading angle and the distance value between the first vehicle of the traffic participant. Lane information includes, but is not limited to: lane slope, curvature, lane number, lane line and speed limit sign.
Specifically, the traffic information can be acquired through the acquired high-precision map information and the traffic information acquired by the vehicle-mounted sensing equipment and the road side sensor; and performing data fusion processing on the traffic information to obtain first running information of the first vehicle and external environment information around the first vehicle.
Here, the traffic information may include a category of the traffic participant (including the first vehicle) (e.g., a pedestrian, a vehicle, an obstacle, etc.), geographical location information of the traffic participant, a distance between the first vehicle and other traffic participants, a length, a width, a height, a heading angle, a speed, etc. of the traffic participant.
The vehicle-mounted sensing equipment comprises a vehicle-mounted vision system, a vehicle-mounted millimeter wave radar, a vehicle-mounted laser radar and the like. The roadside sensor comprises a roadside high-definition camera, a roadside laser radar and the like.
Here, the data fusion processing of the traffic information to obtain the first traveling information of the first vehicle and the external environment information around the first vehicle may specifically include:
grouping the traffic information based on the traffic participant category, and matching the traffic participants in each group to obtain the traffic information (namely, data collected by different sensors) corresponding to the same traffic participant; and then, respectively carrying out data fusion processing on the traffic information of different traffic participants to obtain first running information of the first vehicle and external environment information around the first vehicle.
It should be noted that the data fusion technology is an information processing technology that automatically analyzes and integrates data of multiple sensor information sources under certain criteria to complete required decision-making and evaluation tasks.
Specifically, the data fusion processing may be performed on the traffic information of different traffic participants by using the kalman filter.
102, acquiring a predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
in order to reduce the amount of calculation, optionally, the N number of transportation participants are transportation participants within a preset risk area centered on the first vehicle. For example, a circular area with a radius of 50m centered on the first vehicle is the preset risk area.
Here, since the first vehicle speed in the autonomous driving state is relatively stable, the calculation of the size of the risk area is not required.
103, determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
in the step, if the preset driving route is intersected with the predicted driving track, determining that the corresponding traffic participant and the first vehicle have collision risks; otherwise, the collision risk does not exist, and the risk prejudgment execution rule is simple.
And 104, controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the lane information.
Here, the driving behavior of the first vehicle can be more reasonably and intelligently controlled based on at least one of the traveling information of the target traffic participant having the collision risk, the first traveling information of the first vehicle, and the lane information around the first vehicle, that is, from the multidimensional data, and is applicable to an intersection and a non-intersection scene.
According to the automatic driving vehicle control method, under the condition that a first vehicle drives according to a preset driving route in an automatic driving state, first driving information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises driving information and lane information of M traffic participants; then, according to the driving information of N traffic participants in the M traffic participants, obtaining the predicted driving track of each traffic participant in the N traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer; then, determining at least one target traffic participant having collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; finally, the first vehicle is controlled to execute the target driving behavior according to at least one of the first driving information, the driving information of at least one target traffic participant and the lane information, so that the collision risk is judged based on the prediction of the driving track of the traffic participant, the risk pre-judgment execution rule is simple, the driving behavior of the first vehicle can be more reasonably and intelligently controlled according to at least one of the driving information of the target traffic participant with the collision risk, the first driving information of the first vehicle and the lane information around the first vehicle, namely, the driving behavior is considered from multi-dimensional data, the calculation is simple, the method is applicable to all scenes, and the method has better generalization ability.
As an optional implementation manner, the step 102 of the method according to the embodiment of the present invention, obtaining the predicted driving trajectory of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, may include:
and respectively inputting the historical driving information of each traffic participant in the N traffic participants as input parameters into a pre-trained prediction model to obtain the predicted driving track of each traffic participant.
Specifically, the historical driving information is driving information within a first preset time period earlier than the current time. For example, the travel information within 3 seconds before the current time.
And predicting the running track to be the running track in a second preset time length later than the current time. For example, the travel trajectory within 6 seconds after the current time (i.e., 6 seconds in the future).
Here, the historical travel information of the traffic participant includes the speed, the geographical position information, and the heading angle of the traffic participant.
Optionally, the prediction model is an LSTM prediction model. Here, the LTSM prediction model may be trained using real traffic participant data in advance. Specifically, firstly, a large number of sample data sets of traffic participants are acquired, data preprocessing (such as coordinate conversion, category conversion into classification variables and the like) is carried out on the sample data sets, and then the sample data of each traffic participant is converted into structured data, wherein the structured data comprises a traffic participant identification ID, running time, a traffic participant category and coordinates of the traffic participants; and finally, carrying out LSTM model training by using the structured data, comparing the predicted position coordinates with the real coordinates, continuously optimizing the model according to the result, and finally obtaining the trained LSTM model.
It should be noted that the invention uses a deep learning method, i.e. training an LSTM model to predict the driving trajectory of the traffic participants, and if the predicted driving trajectory intersects with the preset driving route, it is determined that there is a collision risk, otherwise, it is determined that there is no collision risk. The implementation mode does not need to relate to a mathematical formula, does not need to test and adjust parameter values, and reduces development time.
As an optional implementation manner, the step 103 of the method according to the embodiment of the present invention, determining at least one target transportation participant having a collision risk with the first vehicle according to the preset traveling route and the predicted traveling tracks of the N transportation participants, may include:
determining traffic participants corresponding to the predicted driving track intersected with the preset driving route as key traffic participants having collision risks with the first vehicle;
here, the key traffic participant at risk of collision with the first vehicle may be one or more.
If the predicted running track intersecting with the preset running route does not exist, the first vehicle is controlled to keep the original running state unchanged.
Determining at least one target traffic participant based on the key traffic participant.
Here, the step may specifically include:
if the number of the key traffic participants is one, determining the key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are all located in front of the first vehicle or are all located behind the first vehicle, determining the key traffic participants, which are closest to the first vehicle, of the multiple key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are respectively located in front of the first vehicle and behind the first vehicle, determining a first key traffic participant and a second key traffic participant as target traffic participants, wherein the first key traffic participant is a key traffic participant located in front of the first vehicle and closest to the first vehicle, and the second key traffic participant is a key traffic participant located behind the first vehicle and closest to the first vehicle.
Optionally, the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
It should be noted that the key traffic participant is one or more of the N traffic participants. If the driving information of the key traffic participant comprises a distance value between the key traffic participant and the first vehicle, directly comparing the distances to determine the key traffic participant closest to the first vehicle; if the distance value between the key traffic participant and the first vehicle is not included in the driving information of the key traffic participant, calculating to obtain the distance value between the key traffic participant and the first vehicle according to the geographical position information of the key traffic participant in the driving information and the geographical position information in the first driving information of the first vehicle, and then comparing the distances to determine the key traffic participant closest to the first vehicle.
As an optional implementation manner, the step 104 of the method according to an embodiment of the present invention, controlling the first vehicle to perform the target driving behavior according to at least one of the first driving information, the driving information of the at least one target traffic participant, and the information of the lane where the first vehicle is located, may include:
obtaining a first distance value between the target traffic participant and the first vehicle if the number of the target traffic participants is one; controlling the first vehicle to execute a target driving behavior according to the first distance value, or the first distance value and the lane information, wherein the target traffic participant is located in front of the first vehicle or behind the first vehicle, and the first distance value is obtained based on the driving information of the target traffic participant, or is obtained based on the driving information of the target traffic participant and the driving information of the target traffic participant;
based on this situation, as an optional implementation manner, controlling the first vehicle to perform the target driving behavior according to the first distance value includes:
controlling the first vehicle to decelerate if the first distance value is greater than a first preset threshold value and a target traffic participant is located in front of the first vehicle;
here, the target traffic participant is located in front of the first vehicle, and the first distance value of the target traffic participant from the first vehicle is greater than a first preset threshold value, for example, 10 meters, which indicates that the target traffic participant is farther from the first vehicle.
Controlling the first vehicle to accelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located behind the first vehicle.
Here, the target traffic participant is located behind the first vehicle, and the first distance value of the target traffic participant from the first vehicle is greater than the first preset threshold value, such as 10 meters, which indicates that the target traffic participant is farther away from the first vehicle, but since the target traffic participant is located behind the first vehicle, in order to avoid collision with each other, the distance between the first vehicle and the target traffic participant is pulled, and only the first vehicle needs to be controlled to accelerate.
As another optional implementation, controlling the first vehicle to perform a target driving behavior according to the first distance value and the lane information includes:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located forward of the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid overtaking;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located and a space exists in a second lane based on the lane information, controlling the first vehicle to change lanes or borrow and overtake, wherein the second lane is a lane adjacent to the first lane;
here, optionally, the second lane is a left lane of the first lane or a right lane of the first lane with respect to a first vehicle traveling direction. This may be the case.
And if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the second lane does not have a space based on the lane information, controlling the first vehicle to brake.
Here, in this implementation, the target traffic participant is located in front of the first vehicle, and the first distance value of the target traffic participant from the first vehicle is less than or equal to the first preset threshold value, which indicates that the target traffic participant is closer to the first vehicle, the risk of collision is increased, and the first vehicle is controlled to perform different driving behaviors based on the lane information in combination with different situations of the space of the first lane where the first vehicle is located.
As a further optional implementation, controlling the first vehicle to perform a target driving behavior according to the first distance value and the lane information includes:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located behind the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid;
here, the first vehicle is optionally controlled to avoid to the right or to avoid to the left with respect to the first vehicle traveling direction. The details may be as appropriate.
If it is determined that an avoidance space does not exist in a first lane where the first vehicle is located based on the lane information, and a third lane exists, controlling the first vehicle to change lanes or borrow lanes to avoid, wherein the third lane is a lane adjacent to the first lane;
here, optionally, the third lane is a left lane of the first lane or a right lane of the first lane with respect to a first vehicle traveling direction. This may be the case.
And if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the third lane does not have a space based on the lane information, controlling the first vehicle to accelerate.
Here, in this implementation, the target traffic participant is located behind the first vehicle, and the first distance value of the target traffic participant from the first vehicle is smaller than or equal to the first preset threshold value, which indicates that the target traffic participant is closer to the first vehicle, the risk of collision is increased, and the first vehicle is controlled to perform different driving behaviors based on the lane information in combination with different situations of the space of the first lane where the first vehicle is located.
And under the condition that the number of the target traffic participants is two, controlling the first vehicle to execute target driving behaviors according to the lane information, wherein one of the two target traffic participants is positioned in front of the first vehicle, and the other target traffic participant is positioned behind the first vehicle.
Based on this situation, as an optional implementation manner, this step may specifically include:
if it is determined that a lane-changeable lane exists based on the lane information, controlling the first vehicle to change lanes;
and if it is determined that no lane-variable lane exists based on the lane information, controlling the first vehicle to keep the driving state unchanged.
Optionally, the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
Through the control behavior decision, the automatic driving vehicle control method provided by the embodiment of the invention obtains a larger sensing area through the V2X technology, and adds judgment of front/rear traffic participants by matching with a high-precision map, so that various intelligent behavior decisions including acceleration, deceleration, lane-borrowing and overtaking, avoidance, braking, driving keeping and the like can be completed.
The following is a description of a specific implementation of the method of the present invention with respect to an example.
Firstly, selecting a preset sightseeing route as an automatic driving route of a sightseeing vehicle in a park with an intelligent network connection environment;
and then, acquiring high-precision map information and source data acquired by the vehicle-mounted sensing equipment and the road side sensor.
The source data here corresponds to the traffic information in the above-described embodiment.
Then, grouping the plurality of source data based on the traffic participant category, matching the traffic participants in each group to obtain data collected by different sensors corresponding to the same traffic participant, and fusing the data by using Kalman filtering to obtain the driving information of the sightseeing vehicle and the external environment information around the sightseeing vehicle.
Specifically, the driving information of the sightseeing vehicle comprises geographic position, vehicle speed, course angle information and the like. The external environment information includes information on the position, speed, heading angle, distance, etc. of traffic participants such as surrounding vehicles, pedestrians, riders and obstacles, and current lane information such as lane gradient, curvature, number of lanes, lane line, speed limit sign, etc.
Then, a circular area of a radius of 50m with the sightseeing vehicle as the center is set as a risk area. Collision prediction is performed for key traffic participants in the risk area.
Here, the specific collision prediction may include the steps of:
1) and predicting the future 6s (time can be changed according to different conditions) driving track of each key traffic participant according to the driving information of the history 3s of the key traffic participant by using a deep learning method.
Here, the LSTM prediction model may be trained in advance using campus real traffic participant data.
2) And judging whether the sightseeing vehicle and the key traffic participants collide or not according to the preset running route of the sightseeing vehicle and the predicted running track of each key traffic participant.
If the preset running route is intersected with the predicted running track, a key traffic participant corresponding to the predicted running track has a collision risk with the sightseeing vehicle, and the intersection point is a collision point Pc; if the predicted driving trajectory does not intersect with the sightseeing bus, the key traffic participants corresponding to the predicted driving trajectory do not have collision risks with the sightseeing bus.
3) And taking a straight line which passes through the mass center of the sightseeing vehicle and is vertical to the course angle of the sightseeing vehicle as a reference line, determining the area of the reference line towards the course angle of the sightseeing vehicle as the front of the sightseeing vehicle, and determining the area of the reference line towards the back of the sightseeing vehicle as the back of the sightseeing vehicle.
Specifically, whether the sightseeing bus and the key traffic participants in front of the sightseeing bus have collision risks or not is checked according to the position information of the key traffic participants, and if so, the front collision risk Cfront1, front collision point PfThe collision point P with the shortest distance from the sightseeing vehicle is the collision point of all the forward key traffic participantsc(ii) a If not, CfrontIs 0.
Checking whether the sightseeing vehicle and the key traffic participants behind the sightseeing vehicle have collision risks according to the position information of the key traffic participants, and if so, checking the rear collision risk CbackIs 1, rear collision point PbThe collision point P with the shortest distance from the sightseeing vehicle is the collision point of all the rear key traffic participantsc(ii) a If not, CbackIs 0.
Finally, a behavior decision result is output according to the predicted collision risk and collision point by using a rule-based strategy (see fig. 2 in particular).
S1: judging whether collision risk exists in front of the sightseeing bus or not;
if yes, go to step S2; otherwise, step S9 is executed.
S2: judgment of PfWhether the distance between the sightseeing bus and the sightseeing bus is smaller than a preset distance value or not;
for example, the preset distance value is 10 meters.
If yes, go to step S3; otherwise, step S4 is executed.
S3: judging whether the same lane of the sightseeing vehicle has an avoidance space;
if yes, go to step S5; otherwise, step S6 is executed.
S4: the sightseeing vehicle executes a deceleration decision;
s5: the sightseeing vehicle executes an avoidance overtaking decision;
s6: judging whether a left lane of the sightseeing vehicle has a space or not;
if yes, go to step S7; otherwise, step S8 is executed.
S7: the sightseeing vehicle executes a lane change or lane borrowing overtaking decision;
s8: the sightseeing vehicle executes a braking decision;
here, this step is also performed when there is no avoidance space in the same lane and the road is a one-way road.
S9: judging whether collision risk exists behind the sightseeing bus or not;
if yes, go to step S10; otherwise, step S17 is executed.
S10: judgment of PbWhether the distance between the sightseeing bus and the sightseeing bus is smaller than a preset distance value or not;
for example, the preset distance value is 10 meters.
If yes, go to step S11; otherwise, step S12 is executed.
S11: judging whether the same lane of the sightseeing vehicle has an avoidance space;
if yes, go to step S13; otherwise, step S14 is executed.
S12: the sightseeing vehicle executes an acceleration decision;
s13: the sightseeing bus executes a right-approaching lane-giving decision;
s14: judging whether a left lane of the sightseeing vehicle has a space or not;
if yes, go to step S15; otherwise, step S16 is executed.
S15: the sightseeing vehicle executes a lane changing or lane borrowing avoiding decision;
s16: the sightseeing vehicle executes an acceleration decision;
s17: and the sightseeing vehicle executes a decision for keeping the running state unchanged.
According to the automatic driving vehicle control method, under the condition that a first vehicle drives according to a preset driving route in an automatic driving state, first driving information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises driving information and lane information of M traffic participants; then, according to the driving information of N traffic participants in the M traffic participants, obtaining the predicted driving track of each traffic participant in the N traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer; then, determining at least one target traffic participant having collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; finally, the first vehicle is controlled to execute the target driving behavior according to at least one of the first driving information, the driving information of at least one target traffic participant and the lane information, so that the collision risk is judged based on the prediction of the driving track of the traffic participant, the risk pre-judgment execution rule is simple, the driving behavior of the first vehicle can be more reasonably and intelligently controlled according to at least one of the driving information of the target traffic participant with the collision risk, the first driving information of the first vehicle and the lane information around the first vehicle, namely, the driving behavior is considered from multi-dimensional data, the calculation is simple, the method is applicable to all scenes, and the method has better generalization ability.
As shown in fig. 3, an embodiment of the present invention also provides an autonomous vehicle control apparatus, including:
the first obtaining module 301 is configured to obtain first driving information of a first vehicle and external environment information around the first vehicle when the first vehicle is driving according to a preset driving route in an automatic driving state, where the external environment information includes driving information and lane information of M traffic participants;
the second obtaining module 302 is configured to obtain a predicted driving track of each traffic participant of the N traffic participants according to driving information of N traffic participants of the M traffic participants, where M is greater than or equal to N and is greater than or equal to 1, and M, N is a positive integer;
the processing module 303 is configured to determine, according to the preset driving route and the predicted driving trajectories of the N traffic participants, at least one target traffic participant having a collision risk with the first vehicle;
a control module 304, configured to control the first vehicle to perform a target driving behavior according to at least one of the first driving information, the driving information of the at least one target traffic participant, and the lane information.
Optionally, the second obtaining module 302 includes:
and the first acquisition unit is used for inputting the historical driving information of each traffic participant in the N traffic participants as an input parameter into a pre-trained prediction model respectively to obtain the predicted driving track of each traffic participant.
Optionally, the processing module 303 includes:
the first processing unit is used for determining traffic participants corresponding to the predicted driving track intersected with the preset driving route as key traffic participants with collision risks with the first vehicle;
a second processing unit for determining at least one target traffic participant based on the key traffic participant.
Optionally, the second processing unit is specifically configured to:
if the number of the key traffic participants is one, determining the key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are all located in front of the first vehicle or are all located behind the first vehicle, determining the key traffic participants, which are closest to the first vehicle, of the multiple key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are respectively located in front of the first vehicle and behind the first vehicle, determining a first key traffic participant and a second key traffic participant as target traffic participants, wherein the first key traffic participant is a key traffic participant located in front of the first vehicle and closest to the first vehicle, and the second key traffic participant is a key traffic participant located behind the first vehicle and closest to the first vehicle.
Optionally, the control module 304 includes:
a first control unit, configured to obtain a first distance value between the target traffic participant and the first vehicle if the number of the target traffic participants is one; controlling the first vehicle to execute a target driving behavior according to the first distance value, or the first distance value and the lane information, wherein the target traffic participant is located in front of the first vehicle or behind the first vehicle, and the first distance value is obtained based on the driving information of the target traffic participant, or is obtained based on the driving information of the target traffic participant and the driving information of the target traffic participant;
and the second control unit is used for controlling the first vehicle to execute target driving behaviors according to the lane information when the number of the target traffic participants is two, wherein one of the two target traffic participants is positioned in front of the first vehicle, and the other target traffic participant is positioned behind the first vehicle.
Wherein the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
Optionally, the first control unit is specifically configured to:
controlling the first vehicle to decelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located in front of the first vehicle;
controlling the first vehicle to accelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located behind the first vehicle.
Optionally, the first control unit is specifically configured to:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located forward of the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid overtaking;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located and a space exists in a second lane based on the lane information, controlling the first vehicle to change lanes or borrow and overtake, wherein the second lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the second lane does not have a space based on the lane information, controlling the first vehicle to brake.
Optionally, the first control unit is specifically configured to:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located behind the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located based on the lane information, and a third lane exists, controlling the first vehicle to change lanes or borrow lanes to avoid, wherein the third lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the third lane does not have a space based on the lane information, controlling the first vehicle to accelerate.
Optionally, the second control unit is specifically configured to:
if it is determined that a lane-changeable lane exists based on the lane information, controlling the first vehicle to change lanes;
and if it is determined that no lane-variable lane exists based on the lane information, controlling the first vehicle to keep the driving state unchanged.
The automatic driving vehicle control device of the embodiment of the invention acquires first driving information of a first vehicle and external environment information around the first vehicle under the condition that the first vehicle drives according to a preset driving route in an automatic driving state, wherein the external environment information comprises driving information and lane information of M traffic participants; then, according to the driving information of N traffic participants in the M traffic participants, obtaining the predicted driving track of each traffic participant in the N traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer; then, determining at least one target traffic participant having collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; finally, the first vehicle is controlled to execute the target driving behavior according to at least one of the first driving information, the driving information of at least one target traffic participant and the lane information, so that the collision risk is judged based on the prediction of the driving track of the traffic participant, the risk pre-judgment execution rule is simple, the driving behavior of the first vehicle can be more reasonably and intelligently controlled according to at least one of the driving information of the target traffic participant with the collision risk, the first driving information of the first vehicle and the lane information around the first vehicle, namely, the driving behavior is considered from multi-dimensional data, the calculation is simple, the method is applicable to all scenes, and the method has better generalization ability.
It should be noted that, the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment and achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are omitted here.
In order to better achieve the above object, as shown in fig. 4, an embodiment of the present invention further provides a cloud device, including a processor 400 and a transceiver 410, where the transceiver 410 receives and transmits data under the control of the processor, and the processor 400 is configured to perform the following processes:
the method comprises the steps that under the condition that a first vehicle runs according to a preset running route in an automatic driving state, first running information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises running information and lane information of M traffic participants;
acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
and controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the information of the lane where the first vehicle is located.
Optionally, the processor 400 is further configured to:
and respectively inputting the historical driving information of each traffic participant in the N traffic participants as input parameters into a pre-trained prediction model to obtain the predicted driving track of each traffic participant.
Optionally, the processor 400 is further configured to:
determining traffic participants corresponding to the predicted driving track intersected with the preset driving route as key traffic participants having collision risks with the first vehicle;
determining at least one target traffic participant based on the key traffic participant.
Optionally, the processor 400 is further configured to:
if the number of the key traffic participants is one, determining the key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are all located in front of the first vehicle or are all located behind the first vehicle, determining the key traffic participants, which are closest to the first vehicle, of the multiple key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are respectively located in front of the first vehicle and behind the first vehicle, determining a first key traffic participant and a second key traffic participant as target traffic participants, wherein the first key traffic participant is a key traffic participant located in front of the first vehicle and closest to the first vehicle, and the second key traffic participant is a key traffic participant located behind the first vehicle and closest to the first vehicle.
Optionally, the processor 400 is further configured to:
obtaining a first distance value between the target traffic participant and the first vehicle if the number of the target traffic participants is one; controlling the first vehicle to execute a target driving behavior according to the first distance value, or the first distance value and the lane information, wherein the target traffic participant is located in front of the first vehicle or behind the first vehicle, and the first distance value is obtained based on the driving information of the target traffic participant, or is obtained based on the driving information of the target traffic participant and the driving information of the target traffic participant;
and under the condition that the number of the target traffic participants is two, controlling the first vehicle to execute target driving behaviors according to the lane information, wherein one of the two target traffic participants is positioned in front of the first vehicle, and the other target traffic participant is positioned behind the first vehicle.
Optionally, the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
Optionally, the processor 400 is further configured to:
controlling the first vehicle to decelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located in front of the first vehicle;
controlling the first vehicle to accelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located behind the first vehicle.
Optionally, the processor 400 is further configured to:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located forward of the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid overtaking;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located and a space exists in a second lane based on the lane information, controlling the first vehicle to change lanes or borrow and overtake, wherein the second lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the second lane does not have a space based on the lane information, controlling the first vehicle to brake.
Optionally, the processor 400 is further configured to:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located behind the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located based on the lane information, and a third lane exists, controlling the first vehicle to change lanes or borrow lanes to avoid, wherein the third lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the third lane does not have a space based on the lane information, controlling the first vehicle to accelerate.
Optionally, the processor 400 is further configured to:
if it is determined that a lane-changeable lane exists based on the lane information, controlling the first vehicle to change lanes;
and if it is determined that no lane-variable lane exists based on the lane information, controlling the first vehicle to keep the driving state unchanged.
According to the cloud device provided by the embodiment of the invention, under the condition that the first vehicle runs according to the preset running route in the automatic driving state, the first running information of the first vehicle and the external environment information around the first vehicle are obtained, wherein the external environment information comprises the running information and the lane information of M traffic participants; then, according to the driving information of N traffic participants in the M traffic participants, obtaining the predicted driving track of each traffic participant in the N traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer; then, determining at least one target traffic participant having collision risk with the first vehicle according to a preset driving route and the predicted driving tracks of the N traffic participants; finally, the first vehicle is controlled to execute the target driving behavior according to at least one of the first driving information, the driving information of at least one target traffic participant and the lane information, so that the collision risk is judged based on the prediction of the driving track of the traffic participant, the risk pre-judgment execution rule is simple, the driving behavior of the first vehicle can be more reasonably and intelligently controlled according to at least one of the driving information of the target traffic participant with the collision risk, the first driving information of the first vehicle and the lane information around the first vehicle, namely, the driving behavior is considered from multi-dimensional data, the calculation is simple, the method is applicable to all scenes, and the method has better generalization ability.
The embodiment of the present invention further provides a cloud device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements each process in the above-described automatic driving vehicle control method embodiment when executing the program, and can achieve the same technical effect, and details are not repeated here to avoid repetition.
Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements each process in the above-described embodiment of the method for controlling an autonomous vehicle, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block or blocks.
These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (14)
1. An autonomous vehicle control method, comprising:
the method comprises the steps that under the condition that a first vehicle runs according to a preset running route in an automatic driving state, first running information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises running information and lane information of M traffic participants;
acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
and controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the lane information.
2. The method according to claim 1, wherein the obtaining the predicted driving track of each of the N traffic participants according to the driving information of the N traffic participants of the M traffic participants comprises:
and respectively inputting the historical driving information of each traffic participant in the N traffic participants as input parameters into a pre-trained prediction model to obtain the predicted driving track of each traffic participant.
3. The method of claim 1, wherein determining at least one target transportation participant at risk of collision with the first vehicle based on the preset travel route and the predicted travel trajectories of the N transportation participants comprises:
determining traffic participants corresponding to the predicted driving track intersected with the preset driving route as key traffic participants having collision risks with the first vehicle;
determining at least one target traffic participant based on the key traffic participant.
4. The method of claim 3, wherein determining at least one target traffic participant based on the key traffic participant comprises:
if the number of the key traffic participants is one, determining the key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are all located in front of the first vehicle or are all located behind the first vehicle, determining the key traffic participants, which are closest to the first vehicle, of the multiple key traffic participants as target traffic participants;
if the number of the key traffic participants is multiple and the key traffic participants are respectively located in front of the first vehicle and behind the first vehicle, determining a first key traffic participant and a second key traffic participant as target traffic participants, wherein the first key traffic participant is a key traffic participant located in front of the first vehicle and closest to the first vehicle, and the second key traffic participant is a key traffic participant located behind the first vehicle and closest to the first vehicle.
5. The method of claim 1, wherein the controlling the first vehicle to perform a target driving behavior based on at least one of the first travel information, the travel information of the at least one target traffic participant, and the information of the lane in which the first vehicle is located comprises:
obtaining a first distance value between the target traffic participant and the first vehicle if the number of the target traffic participants is one; controlling the first vehicle to execute a target driving behavior according to the first distance value, or the first distance value and the lane information, wherein the target traffic participant is located in front of the first vehicle or behind the first vehicle, and the first distance value is obtained based on the driving information of the target traffic participant, or is obtained based on the driving information of the target traffic participant and the driving information of the target traffic participant;
and under the condition that the number of the target traffic participants is two, controlling the first vehicle to execute target driving behaviors according to the lane information, wherein one of the two target traffic participants is positioned in front of the first vehicle, and the other target traffic participant is positioned behind the first vehicle.
6. The method according to claim 4 or 5, characterized in that the first travel information comprises a heading angle of the first vehicle; the front of the first vehicle is an area with a reference line facing the course angle of the first vehicle, the rear of the first vehicle is the opposite direction of the front of the first vehicle, and the reference line is a straight line which passes through the center of mass of the first vehicle and is perpendicular to the course angle of the first vehicle.
7. The method of claim 5, wherein said controlling the first vehicle to perform a target driving behavior based on the first distance value comprises:
controlling the first vehicle to decelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located in front of the first vehicle;
controlling the first vehicle to accelerate if the first distance value is greater than a first preset threshold and the target traffic participant is located behind the first vehicle.
8. The method of claim 5, wherein the controlling the first vehicle to perform a target driving behavior based on the first distance value and the lane information comprises:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located forward of the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid overtaking;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located and a space exists in a second lane based on the lane information, controlling the first vehicle to change lanes or borrow and overtake, wherein the second lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the second lane does not have a space based on the lane information, controlling the first vehicle to brake.
9. The method of claim 5, wherein the controlling the first vehicle to perform a target driving behavior based on the first distance value and the lane information comprises:
in the event that the first distance value is less than or equal to a first preset threshold and the target traffic participant is located behind the first vehicle,
if the fact that an avoidance space exists in a first lane where the first vehicle is located is determined based on the lane information, the first vehicle is controlled to avoid;
if it is determined that an avoidance space does not exist in a first lane where the first vehicle is located based on the lane information, and a third lane exists, controlling the first vehicle to change lanes or borrow lanes to avoid, wherein the third lane is a lane adjacent to the first lane;
and if it is determined that the first lane where the first vehicle is located does not have an avoidance space and the third lane does not have a space based on the lane information, controlling the first vehicle to accelerate.
10. The method of claim 5, wherein the controlling the first vehicle to perform a target driving behavior based on the lane information comprises:
if it is determined that a lane-changeable lane exists based on the lane information, controlling the first vehicle to change lanes;
and if it is determined that no lane-variable lane exists based on the lane information, controlling the first vehicle to keep the driving state unchanged.
11. An autonomous vehicle control apparatus, characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring first running information of a first vehicle and external environment information around the first vehicle under the condition that the first vehicle runs according to a preset running route in an automatic driving state, and the external environment information comprises running information and lane information of M traffic participants;
the second acquisition module is used for acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
the processing module is used for determining at least one target traffic participant having collision risk with the first vehicle according to the preset running route and the predicted running tracks of the N traffic participants;
and the control module is used for controlling the first vehicle to execute the target driving behavior according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the lane information.
12. A cloud device comprising a processor and a transceiver, the transceiver receiving and transmitting data under control of the processor, wherein the processor is configured to:
the method comprises the steps that under the condition that a first vehicle runs according to a preset running route in an automatic driving state, first running information of the first vehicle and external environment information around the first vehicle are obtained, wherein the external environment information comprises running information and lane information of M traffic participants;
acquiring the predicted driving track of each traffic participant in the N traffic participants according to the driving information of the N traffic participants in the M traffic participants, wherein M is more than or equal to N and is more than or equal to 1, and M, N is a positive integer;
determining at least one target traffic participant having a collision risk with the first vehicle according to the preset driving route and the predicted driving tracks of the N traffic participants;
and controlling the first vehicle to execute target driving behaviors according to at least one item of the first driving information, the driving information of the at least one target traffic participant and the information of the lane where the first vehicle is located.
13. A cloud device comprising a memory, a processor, and a program stored on the memory and executable on the processor; characterized in that the processor, when executing the program, implements the autonomous vehicle control method according to any one of claims 1 to 10.
14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps in the autonomous vehicle control method of any one of claims 1 to 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110208312.1A CN113071487B (en) | 2021-02-24 | 2021-02-24 | Automatic driving vehicle control method and device and cloud equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110208312.1A CN113071487B (en) | 2021-02-24 | 2021-02-24 | Automatic driving vehicle control method and device and cloud equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113071487A true CN113071487A (en) | 2021-07-06 |
CN113071487B CN113071487B (en) | 2022-02-18 |
Family
ID=76609554
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110208312.1A Active CN113071487B (en) | 2021-02-24 | 2021-02-24 | Automatic driving vehicle control method and device and cloud equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113071487B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113628444A (en) * | 2021-08-12 | 2021-11-09 | 智道网联科技(北京)有限公司 | Method, device and computer-readable storage medium for prompting traffic risk |
CN113963537A (en) * | 2021-10-19 | 2022-01-21 | 东软睿驰汽车技术(上海)有限公司 | Vehicle track prediction method for intersection and related device |
CN114194201A (en) * | 2021-12-28 | 2022-03-18 | 中国第一汽车股份有限公司 | Vehicle control method and device, electronic equipment and storage medium |
CN115277767A (en) * | 2022-07-22 | 2022-11-01 | 联想(北京)有限公司 | Internet of vehicles data processing method and device and electronic equipment |
WO2023087524A1 (en) * | 2021-11-18 | 2023-05-25 | 上海仙途智能科技有限公司 | Vehicle travelling method and apparatus |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109737977A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Automatic driving vehicle localization method, device and storage medium |
CN110164183A (en) * | 2019-05-17 | 2019-08-23 | 武汉理工大学 | A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic |
CN110751847A (en) * | 2019-10-15 | 2020-02-04 | 清华大学 | Decision-making method and system for automatically driving vehicle behaviors |
CN110834644A (en) * | 2019-10-30 | 2020-02-25 | 中国第一汽车股份有限公司 | Vehicle control method and device, vehicle to be controlled and storage medium |
CN111559388A (en) * | 2020-03-26 | 2020-08-21 | 吉利汽车研究院(宁波)有限公司 | Target vehicle screening method, device, equipment and storage medium |
-
2021
- 2021-02-24 CN CN202110208312.1A patent/CN113071487B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109737977A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Automatic driving vehicle localization method, device and storage medium |
CN110164183A (en) * | 2019-05-17 | 2019-08-23 | 武汉理工大学 | A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic |
CN110751847A (en) * | 2019-10-15 | 2020-02-04 | 清华大学 | Decision-making method and system for automatically driving vehicle behaviors |
CN110834644A (en) * | 2019-10-30 | 2020-02-25 | 中国第一汽车股份有限公司 | Vehicle control method and device, vehicle to be controlled and storage medium |
CN111559388A (en) * | 2020-03-26 | 2020-08-21 | 吉利汽车研究院(宁波)有限公司 | Target vehicle screening method, device, equipment and storage medium |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113628444A (en) * | 2021-08-12 | 2021-11-09 | 智道网联科技(北京)有限公司 | Method, device and computer-readable storage medium for prompting traffic risk |
CN113963537A (en) * | 2021-10-19 | 2022-01-21 | 东软睿驰汽车技术(上海)有限公司 | Vehicle track prediction method for intersection and related device |
WO2023087524A1 (en) * | 2021-11-18 | 2023-05-25 | 上海仙途智能科技有限公司 | Vehicle travelling method and apparatus |
CN114194201A (en) * | 2021-12-28 | 2022-03-18 | 中国第一汽车股份有限公司 | Vehicle control method and device, electronic equipment and storage medium |
CN115277767A (en) * | 2022-07-22 | 2022-11-01 | 联想(北京)有限公司 | Internet of vehicles data processing method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113071487B (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113071487B (en) | Automatic driving vehicle control method and device and cloud equipment | |
CN110562258B (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
CN109863513B (en) | Neural network system for autonomous vehicle control | |
US10496099B2 (en) | Systems and methods for speed limit context awareness | |
US10829116B2 (en) | Affecting functions of a vehicle based on function-related information about its environment | |
US11702070B2 (en) | Autonomous vehicle operation with explicit occlusion reasoning | |
CN109643118B (en) | Influencing a function of a vehicle based on function-related information about the environment of the vehicle | |
EP3802259A1 (en) | Time-warping for autonomous driving simulation | |
Chae et al. | Virtual target-based overtaking decision, motion planning, and control of autonomous vehicles | |
CN113085852A (en) | Behavior early warning method and device for automatic driving vehicle and cloud equipment | |
EP4222036A1 (en) | Methods and systems for predicting actions of an object by an autonomous vehicle to determine feasible paths through a conflicted area | |
US11731630B2 (en) | Methods and systems for asserting right of way for traversing an intersection | |
US11615702B2 (en) | Determining vehicle path | |
US20220340138A1 (en) | Methods and systems for generating trajectory of an autonomous vehicle for traversing an intersection | |
US11643105B2 (en) | Systems and methods for generating simulation scenario definitions for an autonomous vehicle system | |
JP2022041923A (en) | Vehicle path designation using connected data analysis platform | |
Guo et al. | Self-defensive coordinated maneuvering of an intelligent vehicle platoon in mixed traffic | |
Siboo et al. | An empirical study of ddpg and ppo-based reinforcement learning algorithms for autonomous driving | |
CN113460083A (en) | Vehicle control device, vehicle control method, and storage medium | |
CN115136081A (en) | Method for training at least one algorithm for a controller of a motor vehicle, method for optimizing a traffic flow in a region, computer program product and motor vehicle | |
WO2023177969A1 (en) | Method and system for assessing whether a vehicle is likely to leave an off-road parking area | |
CN113525413B (en) | Vehicle control device, vehicle control method, and storage medium | |
CN113460079A (en) | Vehicle control device, vehicle control method, and storage medium | |
CN117944684B (en) | Track changing planning method and device, storage medium and electronic equipment | |
US20240190452A1 (en) | Methods and systems for handling occlusions in operation of autonomous vehicle |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |