CN114475653B - Vehicle emergency steering simulation scene configuration method and device - Google Patents
Vehicle emergency steering simulation scene configuration method and device Download PDFInfo
- Publication number
- CN114475653B CN114475653B CN202111635771.4A CN202111635771A CN114475653B CN 114475653 B CN114475653 B CN 114475653B CN 202111635771 A CN202111635771 A CN 202111635771A CN 114475653 B CN114475653 B CN 114475653B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- value
- time
- steering wheel
- acceleration
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000004088 simulation Methods 0.000 title claims abstract description 45
- 230000001133 acceleration Effects 0.000 claims abstract description 157
- 238000012360 testing method Methods 0.000 claims abstract description 99
- 230000008859 change Effects 0.000 claims abstract description 47
- 230000008569 process Effects 0.000 claims abstract description 38
- 238000010009 beating Methods 0.000 claims description 11
- 230000036461 convulsion Effects 0.000 claims description 3
- 230000003139 buffering effect Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/007—Emergency override
-
- 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
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/18—Steering angle
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention relates to a vehicle emergency steering simulation scene configuration method and device, wherein the method comprises the following steps: obtaining drive test data in the running process of the vehicle; identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point; when the fact that the vehicle does not belong to the lane change state before the first time point is determined, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; and determining target drive test data according to the first time point and the second time point, and configuring a vehicle emergency steering simulation scene according to the target drive test data. The method and the device improve the accuracy of identifying the emergency steering scene, greatly reduce the degree of human participation, and reduce the scene uncertainty caused by subjective factors of annotators.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicles, in particular to a vehicle emergency steering simulation scene configuration method and device.
Background
Autonomous vehicles may take some action of emergency avoidance, including emergency steering, because of perceived or predicted danger. However, emergency steering not only causes discomfort to passengers in the vehicle, but also is more likely to cause serious accidents. Therefore, it is desirable to simulate the emergency steering scenario of a vehicle, and to improve the ability of the vehicle to handle emergency steering events based on a large number of simulation tests.
The simulation by using the drive test data is a common simulation mode in automatic driving, and the simulation is performed on the emergency steering scene, so that the data related to the emergency steering scene needs to be found out from massive drive test data.
In conventional approaches, it is often necessary for a labeling person to identify data about an emergency diversion scenario from complete drive test data, and then manually configure the critical time for the scenario. This process takes a lot of manpower and the accuracy of identifying critical times for emergency steering scenarios and configuration scenarios depends on the experience of the annotators. Along with the rapid expansion of the drive test scale and the great difficulty in unified training of the annotators, the number and the quality of scenes are limited by subjective factors such as experience level of the annotators.
Therefore, the conventional method for configuring the emergency steering simulation scene also has the problems of high labor cost, low scene identification accuracy and limitation by subjective factors of annotators.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, a first aspect of the present invention proposes a vehicle emergency steering simulation scene configuration method, the method comprising:
the method comprises the steps of obtaining drive test data in the running process of a vehicle, wherein the drive test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle;
identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point;
when the fact that the vehicle does not belong to the lane change state before the first time point is determined, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; the target time period is a time period with a time difference of a preset first threshold value from the first time point;
Judging whether the emergency steering wheel event belongs to an emergency steering scene of the unmanned vehicle according to the lane line information and the control state information corresponding to the second time point;
if yes, determining target drive test data based on the first time point and the second time point, and configuring an emergency steering simulation scene of the unmanned vehicle according to the target drive test data.
Optionally, the acceleration information includes a time stamp, and an acceleration value and an acceleration direction corresponding to the time stamp, and the identifying, according to the acceleration information of the vehicle, an emergency braking event of the vehicle in a running process includes:
acquiring an acceleration value of which the acceleration direction is opposite to the vehicle advancing direction, and obtaining a first acceleration value;
determining whether a target first acceleration value exists, wherein the target first acceleration value is a first acceleration value which is larger than or equal to a preset minimum effective acceleration value;
if so, determining that the vehicle has an emergency braking event in the driving process.
Optionally, the determining the starting time point corresponding to the emergency braking event includes:
according to the sequence of the time stamps, the first acceleration values at all moments are put into a set to obtain a first acceleration set;
Traversing the first acceleration set in a reverse direction starting from a largest first acceleration value in the first acceleration set;
in the traversing process, if the traversed acceleration value is greater than or equal to the preset minimum effective acceleration value, the value of the counter is increased by one, and the reverse traversing is continued; if the traversed acceleration value is smaller than the minimum effective acceleration value, resetting a counter, continuing to traverse reversely until the value of the counter is larger than the preset buffer time, and ending the traversal;
and determining the difference value between the time stamp corresponding to the last traversed acceleration value and the current numerical value of the counter as the starting time point of the emergency braking event.
Optionally, the identifying the emergency steering wheel event of the vehicle according to the steering wheel angle information of the vehicle in the target time period includes:
acquiring steering wheel angle values of the vehicle at various moments in the target time period;
determining steering wheel angle values corresponding to all the moments according to the steering wheel angle values, wherein the steering angle values are differences between the steering wheel angle values at the previous moment and the steering wheel angle values at the next moment;
Determining a predicted value of the steering wheel angle value at the next moment according to the steering wheel angle value before the previous moment;
acquiring a true value of the steering wheel angle at the next moment;
determining an absolute value of a difference between the predicted value and the true value to obtain an absolute rotation angle difference value, and determining a quotient between the absolute rotation angle difference value and the true value to obtain a rotation angle quotient;
and if the absolute steering angle difference value is larger than a preset minimum hard steering error value and the steering angle quotient is larger than a preset minimum hard steering rate, determining that the vehicle has a sudden steering wheel event at the next moment.
Optionally, the determining, according to the steering wheel angle value before the previous time, the predicted value of the steering wheel angle value at the next time includes:
is determined to be at (t-t) w ) In the time period between the moment and the t moment, the difference value between the steering wheel angles at every two adjacent moments; wherein the time t is the last time, the time (t+1) is the next time, and the time t is w The window time is preset;
determining the average value of the difference values to obtain an average difference value;
obtaining said (t-t) w ) The steering wheel angle value at the moment is obtained and (t w +1) the steering wheel angle value at the moment, respectively obtaining a first angle value and a second angle value;
calculating the product between the second rotation angle value and the average difference value to obtain a first product;
and taking the sum of the first rotation angle value and the first product as a predicted value of the steering wheel rotation angle at the time of (t+1).
Optionally, the road test data further includes lane change status data of the vehicle, and after determining the starting time point corresponding to the emergency braking event, the road test data further includes:
and determining whether the vehicle belongs to the lane change state before the first time point according to the lane change state data.
Optionally, the determining whether the emergency steering wheel event belongs to an emergency steering scene according to the lane line information and the control state information corresponding to the second time point includes:
judging whether the vehicle meets a first condition and a second condition according to the control state information and the lane line information corresponding to the second time point, wherein the first condition is that the vehicle is in an unmanned state at the second time point, and the second condition is that the vehicle runs at the center of a lane at the second time point;
and if the vehicle meets the first condition and the second condition at the same time, determining that the emergency steering wheel event belongs to an emergency steering scene.
Optionally, the determining the target drive test data according to the first time point and the second time point includes:
determining the starting time of the emergency steering scene according to the first time point and a preset first buffer time;
determining the ending time of the emergency steering scene according to the first time point and a preset second buffer time;
and obtaining drive test data between the starting time of the emergency steering scene and the ending time of the emergency steering scene to obtain target drive test data.
Optionally, the drive test data further includes obstacle information around the vehicle at each time, the obstacle information including position information of the obstacle, and the method further includes:
acquiring the obstacle information from drive test data in a preset time period before the first time point;
determining target obstacle information from the obstacle information according to the position and size information of the obstacle; the target obstacle information is an obstacle which is the same lane as the vehicle or adjacent to the vehicle and has a distance from the vehicle smaller than a preset distance threshold;
and configuring a vehicle emergency steering simulation scene according to the target drive test data and the target obstacle information.
The invention provides a vehicle emergency steering simulation scene configuration device in a second direction, which comprises:
the drive test data acquisition module is used for acquiring drive test data in the running process of the vehicle, wherein the drive test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle;
the emergency brake identification module is used for identifying an emergency brake event of the vehicle in the running process according to the acceleration information of the vehicle, determining a starting time point corresponding to the emergency brake event and obtaining a first time point;
the rapid-beating direction identification module is used for identifying a rapid-beating steering wheel event of the vehicle according to the steering wheel angle information of the vehicle in a target time period when the vehicle is determined not to belong to a lane change state before the first time point, and acquiring a time point corresponding to the rapid-beating steering wheel event to obtain a second time point; the target time period is a time period with a time difference of a preset first threshold value from the first time point;
the scene determining module is used for determining whether the emergency steering wheel event belongs to an emergency steering scene of the unmanned vehicle according to the lane line information and the control state information corresponding to the second time point;
And the first scene configuration module is used for determining target drive test data based on the first time point and the second time point if yes, and configuring an emergency steering simulation scene of the unmanned vehicle according to the target drive test data.
Optionally, the acceleration information includes a time stamp, and an acceleration value and an acceleration direction corresponding to the time stamp, and the emergency brake identification module is specifically configured to:
acquiring an acceleration value of which the acceleration direction is opposite to the vehicle advancing direction, and obtaining a first acceleration value;
determining whether a target first acceleration value exists, wherein the target first acceleration value is a first acceleration value which is larger than or equal to a preset minimum effective acceleration value;
if so, determining that the vehicle has an emergency braking event in the driving process.
Optionally, the emergency brake identification module is specifically configured to:
according to the sequence of the time stamps, the first acceleration values at all moments are put into a set to obtain a first acceleration set;
traversing the first acceleration set in a reverse direction starting from a largest first acceleration value in the first acceleration set;
in the traversing process, if the traversed acceleration value is greater than or equal to the preset minimum effective acceleration value, the value of the counter is increased by one, and the reverse traversing is continued; if the traversed acceleration value is smaller than the minimum effective acceleration value, resetting a counter, continuing to traverse reversely until the value of the counter is larger than the preset buffer time, and ending the traversal;
And determining the difference value between the time stamp corresponding to the last traversed acceleration value and the current numerical value of the counter as the starting time point of the emergency braking event.
Optionally, the rapid beating direction identification module is specifically configured to:
acquiring steering wheel angle values of the vehicle at various moments in the target time period;
determining steering wheel angle values corresponding to all the moments according to the steering wheel angle values, wherein the steering angle values are differences between the steering wheel angle values at the previous moment and the steering wheel angle values at the next moment;
determining a predicted value of the steering wheel angle value at the next moment according to the steering wheel angle value before the previous moment;
acquiring a true value of the steering wheel angle at the next moment;
determining an absolute value of a difference between the predicted value and the true value to obtain an absolute rotation angle difference value, and determining a quotient between the absolute rotation angle difference value and the true value to obtain a rotation angle quotient;
and if the absolute steering angle difference value is larger than a preset minimum hard steering error value and the steering angle quotient is larger than a preset minimum hard steering rate, determining that the vehicle has a sudden steering wheel event at the next moment.
Optionally, the rapid beating direction identification module is specifically configured to:
is determined to be at (t-t) w ) In the time period between the moment and the t moment, the difference value between the steering wheel angles at every two adjacent moments; wherein the time t is the last time, the time (t+1) is the next time, and the time t is w The window time is preset;
determining the average value of the difference values to obtain an average difference value;
obtaining said (t-t) w ) The steering wheel angle value at the moment is obtained and (t w +1) the steering wheel angle value at the moment, respectively obtaining a first angle value and a second angle value;
calculating the product between the second rotation angle value and the average difference value to obtain a first product;
and taking the sum of the first rotation angle value and the first product as a predicted value of the steering wheel rotation angle at the time of (t+1).
Optionally, the drive test data further includes lane change status data of the vehicle, and the apparatus further includes:
and the lane change state determining module is used for determining whether the vehicle belongs to a lane change state before the first time point according to the lane change state data.
Optionally, the scene determination module is specifically configured to:
judging whether the vehicle meets a first condition and a second condition according to the control state information and the lane line information corresponding to the second time point, wherein the first condition is that the vehicle is in an unmanned state at the second time point, and the second condition is that the vehicle runs at the center of a lane at the second time point;
And if the vehicle meets the first condition and the second condition at the same time, determining that the emergency steering wheel event belongs to an emergency steering scene.
Optionally, the scene configuration module is specifically configured to:
determining the starting time of the emergency steering scene according to the first time point and a preset first buffer time;
determining the ending time of the emergency steering scene according to the first time point and a preset second buffer time;
and obtaining drive test data between the starting time of the emergency steering scene and the ending time of the emergency steering scene to obtain target drive test data.
Optionally, the drive test data further includes obstacle information around the vehicle at each time, the obstacle information including position information of the obstacle, and the apparatus further includes:
the obstacle information acquisition module is used for acquiring the obstacle information from the road test data in a preset time period before the first time point;
a target information determining module, configured to determine target obstacle information from the obstacle information according to the position and size information of the obstacle; the target obstacle information is an obstacle which is the same lane as the vehicle or adjacent to the vehicle and has a distance from the vehicle smaller than a preset distance threshold;
And the second scene configuration module is used for configuring a vehicle emergency steering simulation scene according to the target drive test data and the target obstacle information.
A third aspect of the present invention proposes an apparatus comprising a processor and a memory storing at least one instruction, at least one program, a set of codes or a set of instructions, the at least one instruction, the at least one program, the set of codes or the set of instructions being loaded and executed by the processor to implement the vehicle emergency steering simulation scenario configuration method according to the first aspect.
A fourth aspect of the present invention proposes a computer readable storage medium having stored therein at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement the vehicle emergency steering simulation scenario configuration method according to the first aspect.
According to the specific embodiment provided by the invention, the invention has the following technical effects:
the vehicle emergency steering scene configuration method provided by the embodiment of the invention obtains the drive test data in the running process of the vehicle; identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point; when the fact that the vehicle does not belong to the lane change state before the first time point is determined, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; judging whether the emergency braking event and the emergency steering wheel event belong to an emergency steering scene or not according to lane line information and control state information corresponding to the second time point; if yes, determining target drive test data according to the first time point and the second time point, and configuring a vehicle emergency steering simulation scene according to the target drive test data. According to the scheme, an accurate algorithm is adopted to identify the emergency steering scene, a key time point corresponding to the emergency steering scene is automatically found, and target drive test data are determined from massive drive test data according to the key time point, so that accuracy of identifying the emergency steering scene and configuring key time of the scene is improved; in addition, the standardized scene is generated by using the standardized algorithm and the standardized flow, so that the degree of human participation is greatly reduced, and the scene uncertainty caused by subjective factors of annotators is reduced.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the following description will make a brief introduction to the drawings used in the description of the embodiments or the prior art. It should be apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained from these drawings without inventive effort to those of ordinary skill in the art.
FIG. 1 is a flow chart of steps of a method for configuring a simulated scene of emergency steering of a vehicle according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of another method for configuring a simulated scene of vehicle emergency steering according to an embodiment of the present invention;
fig. 3 is a block diagram of a vehicle emergency steering simulation scene configuration device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of a vehicle emergency steering scene configuration method according to an embodiment of the present invention. The present specification provides method operational steps as described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment).
The method may comprise the steps of:
step 101, road test data in the running process of a vehicle are obtained, wherein the road test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle.
The drive test data refers to measurement data obtained during actual running of the vehicle on the road. A visual sensor, a radar sensor and the like are arranged on a vehicle, the triggering period of the sensor is set, the sensor sends a detection signal according to the triggering period, and measurement results corresponding to all moments can be obtained.
The measurement results at least comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle.
The control state of the vehicle refers to an unmanned state or a manned state of the vehicle.
Step 102, identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point.
In general, when a vehicle suddenly finds an obstacle ahead, an emergency steering occurs, and an emergency steering scene generally includes an emergency braking event and a sudden steering wheel event, so the emergency braking event and the sudden steering wheel event are first identified from the drive test data.
When the vehicle is braked in an emergency, the acceleration direction of the vehicle is opposite to the advancing direction of the vehicle, and the acceleration value is larger. Searching whether acceleration values larger than or equal to a preset threshold value exist in acceleration information opposite to the advancing direction of the vehicle, and if so, the time periods corresponding to the acceleration values are time periods when an emergency braking event occurs.
Further, a starting time point corresponding to the emergency braking event is determined, and for convenience of description, the starting time point is referred to as a first time point.
If no emergency braking event is identified from the current lot of road test data according to the acceleration information of the vehicle, no emergency steering scene exists in the section of road test data, and the next lot of road test data is identified again.
Step 103, when it is determined that the vehicle does not belong to the lane change state before the first time point, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; the target time period is a time period of which the time difference from the first time point is a preset first threshold value.
The emergency steering scene has an emergency attribute, namely emergency braking happens suddenly, and the vehicle does not belong to a lane change state before emergency braking, so that the emergency attribute can be described.
Therefore, it is also necessary to determine whether the vehicle is in a lane change state before the first point in time. If the vehicle belongs to the lane change state, the situation that the vehicle possibly finds an obstacle in front before emergency braking and starts lane change response is explained, and the situation does not belong to an emergency steering scene. If the vehicle does not belong to a lane change state prior to the emergency brake, it is stated that the vehicle may not find a forward obstacle condition prior to the emergency brake, and the emergency brake event is part of an emergency steering scenario.
Thus, after determining that the vehicle did not belong to the lane change state before the first point in time, a further step of identifying the emergency steering scenario is performed, i.e. identifying whether a jerk steering event occurred within the target period of time.
The steering wheel angle is changed greatly in a short time. Also, in emergency steering scenarios, a hard-drive steering wheel event typically occurs before and after an emergency brake. Therefore, whether a sudden steering event occurs in the vehicle can be identified based on the steering wheel angle information of the vehicle in the target period.
The target time period is a time period that is closer to the first time point, a first threshold may be preset, and a time period that is a time difference from the first time point is the first threshold is determined as the target time period.
Further, a time point corresponding to the emergency steering wheel event is obtained, and a second time point is obtained.
If the vehicle is determined to be in the lane change state before the first time point or the emergency braking event is not identified in the target time period, determining that the emergency steering scene does not exist in the road test data, and identifying the next batch of road test data again.
And 104, judging whether the emergency steering wheel event belongs to an emergency steering scene according to the lane line information and the control state information corresponding to the second time point.
In the unmanned vehicle, the emergency steering scene is judged, and when the second time point is needed to be determined, whether the vehicle is in an unmanned state or not, and whether the vehicle is in the middle of a lane line or not at the second time point is determined, and only then, the emergency steering scene which occurs under the condition of the unmanned vehicle can be determined.
And 105, if so, determining target drive test data based on the first time point and the second time point, and configuring a vehicle emergency steering simulation scene according to the target drive test data.
The first time point is the starting event of emergency braking, the second time point is the occurrence time of emergency steering wheel, the starting time and the ending time of the emergency steering scene are determined according to the two time points, and the road test data between the starting time and the ending time are further obtained and used as target road test data.
And then, configuring the emergency steering simulation scene of the vehicle by using the target drive test data.
Optionally, the drive test data further includes obstacle information around the vehicle at each moment, the obstacle information includes position information of the obstacle, and the vehicle emergency steering simulation scene configuration method further includes the following steps A1-A3:
a1, acquiring the obstacle information from drive test data in a preset time period before the first time point;
a2, determining target obstacle information from the obstacle information according to the position and the size information of the obstacle; the target obstacle information is an obstacle which is the same lane as the vehicle or adjacent to the vehicle and has a distance from the vehicle smaller than a preset distance threshold;
A3, configuring a vehicle emergency steering simulation scene according to the target drive test data and the target obstacle information.
In steps A1-A3, the emergency steering scenario generally occurs when the unmanned vehicle suddenly finds an obstacle, so, in order to better simulate the emergency steering scenario, the response capability of the unmanned vehicle to the obstacle is trained, and the visual sensor can be used to acquire the obstacle information around the vehicle in the drive test.
Specifically, an object having a size larger than a preset standard size may be defined as an obstacle.
And obtaining drive test data in a preset time period before the first time point, and searching for target obstacle information from the drive test data. The target obstacle is an object that may cause the vehicle to turn in an emergency, and thus, the target obstacle is an obstacle that is the same lane as or adjacent to the vehicle and has a distance from the vehicle that is less than a preset distance threshold.
Therefore, the target obstacle information can be added into the emergency steering simulation scene, so that the reality of the scene is improved, the training data of the unmanned vehicle is increased, and the strain capacity of an algorithm is further improved.
According to the embodiment of the invention, the degree of human participation in the scene configuration process is greatly reduced, and the scene conversion efficiency is improved; and a standardized scene can be generated by using a standardized algorithm and a standardized flow, so that scene uncertainty caused by subjective factors of annotators is reduced.
In summary, the vehicle emergency steering scene configuration method provided by the embodiment of the invention acquires drive test data in the running process of the vehicle; identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point; when the fact that the vehicle does not belong to the lane change state before the first time point is determined, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; judging whether the emergency braking event and the emergency steering wheel event belong to an emergency steering scene or not according to lane line information and control state information corresponding to the second time point; if yes, determining target drive test data according to the first time point and the second time point, and configuring a vehicle emergency steering simulation scene according to the target drive test data. According to the scheme, an accurate algorithm is adopted to identify the emergency steering scene, a key time point corresponding to the emergency steering scene is automatically found, and target drive test data are determined from massive drive test data according to the key time point, so that accuracy of identifying the emergency steering scene and configuring key time of the scene is improved; in addition, the standardized scene is generated by using the standardized algorithm and the standardized flow, so that the degree of human participation is greatly reduced, and the scene uncertainty caused by subjective factors of annotators is reduced.
Fig. 2 is a flowchart of another vehicle emergency steering simulation scene configuration method according to an embodiment of the present invention.
Step 201, road test data in the running process of a vehicle is obtained, wherein the road test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle.
In the embodiment of the present invention, step 201 may refer to step 101, which is not described herein.
Step 202, obtaining an acceleration value of which the acceleration direction is opposite to the vehicle advancing direction, and obtaining a first acceleration value.
The acceleration information in the drive test data comprises a time stamp, and an acceleration value and an acceleration direction corresponding to the time stamp.
When the vehicle is braked in an emergency, the acceleration direction of the vehicle is opposite to the vehicle advancing direction, so that an acceleration value opposite to the vehicle advancing direction is obtained from the acceleration information to obtain a first acceleration value. An emergency braking event may subsequently be identified based on the first acceleration value.
Step 203, determining whether a target first acceleration value exists, wherein the target first acceleration value is a first acceleration value which is greater than or equal to a preset minimum effective acceleration value.
And presetting a minimum effective acceleration value which is the maximum value of normal acceleration of the vehicle, and when the vehicle acceleration exceeds the maximum value, indicating that the vehicle is braked emergently.
Step 204, if yes, determining that an emergency braking event occurs in the running process of the vehicle.
If the target first acceleration value exists, the vehicle is indicated to have emergency braking, if the target first acceleration value does not exist, the vehicle is indicated to have no emergency braking, and no emergency steering scene exists in the batch test data.
Step 205, putting the first acceleration values at each moment into a set according to the sequence of the time stamps, so as to obtain a first acceleration set.
Steps 205-208 are steps of determining a starting point in time of an emergency braking event. Assuming that from time 0 to time n, the first acceleration value at each time is a 0 、a 1 、a 2 、……a n Then the first set of accelerations is a= [ a ] 0 ,a 1 ,a 2 ,…,a n ]。
Step 206, starting from the largest first acceleration value in the first acceleration set, traversing the first acceleration set reversely.
Assuming that the acceleration value at time t is maximum, the time t is an emergency brake, and in order to find the starting time of the emergency brake, the acceleration value at time t is equal to the starting time of the emergency brake t Reverse traversal of set a begins.
Step 207, in the traversal process, if the traversed acceleration value is greater than or equal to the preset minimum effective acceleration value, the value of the counter is increased by one, and the reverse traversal is continued; and if the traversed acceleration value is smaller than the minimum effective acceleration value, resetting the counter, continuing to traverse reversely until the value of the counter is larger than the preset buffer time, and ending the traversal.
The emergency braking is generally performed by continuously braking for a plurality of times, and the obtained acceleration curve is in a plurality of wave shapes, so that if the acceleration of a certain frame is found to be smaller, the whole emergency braking process is not necessarily ended. Thus, a counter may be provided which only considers the complete emergency braking process to be completed after the acceleration has been reduced beyond the buffer time. Presetting a counter which starts timing from 0 and assumes that the current value of the counter ist keep . Further, a minimum effective acceleration value Min Effective Acc and a buffer time buffer are set in advance. When the value of the counter is greater than the buffering time, the emergency braking process is considered to be ended.
Specifically, during the traversal, if the acceleration value a is traversed i If the value of the counter is less than Min Effective Acc, the acceleration of the vehicle is smaller and does not belong to the acceleration range corresponding to emergency braking, and the value of the counter is increased by 1, namely t keep =t keep +1, then the reverse traversal continues.
When the value of the counter is greater than the buffering time, i.e. t keep If the buffer is greater, the whole emergency braking process is considered to be ended, and i-t is calculated keep As the starting time for emergency braking.
If t keep If the buffer is less than the buffer, the reverse traversal is continued, namely traversal a i-1 If a i-1 And Min Effective Acc, repeating the steps. If a is i-1 Not less than Min Effective Acc, the counter is set to 0, i.e. t keep =0, and the timing is restarted.
In an implementation, generally Min Effective Acc takes 0.1m/s 2 Buffer fetch 5.
Step 208, determining the difference between the time stamp corresponding to the last traversed acceleration value and the current value of the counter as the starting time point of the emergency braking event.
If the timestamp corresponding to the last traversed acceleration value is i, the current value of the counter is t keep Will i-t keep As the starting time for emergency braking.
In the steps 205-208, the first acceleration set is traversed reversely from the largest first acceleration value in the first acceleration set, whether the traversing operation is continued is determined according to the counter and the buffer value, so that whether the emergency braking is ended is determined, and the starting time of the emergency braking is further determined, wherein whether the traversing operation is continued is determined according to the counter and the buffer value, the situation that the acceleration rate is changed in a curve in a plurality of continuous braking is fully considered, and the obtained starting time of the emergency braking is more scientific and accurate.
Step 209, determining whether the vehicle belongs to a lane change state before the first time point according to the lane change state data.
The emergency steering scene has an emergency attribute, namely emergency braking happens suddenly, and the vehicle does not belong to a lane change state before emergency braking, so that the emergency attribute can be described.
Therefore, it is also necessary to determine whether the vehicle is in a lane change state before the first point in time. If the vehicle belongs to the lane change state, the situation that the vehicle possibly finds an obstacle in front before emergency braking and starts lane change response is explained, and the situation does not belong to an emergency steering scene. If the vehicle does not belong to a lane change state prior to the emergency brake, it is stated that the vehicle may not find a forward obstacle condition prior to the emergency brake, and the emergency brake event is part of an emergency steering scenario.
The road test data also comprises lane change state data of the vehicle, so that whether the vehicle belongs to the lane change state before the first time point can be directly determined according to the lane change state data.
Step 210, when it is determined that the vehicle does not belong to the lane change state before the first time point, obtaining steering wheel angle values of the vehicle at various moments in the target time period.
After determining that the vehicle does not belong to the lane change state before the first time point, performing a step of further identifying the emergency steering scene, namely identifying whether the emergency steering wheel event occurs in the target time period.
The steering wheel angle is changed greatly in a short time. Also, in emergency steering scenarios, a hard-drive steering wheel event typically occurs before and after an emergency brake. Therefore, the steering wheel angle value of the vehicle at each moment in the target time period can be obtained, and whether the emergency steering wheel event occurs to the vehicle is further identified according to the steering wheel angle value.
Step 211, determining steering wheel angle values corresponding to the respective moments according to the steering wheel angle values, wherein the steering angle values are differences between the steering wheel angle values at the previous moment and the steering wheel angle values at the next moment.
Under normal conditions, the angle of the steering wheel is changed between the last moment and the next moment, but the change degree is within a certain range, but when the steering wheel is suddenly driven, the change degree of the angle of the steering wheel between the last moment and the next moment is very large, so that whether the emergency driving steering wheel event occurs can be determined according to the change degree of the angle of the steering wheel.
Specifically, a steering wheel angle value corresponding to each moment is determined, and the steering angle value is a difference value between the steering wheel angle at the previous moment and the steering wheel angle at the next moment, namely, the degree of change of the steering wheel angle.
Step 212, determining a predicted value of the steering wheel angle value at the next moment according to the steering wheel angle value before the previous moment.
The average difference between the steering wheel angle value at the previous time and the steering wheel angle value at the next time under normal conditions can be calculated, and then the steering wheel angle value at the next time can be predicted by the steering wheel angle value before the previous time.
Therefore, the predicted value of the steering wheel angle value at the next time under normal conditions can be determined based on the steering wheel angle value before the previous time.
Optionally, the determining the predicted value of the steering wheel angle value at the next time according to the steering wheel angle value before the previous time includes the following steps B1-B5:
b1, defined in (t-t) w ) In the time period between the moment and the t moment, the difference value between the steering wheel angles at every two adjacent moments; wherein the time t is the last time, the time (t+1) is the next time, and the time t is w Is a preset window time.
From the start time of the target period as time t, a (t-t w ) In the time period between the moment and the moment t, the difference value between steering wheel angles between every two adjacent moments is obtained to obtain a difference value set w,
and B2, determining the average value of the difference values to obtain an average difference value.
Average difference
B3, obtaining the (t-t) w ) The steering wheel angle value at the moment is obtained and (t w +1) the steering wheel angle value at the moment, and respectively obtaining a first angle value and a second angle value.
Acquisition (t-t) w ) The steering wheel angle value at the moment is obtainedAcquisition (t) w +1) time steering angle value, to obtain +.>
And B4, calculating the product between the second rotation angle value and the average difference value to obtain a first product.
The first product is:
b5, taking the sum of the first rotation angle value and the first product as a predicted value of the steering wheel rotation angle at the time of (t+1).
Then, the predicted value of the steering wheel angle at the time (t+1) is:
and step 213, obtaining the actual value of the steering wheel angle at the next moment.
The actual value of the steering wheel angle at the next moment is w t+1 。
Step 214, determining an absolute value of the difference between the predicted value and the true value to obtain an absolute rotation angle difference, and determining a quotient between the absolute rotation angle difference and the true value to obtain a rotation angle quotient.
Absolute angle difference isThe angle quotient is Deltaw t+1 /w t+1 。
Step 215, if the absolute steering angle difference is greater than a preset minimum hard steering error value and the steering angle quotient is greater than a preset minimum hard steering rate, determining that the vehicle has a sudden steering wheel event at the next moment.
The minimum hard steering error value Min Hard Swerve Error is preset and the minimum hard steering rate Min Hard Swerve Ratio is set. If Deltaw t+1 > Min Hard Swerve Error, and Δw t+1 /w t+1 If the speed is larger than MinHard Swerve Ratio, the situation that the vehicle is in a sudden steering wheel event at the time t+1, namely the next time is determined.
In step 211-step 215, according to the predicted and actual values of the steering wheel angle value at the next moment, the absolute angle difference and the angle quotient are determined, and according to the magnitude relation between the absolute angle difference and the angle quotient and the preset minimum hard steering error value and minimum hard steering rate, whether the vehicle has a sudden steering wheel event or not can be accurately determined.
And step 216, judging whether the vehicle meets a first condition and a second condition according to the control state information and the lane line information corresponding to the second time point, wherein the first condition is that the vehicle is in an unmanned state at the second time point, and the second condition is that the vehicle runs at the center of a lane at the second time point.
In the unmanned vehicle, determining an emergency steering scene, and determining whether the vehicle is in an unmanned state at a second time point, and whether the vehicle is in the middle of a lane line at the second time point,
and 217, if the vehicle meets the first condition and the second condition at the same time, determining that the emergency steering wheel event belongs to an emergency steering scene.
When both conditions are met, it is possible to determine that the emergency steering event is an emergency steering scenario that occurs with an unmanned vehicle.
Step 218, determining the starting time of the emergency steering scene according to the first time point and the preset first buffering time.
In the emergency steering scene, an emergency braking event generally occurs first, and then an emergency steering wheel event occurs, so that the starting time of the emergency steering scene can be determined according to the first time point and the preset first buffering time.
Specifically, the preset first buffering time is a period of time, such as 3 seconds, 5 seconds, etc.
If the first time point is t s The first buffer time is 3 seconds, the starting time T of the emergency steering scene s =t s -3。
Step 219, determining the ending time of the emergency steering scene according to the first time point and the preset second buffering time.
Specifically, the preset second buffering time is a period of time, such as 6 seconds, 8 seconds, etc.
If the second time point is t p The second buffer time is 6 seconds, and the ending time of the emergency steering scene is T p =t p -6。
Step 220, obtaining drive test data between the starting time of the emergency steering scene and the ending time of the emergency steering scene, and obtaining target drive test data.
From the start time and the end time of the emergency steering scene obtained in the above steps, it can be determined in which time period the vehicle is in the emergency steering scene.
Then the drive test data between the starting time and the ending time is intercepted to obtain the target drive test data.
And 221, configuring a vehicle emergency steering simulation scene according to the target drive test data.
Specifically, the target drive test data can be utilized to configure corresponding emergency braking events and emergency steering wheel events, and the positions of the vehicles on the lane lines are configured, so that the vehicle emergency steering simulation scene is obtained.
Further, after configuring the vehicle emergency steering scenario, appropriate evaluation indicators may be configured with the desired driving behavior. For example, monitoring acceleration of the vehicle, and if the minimum effective acceleration is exceeded, generating an alarm; the rate of change of the steering wheel angle of the vehicle is monitored and an alert is generated if the minimum hard steering rate is exceeded.
The scene configuration may also be verified after configuring the vehicle emergency steering scene. For example, a large-scale simulation platform is utilized to periodically run newly generated simulation scenes in batches, the same automatic driving algorithm version as that used when an accident occurs is used, and algorithms such as track similarity are utilized to detect whether the problems in the original accident can be recovered in the simulation; if the scene is reproduced, further detecting whether the automatically configured evaluation standard can correctly output the result; the verification result report can be automatically generated and submitted to the auditor for approval into the scene library.
In summary, the vehicle emergency steering scene configuration method in fig. 2 starts from the largest first acceleration value in the first acceleration set, traverses the first acceleration set in a reverse direction, determines whether the traversing operation is continued according to the counter and the buffer value, thereby determining whether the emergency braking is finished, and further determines the starting time of the emergency braking, wherein determining whether the traversing operation is continued according to the counter and the buffer value, fully considers the situation that the acceleration rate is changed in a curve in a plurality of continuous braking, and thus the obtained starting time of the emergency braking is more scientific and accurate.
And according to the prediction and the true value of the steering wheel angle value at the next moment, determining an absolute angle difference value and an angle quotient, and according to the magnitude relation between the absolute angle difference value and the angle quotient and the preset minimum hard steering error value and the minimum hard steering rate, determining whether the vehicle has a sudden steering wheel event or not accurately.
Fig. 3 is a block diagram of a vehicle emergency steering simulation scene configuration device according to an embodiment of the present invention.
As shown in fig. 3, the vehicle emergency steering simulation scene configuration apparatus 300 includes:
the drive test data acquisition module 301 is configured to acquire drive test data during a running process of a vehicle, where the drive test data includes lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle, and control state information of the vehicle;
the emergency brake identification module 302 is configured to identify an emergency brake event of the vehicle during driving according to acceleration information of the vehicle, and determine a start time point corresponding to the emergency brake event, so as to obtain a first time point;
the rapid-beating direction identifying module 303 is configured to identify a rapid-beating steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period when it is determined that the vehicle does not belong to a lane change state before the first time point, and obtain a time point corresponding to the rapid-beating steering wheel event, so as to obtain a second time point; the target time period is a time period with a time difference of a preset first threshold value from the first time point;
The scene determining module 304 is configured to determine whether the emergency steering wheel event belongs to an emergency steering scene of the unmanned vehicle according to the lane line information and the control state information corresponding to the second time point;
the first scene configuration module 305 is configured to determine target drive test data based on the first time point and the second time point if yes, and configure an emergency steering simulation scene of the unmanned vehicle according to the target drive test data.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In yet another embodiment of the present invention, there is further provided an apparatus, including a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the vehicle emergency steering simulation scene configuration method described in the embodiments of the present invention.
In yet another embodiment of the present invention, there is further provided a computer readable storage medium having stored therein at least one instruction, at least one program, a code set, or an instruction set, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the vehicle emergency steering simulation scene configuration method described in the embodiments of the present invention.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (18)
1. A vehicle emergency steering simulation scene configuration method, the method comprising:
the method comprises the steps of obtaining drive test data in the running process of a vehicle, wherein the drive test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle;
identifying an emergency braking event of the vehicle in the running process according to the acceleration information of the vehicle, and determining a starting time point corresponding to the emergency braking event to obtain a first time point;
when the fact that the vehicle does not belong to the lane change state before the first time point is determined, identifying a sudden steering wheel event of the vehicle according to steering wheel angle information of the vehicle in a target time period, and acquiring a time point corresponding to the sudden steering wheel event to obtain a second time point; the target time period is a time period with a time difference of a preset first threshold value from the first time point;
Judging whether the vehicle meets a first condition and a second condition according to the control state information and the lane line information corresponding to the second time point, wherein the first condition is that the vehicle is in an unmanned state at the second time point, and the second condition is that the vehicle runs at the center of a lane at the second time point; if the vehicle meets the first condition and the second condition at the same time, determining that the emergency steering wheel event belongs to an emergency steering scene;
if yes, determining target drive test data based on the first time point and the second time point, and configuring an emergency steering simulation scene of the unmanned vehicle according to the target drive test data.
2. The method according to claim 1, wherein the acceleration information includes a time stamp and an acceleration value and an acceleration direction corresponding to the time stamp, and the identifying the emergency braking event of the vehicle during the driving according to the acceleration information of the vehicle includes:
acquiring an acceleration value of which the acceleration direction is opposite to the vehicle advancing direction, and obtaining a first acceleration value;
determining whether a target first acceleration value exists, wherein the target first acceleration value is a first acceleration value which is larger than or equal to a preset minimum effective acceleration value;
If so, determining that the vehicle has an emergency braking event in the driving process.
3. The method of claim 2, wherein the determining the starting point in time for the emergency braking event comprises:
according to the sequence of the time stamps, the first acceleration values at all moments are put into a set to obtain a first acceleration set;
traversing the first acceleration set in a reverse direction starting from a largest first acceleration value in the first acceleration set;
in the traversing process, if the traversed acceleration value is greater than or equal to the preset minimum effective acceleration value, the value of the counter is increased by one, and the reverse traversing is continued; if the traversed acceleration value is smaller than the minimum effective acceleration value, resetting a counter, continuing to traverse reversely until the value of the counter is larger than the preset buffer time, and ending the traversal;
and determining the difference value between the time stamp corresponding to the last traversed acceleration value and the current numerical value of the counter as the starting time point of the emergency braking event.
4. The method of claim 1, wherein the identifying a hard drive steering wheel event of the vehicle based on steering wheel angle information of the vehicle over a target period of time comprises:
Acquiring steering wheel angle values of the vehicle at various moments in the target time period;
determining steering wheel angle values corresponding to all the moments according to the steering wheel angle values, wherein the steering angle values are differences between the steering wheel angle values at the previous moment and the steering wheel angle values at the next moment;
determining a predicted value of the steering wheel angle value at the next moment according to the steering wheel angle value before the previous moment;
acquiring a true value of the steering wheel angle at the next moment;
determining an absolute value of a difference between the predicted value and the true value to obtain an absolute rotation angle difference value, and determining a quotient between the absolute rotation angle difference value and the true value to obtain a rotation angle quotient;
and if the absolute steering angle difference value is larger than a preset minimum hard steering error value and the steering angle quotient is larger than a preset minimum hard steering rate, determining that the vehicle has a sudden steering wheel event at the next moment.
5. The method of claim 4, wherein said determining a predicted value of the steering wheel angle value at the next time based on the steering wheel angle value before the previous time comprises:
is determined to be at (t-t) w ) In the time period between the moment and the t moment, the difference value between the steering wheel angles at every two adjacent moments; wherein the time t is the last time, the time (t+1) is the next time, and the time t is w The window time is preset;
determining the average value of the difference values to obtain an average difference value;
obtaining said (t-t) w ) The steering wheel angle value at the moment is obtained and (t w +1) the steering wheel angle value at the moment, respectively obtaining a first angle value and a second angle value;
calculating the product between the second rotation angle value and the average difference value to obtain a first product;
and taking the sum of the first rotation angle value and the first product as a predicted value of the steering wheel rotation angle at the time of (t+1).
6. The method of claim 1, wherein the drive test data further includes lane change status data of the vehicle, and further comprising, after determining the starting point in time corresponding to the emergency braking event:
and determining whether the vehicle belongs to the lane change state before the first time point according to the lane change state data.
7. The method of claim 1, wherein the determining target drive test data from the first point in time and the second point in time comprises:
Determining the starting time of the emergency steering scene according to the first time point and a preset first buffer time;
determining the ending time of the emergency steering scene according to the first time point and a preset second buffer time;
and obtaining drive test data between the starting time of the emergency steering scene and the ending time of the emergency steering scene to obtain target drive test data.
8. The method of claim 1, wherein the drive test data further includes obstacle information surrounding the vehicle at each time, the obstacle information including location information of the obstacle, the method further comprising:
acquiring the obstacle information from drive test data in a preset time period before the first time point;
determining target obstacle information from the obstacle information according to the position and size information of the obstacle; the target obstacle information is an obstacle which is the same lane as the vehicle or adjacent to the vehicle and has a distance from the vehicle smaller than a preset distance threshold;
and configuring a vehicle emergency steering simulation scene according to the target drive test data and the target obstacle information.
9. A vehicle emergency steering simulation scene configuration apparatus, the apparatus comprising:
The drive test data acquisition module is used for acquiring drive test data in the running process of the vehicle, wherein the drive test data comprise lane line information of the vehicle at each moment, acceleration information of the vehicle, steering wheel angle information of the vehicle and control state information of the vehicle;
the emergency brake identification module is used for identifying an emergency brake event of the vehicle in the running process according to the acceleration information of the vehicle, determining a starting time point corresponding to the emergency brake event and obtaining a first time point;
the rapid-beating direction identification module is used for identifying a rapid-beating steering wheel event of the vehicle according to the steering wheel angle information of the vehicle in a target time period when the vehicle is determined not to belong to a lane change state before the first time point, and acquiring a time point corresponding to the rapid-beating steering wheel event to obtain a second time point; the target time period is a time period with a time difference of a preset first threshold value from the first time point;
the scene determining module is used for determining whether the vehicle meets a first condition and a second condition according to the control state information and the lane line information corresponding to the second time point, wherein the first condition is that the vehicle is in an unmanned state at the second time point, and the second condition is that the vehicle runs at the center of a lane at the second time point; if the vehicle meets the first condition and the second condition at the same time, determining that the emergency steering wheel event belongs to an emergency steering scene;
And the first scene configuration module is used for determining target drive test data based on the first time point and the second time point if yes, and configuring an emergency steering simulation scene of the unmanned vehicle according to the target drive test data.
10. The device according to claim 9, wherein the acceleration information includes a timestamp, and an acceleration value and an acceleration direction corresponding to the timestamp, and the emergency brake identification module is specifically configured to:
acquiring an acceleration value of which the acceleration direction is opposite to the vehicle advancing direction, and obtaining a first acceleration value;
determining whether a target first acceleration value exists, wherein the target first acceleration value is a first acceleration value which is larger than or equal to a preset minimum effective acceleration value;
if so, determining that the vehicle has an emergency braking event in the driving process.
11. The device according to claim 10, wherein the emergency brake identification module is specifically configured to:
according to the sequence of the time stamps, the first acceleration values at all moments are put into a set to obtain a first acceleration set;
traversing the first acceleration set in a reverse direction starting from a largest first acceleration value in the first acceleration set;
In the traversing process, if the traversed acceleration value is greater than or equal to the preset minimum effective acceleration value, the value of the counter is increased by one, and the reverse traversing is continued; if the traversed acceleration value is smaller than the minimum effective acceleration value, resetting a counter, continuing to traverse reversely until the value of the counter is larger than the preset buffer time, and ending the traversal;
and determining the difference value between the time stamp corresponding to the last traversed acceleration value and the current numerical value of the counter as the starting time point of the emergency braking event.
12. The apparatus of claim 9, wherein the jerk direction identification module is specifically configured to:
acquiring steering wheel angle values of the vehicle at various moments in the target time period;
determining steering wheel angle values corresponding to all the moments according to the steering wheel angle values, wherein the steering angle values are differences between the steering wheel angle values at the previous moment and the steering wheel angle values at the next moment;
determining a predicted value of the steering wheel angle value at the next moment according to the steering wheel angle value before the previous moment;
acquiring a true value of the steering wheel angle at the next moment;
Determining an absolute value of a difference between the predicted value and the true value to obtain an absolute rotation angle difference value, and determining a quotient between the absolute rotation angle difference value and the true value to obtain a rotation angle quotient;
and if the absolute steering angle difference value is larger than a preset minimum hard steering error value and the steering angle quotient is larger than a preset minimum hard steering rate, determining that the vehicle has a sudden steering wheel event at the next moment.
13. The apparatus of claim 12, wherein the jerk direction identification module is specifically configured to:
is determined to be at (t-t) w ) In the time period between the moment and the t moment, the difference value between the steering wheel angles at every two adjacent moments; wherein the time t is the last time, the time (t+1) is the next time, and the time t is w The window time is preset;
determining the average value of the difference values to obtain an average difference value;
obtaining said (t-t) w ) The steering wheel angle value at the moment is obtained and (t w +1) the steering wheel angle value at the moment, respectively obtaining a first angle value and a second angle value;
calculating the product between the second rotation angle value and the average difference value to obtain a first product;
and taking the sum of the first rotation angle value and the first product as a predicted value of the steering wheel rotation angle at the time of (t+1).
14. The apparatus of claim 9, wherein the drive test data further includes lane change status data of the vehicle, the apparatus further comprising:
and the lane change state determining module is used for determining whether the vehicle belongs to a lane change state before the first time point according to the lane change state data.
15. The apparatus of claim 9, wherein the scene configuration module is specifically configured to:
determining the starting time of the emergency steering scene according to the first time point and a preset first buffer time;
determining the ending time of the emergency steering scene according to the first time point and a preset second buffer time;
and obtaining drive test data between the starting time of the emergency steering scene and the ending time of the emergency steering scene to obtain target drive test data.
16. The apparatus of claim 9, wherein the drive test data further includes obstacle information surrounding the vehicle at each time, the obstacle information including position information of the obstacle, the apparatus further comprising:
the obstacle information acquisition module is used for acquiring the obstacle information from the road test data in a preset time period before the first time point;
A target information determining module, configured to determine target obstacle information from the obstacle information according to the position and size information of the obstacle; the target obstacle information is an obstacle which is the same lane as the vehicle or adjacent to the vehicle and has a distance from the vehicle smaller than a preset distance threshold;
and the second scene configuration module is used for configuring a vehicle emergency steering simulation scene according to the target drive test data and the target obstacle information.
17. An apparatus comprising a processor and a memory having stored therein at least one instruction, at least one program, code set, or instruction set that is loaded and executed by the processor to implement the vehicle emergency steering simulation scenario configuration method of any one of claims 1-8.
18. A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by a processor to implement the vehicle emergency steering simulation scenario configuration method of any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111635771.4A CN114475653B (en) | 2021-12-28 | 2021-12-28 | Vehicle emergency steering simulation scene configuration method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111635771.4A CN114475653B (en) | 2021-12-28 | 2021-12-28 | Vehicle emergency steering simulation scene configuration method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114475653A CN114475653A (en) | 2022-05-13 |
CN114475653B true CN114475653B (en) | 2024-03-15 |
Family
ID=81508025
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111635771.4A Active CN114475653B (en) | 2021-12-28 | 2021-12-28 | Vehicle emergency steering simulation scene configuration method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114475653B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108290579A (en) * | 2015-11-04 | 2018-07-17 | 祖克斯有限公司 | Simulation system and method for autonomous vehicle |
CN110717248A (en) * | 2019-09-11 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Method and system for generating automatic driving simulation scene, server and medium |
CN111252140A (en) * | 2018-11-30 | 2020-06-09 | 丰田自动车株式会社 | Steering determination device and automatic driving system |
CN112567374A (en) * | 2020-10-21 | 2021-03-26 | 华为技术有限公司 | Simulated traffic scene file generation method and device |
CN112793576A (en) * | 2021-01-26 | 2021-05-14 | 北京理工大学 | Lane change decision method and system based on rule and machine learning fusion |
CN113157578A (en) * | 2021-01-11 | 2021-07-23 | 北京赛目科技有限公司 | Automatic driving simulation test method and device based on scene |
CN113525373A (en) * | 2020-03-30 | 2021-10-22 | 华为技术有限公司 | Lane changing control system and method for vehicle |
-
2021
- 2021-12-28 CN CN202111635771.4A patent/CN114475653B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108290579A (en) * | 2015-11-04 | 2018-07-17 | 祖克斯有限公司 | Simulation system and method for autonomous vehicle |
CN111252140A (en) * | 2018-11-30 | 2020-06-09 | 丰田自动车株式会社 | Steering determination device and automatic driving system |
CN110717248A (en) * | 2019-09-11 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Method and system for generating automatic driving simulation scene, server and medium |
CN113525373A (en) * | 2020-03-30 | 2021-10-22 | 华为技术有限公司 | Lane changing control system and method for vehicle |
CN112567374A (en) * | 2020-10-21 | 2021-03-26 | 华为技术有限公司 | Simulated traffic scene file generation method and device |
CN113157578A (en) * | 2021-01-11 | 2021-07-23 | 北京赛目科技有限公司 | Automatic driving simulation test method and device based on scene |
CN112793576A (en) * | 2021-01-26 | 2021-05-14 | 北京理工大学 | Lane change decision method and system based on rule and machine learning fusion |
Also Published As
Publication number | Publication date |
---|---|
CN114475653A (en) | 2022-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111191697B (en) | ADAS road test verification optimization method and device based on sensor fusion | |
CN109784254B (en) | Vehicle violation event detection method and device and electronic equipment | |
JP7149098B2 (en) | Predictive diagnosis device and method | |
US20200070845A1 (en) | Positioning Drift Detecting Method, Apparatus, Device and Computer Readable Storage Medium | |
CN113291321A (en) | Vehicle track prediction method, device, equipment and storage medium | |
CN112749210B (en) | Vehicle collision recognition method and system based on deep learning | |
CN112530170A (en) | Vehicle driving state detection method and device, electronic equipment and storage medium | |
CN111612378A (en) | Potential collision risk prediction method and device and computer equipment | |
CN112287801A (en) | Vehicle-mounted data processing method and device, server and readable storage medium | |
US10589741B2 (en) | Enhanced collision avoidance | |
CN115165398A (en) | Vehicle driving function test method and device, computing equipment and medium | |
WO2017058134A1 (en) | Enhanced curve negotiation | |
CN112863242B (en) | Parking space detection method and device | |
CN114475653B (en) | Vehicle emergency steering simulation scene configuration method and device | |
CN112633262B (en) | Channel monitoring method and device, electronic equipment and medium | |
CN112356845B (en) | Method, device and equipment for predicting motion state of target and vehicle | |
CN112883866A (en) | Method, system and storage medium for detecting regional invasion in real time | |
CN112781556A (en) | Well lid transaction monitoring method and device based on multi-data fusion filtering | |
CN111709665A (en) | Vehicle safety evaluation method and device | |
KR102006755B1 (en) | In-vehicle external data intrusion detection apparatus by comparing information entropy and operating method thereof | |
WO2020106201A1 (en) | Method, Computer Program, Control Unit for Detecting Faults in a Driver-Assistance System and Vehicle | |
CN116461546A (en) | Vehicle early warning method, device, storage medium and processor | |
US10618524B2 (en) | Method for determining a reference driving class | |
CN113345125B (en) | Method, device, equipment and storage medium for detecting and processing vehicle falling event | |
CN115270400A (en) | Test scene construction method for automatic driving simulation and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |