WO2021129309A1 - 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 - Google Patents
车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 Download PDFInfo
- Publication number
- WO2021129309A1 WO2021129309A1 PCT/CN2020/132412 CN2020132412W WO2021129309A1 WO 2021129309 A1 WO2021129309 A1 WO 2021129309A1 CN 2020132412 W CN2020132412 W CN 2020132412W WO 2021129309 A1 WO2021129309 A1 WO 2021129309A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- trajectory
- driving
- domain controller
- intelligent
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 96
- 238000004891 communication Methods 0.000 claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 description 23
- 238000013461 design Methods 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000003062 neural network model Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000000994 depressogenic effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
- G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
- G08G1/163—Decentralised systems, e.g. inter-vehicle communication involving continuous checking
-
- 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
- B60W60/005—Handover processes
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- 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
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0259—Control of position or course in two dimensions specially adapted to land vehicles using magnetic or electromagnetic means
- G05D1/0263—Control of position or course in two dimensions specially adapted to land vehicles using magnetic or electromagnetic means using magnetic strips
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/028—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using a RF signal
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
- G05D1/0289—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling with means for avoiding collisions between vehicles
-
- 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
-
- 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
- B60W2540/10—Accelerator pedal position
-
- 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
- B60W2540/12—Brake pedal position
-
- 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
- B60W2540/16—Ratio selector position
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/20—Direction indicator values
-
- 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
- B60W2540/30—Driving style
-
- 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
- B60W2552/30—Road curve radius
-
- 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
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
-
- 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
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/804—Relative longitudinal speed
-
- 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
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/10—Historical data
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/65—Data transmitted between vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
Definitions
- This application relates to the field of smart cars, and in particular to a method and device for vehicle trajectory planning, a smart driving domain controller and a smart car.
- a smart car In the process of autonomous driving (ADS), a smart car (smart/intelligent car) will plan a collision-free safe path according to the surrounding environment.
- obstacle information is one of the important inputs for path planning.
- traditional technology there is no trajectory prediction for obstacles, and only the current situation of obstacles is analyzed and predicted, which is a static analysis process.
- the obstacle's trajectory is a dynamic process, and the obstacle's trajectory may jump or even collide with other people or objects.
- Smart cars need to predict the trajectory of surrounding vehicles and then plan the trajectory of their own vehicles.
- the current trajectory prediction is mainly based on the smart car relying on its own sensors, based on the historical data of the surrounding vehicles and road topology and other information, and assuming that the obstacle will maintain the current state of motion, the speed and direction will not change significantly, and the unified
- the rules (such as the default that the vehicle in front encounters obstacles first to avoid from the left) predict the trajectory of surrounding vehicles.
- vehicle movement on the actual road has great uncertainty.
- the behavior of a manually driven vehicle is subjectively determined by the driver, while the behavior of an autonomous vehicle may have multiple behavioral decisions in the same scene. It is difficult to make deterministic predictions using the above-mentioned methods, which will lead to the inaccurate trajectory planning of autonomous vehicles. Therefore, how to provide a method for accurately predicting the trajectory of a vehicle has become an urgent technical problem in the field of smart cars.
- This application provides a method and device for vehicle trajectory planning, which are used for smart cars to accurately perform trajectory planning.
- the present application provides a method of vehicle trajectory planning, which can be applied to a smart driving domain controller of a first vehicle, and the smart driving domain controller obtains the first trajectory of the first vehicle, And obtain the second trajectory of at least one second vehicle based on the first communication technology; then determine the trajectory plan of the first vehicle according to the first trajectory and the second trajectory of the at least one second vehicle.
- the traditional technology avoids the judgment error caused by the trajectory prediction of the vehicle at the current time only.
- This method can recognize the changes of the trajectory of other vehicles and ensure that the first vehicle does not appear at the same location at the same time as any other vehicle. Avoid collisions, which can improve the driving safety of smart cars.
- the specific method when the intelligent driving domain controller obtains the first trajectory of the first vehicle may be: the intelligent driving domain controller first determines the current driving mode of the first vehicle, Then, the first trajectory of the first vehicle is acquired according to the driving mode of the first vehicle, wherein the driving mode includes an automatic driving mode and a manual driving mode.
- the intelligent driving domain controller can accurately obtain the first trajectory of the first vehicle according to the actual driving mode of the first vehicle, and then accurately perform trajectory planning subsequently.
- the specific method may be: when the intelligent driving domain controller determines When the current driving mode of the first vehicle is the automatic driving mode, the intelligent driving domain controller obtains the automatic driving trajectory of the first vehicle, and then uses the automatic driving trajectory as the first trajectory. In this way, the first vehicle can obtain a trajectory matching the automatic driving mode of the first vehicle, thereby completing subsequent accurate trajectory planning.
- the specific method may be: when the intelligent driving domain controller determines When the current driving mode of the first vehicle is the manual driving mode, the intelligent driving domain controller may predict the manual driving trajectory of the first vehicle, and then use the predicted manual driving trajectory as the first trajectory .
- the intelligent driving domain controller can obtain the first trajectory matching the driving habits of the current driver according to the prediction, and then complete the subsequent accurate trajectory planning.
- the specific method when the intelligent driving domain controller predicts the manual driving trajectory of the first vehicle may be: the intelligent driving domain controller obtains the first parameter set and the corresponding first vehicle And predict the trajectory point of the first vehicle according to the first parameter set and the trajectory prediction model, and finally determine the manual driving trajectory of the first vehicle according to the trajectory point of the first vehicle;
- the first parameter set includes the position of the first vehicle, the driving data of the obstacles around the first vehicle relative to the first vehicle, and the driving state of the first vehicle.
- the driving state of is used to indicate the driving habits of the user currently driving the first vehicle;
- the trajectory prediction model is obtained by training based on historical data of the driving habits of the user currently driving the first vehicle.
- the position of the first vehicle may include the longitude and latitude that identify the location of the first vehicle; the obstacles around the first vehicle may include one or more obstacles, any obstacle
- the driving data of the object may include the relative speed and relative distance of any obstacle relative to the first vehicle; the driving state of the first vehicle includes the current lane attributes, road radius, and road radius of the road where the first vehicle is located.
- the trajectory point of the first vehicle includes the predicted longitude and the predicted latitude included in the predicted travel trajectory of the first vehicle. In this way, the prediction accuracy and prediction dimensions contained in each trajectory point can obtain a predicted position of the first vehicle, and the predicted position can form a predicted driving trajectory.
- the trajectory point of the first vehicle further includes the confidence of the predicted longitude and the confidence of the predicted latitude.
- the confidence of the prediction accuracy indicates the accuracy of the prediction accuracy
- the confidence of the predicted latitude indicates the accuracy of the predicted latitude.
- the intelligent driving domain controller may send the first parameter set and the trajectory point of the first vehicle to a cloud server, so that the cloud server can be configured according to the first parameter set and the trajectory point of the first vehicle.
- the trajectory point of the first vehicle corrects the trajectory prediction model; and receives the corrected trajectory prediction model sent by the cloud server, and then, the intelligent driving domain controller uses the corrected trajectory prediction model and the second A two-parameter set predicts the trajectory point of the first vehicle, and the second parameter set is collected at the current moment, including the position of the first vehicle, and the driving of obstacles around the first vehicle relative to the first vehicle Data and data of the driving state of the first vehicle.
- a trajectory prediction model determined according to the driving habits of each driver can be obtained.
- the above method can obtain a customized trajectory prediction model for each driver in a smart car or a non-smart car in the manual driving mode, and predict according to their respective driving habits Compared with the method of using unified rules to predict the trajectory in the traditional technology, its driving trajectory is closer to the driving trajectory of the vehicle. Further, the intelligent driving domain controller can determine the driving trajectory of the self-vehicle according to the predicted trajectory obtained by the aforementioned acquisition prediction model, reasonably plan the driving trajectory of the self-vehicle, and reduce the risk of collision with other vehicles.
- the intelligent driving domain controller sends the first trajectory to the at least one second vehicle.
- at least one second vehicle can be combined with the first trajectory for trajectory planning.
- the intelligent driving domain controller determines that the at least one second vehicle is within a set range before communicating with the at least one second vehicle, or the intelligent driving domain The controller determines that the at least one second vehicle has passed the safety certification; wherein the setting range is a circular area centered on the first vehicle, and the radius of the circular area is a setting value. In this way, the security of data transmission between vehicles is guaranteed.
- the first communication technology is V2X, a wireless communication technology for vehicles.
- the intelligent driving domain controller determines the driving trajectory of the first vehicle according to at least one of the following rules: Rule 1: Does not violate traffic rules; Rule 2: With obstacles (such as other vehicles) The distance between them needs to be greater than the preset value; Rule 3: Do not be in the same position with obstacles (such as other vehicles) at the same time.
- the present application provides an intelligent driving domain controller, which includes various modules or units for executing the vehicle trajectory planning method in the first aspect or any one of the possible designs of the first aspect , Such as processing unit and acquisition unit.
- the present application provides an intelligent driving domain controller.
- the intelligent driving domain controller includes a processor and a memory.
- the processor executes the computer stored in the memory.
- the computer program or instruction is executed to make the intelligent driving domain controller execute the corresponding method shown in the first aspect or any one of the possible designs of the first aspect.
- the present application provides a smart car, and the smart car may include the smart driving domain controller described in any of the second or third aspects.
- the smart car may be the first vehicle involved in the above-mentioned first aspect.
- the present application provides a system, which may include the above-mentioned first vehicle and at least one second vehicle.
- this application provides a computer-readable storage medium in which a program or instruction is stored, which when running on a computer, causes the computer to execute the first aspect or any one of the first aspect Possible design methods described in.
- the present application provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the method described in the first aspect or any one of the possible designs in the first aspect.
- FIG. 1 is a schematic diagram of the architecture of a system to which a vehicle trajectory planning method provided by this application is applicable;
- Figure 2 is a schematic diagram of a vehicle driving scene provided by this application.
- FIG. 3 is a flowchart of a method for vehicle trajectory planning provided by this application.
- FIG. 4 is a schematic structural diagram of a vehicle trajectory planning device provided by this application.
- FIG. 5 is a schematic structural diagram of a device provided by this application.
- Fig. 6 is a structural diagram of an intelligent driving domain controller provided by this application.
- FIG. 1 shows a schematic diagram of the architecture of a system to which a method for vehicle trajectory planning provided by an embodiment of the present application is applicable.
- the architecture of the system includes at least two vehicles and a cloud 100.
- n vehicles are shown, which are vehicle 1, vehicle 2, ... vehicle n, and n is an integer greater than or equal to 2.
- n vehicles include smart cars and non-smart cars; the at least two vehicles are self-driving vehicles with manual driving mode. In actual driving, each vehicle can work in automatic driving mode or work. In manual driving mode.
- any vehicle may include a sensor, an intelligent driving domain controller 104, an in-vehicle communication device 105, a high-precision positioning device 106, other vehicle controllers 107, and a human-computer interaction system 108.
- the sensor includes one or more of the following devices: at least one millimeter wave radar 101, at least one laser radar 102, and at least one camera 103. Specifically, only the vehicle 1 is shown in FIG. 1. The functions of the above modules included in the vehicle are explained in detail below:
- Millimeter wave radar 101 is a radar that works in millimeter wave (millimeter wave) detection, and is used to collect the transmission time of the beam and the speed of the beam to an obstacle, and send the collected data to the intelligent driving domain controller 104; or It is used to calculate data such as the distance and speed of surrounding obstacles after collecting the light beam transmission time and the speed of the light beam, and send the calculated data to the intelligent driving domain controller 104.
- millimeter wave millimeter wave
- Lidar 102 is a radar system that emits laser beams to detect the position and speed of a target and other characteristic quantities. Its working principle is to transmit a detection signal (laser beam) to the target, and then compare the received signal (target echo) from the target with the transmitted signal. After proper processing, the relevant data of the target can be obtained, such as Target distance, azimuth, height, speed, attitude, and even shape and other parameters.
- the lidar 102 is used to collect the signal reflected from the obstacle, and send the reflected signal and the transmitted signal to the intelligent driving domain controller 104; or after collecting the signal reflected from the obstacle, Compared with the transmitted signal, data such as the distance and speed of surrounding obstacles are obtained by processing, and the processed data is sent to the intelligent driving domain controller 104.
- Camera 103 Used to collect surrounding images or videos, and send the collected images or videos to the smart driving domain controller 104; where, when the camera 103 is a smart camera, the camera 103 can analyze the image after collecting the image or video Or the video obtains the speed and distance of surrounding obstacles, etc., and sends the analyzed data to the intelligent driving domain controller 104.
- High-precision positioning equipment 106 Collects the current vehicle's precise position information (with an error of less than 20cm), and the global positioning system (global positioning system, GPS) time information corresponding to the precise position information, and sends the collected information to the smart Driving the domain controller 104.
- the high-precision positioning device 106 may be a combined positioning system or a combined positioning module.
- the high-precision positioning device 106 may include devices and sensors such as a global navigation satellite system (GNSS) and an inertial measurement unit (IMU).
- GNSS global navigation satellite system
- IMU inertial measurement unit
- the global navigation satellite system can output global positioning information with a certain accuracy (for example, 5-10 Hz).
- the frequency of the inertial measurement unit is generally higher (for example, 1000 Hz).
- the high-precision positioning device 106 can integrate the inertial measurement unit and the global navigation satellite System information, output high-frequency precise positioning information (generally require more than 200Hz).
- Other vehicle controllers 107 execute control commands of the intelligent driving domain controller 104, and send relevant information such as vehicle steering, gear position, acceleration, and deceleration to the intelligent driving domain controller 104.
- Human-machine interaction system 108 Provides an audio and video mode of message interaction between the smart car and the driver, and can use the display screen to display the trajectory of the vehicle and other vehicles.
- the intelligent driving domain controller 104 can be installed in the vehicle.
- the intelligent driving domain controller 104 is specifically implemented by a processor, and the processor includes a central processing unit (CPU) or a device or module with processing functions.
- the intelligent driving domain controller 104 may be a mobile data center (mobile data center, MDC).
- the intelligent driving domain controller 104 sends the trajectory planning information to the vehicle-mounted communication device 105, and sends its own position information and the predicted trajectories of other surrounding vehicles to the human-computer interaction system 108;
- the sensor information and the actual trajectory of the vehicle and its own predicted trajectory (according to the sensor information and the information from other vehicle controllers are used by neural networks or other artificial intelligence (AI) algorithms Prediction) is sent to the vehicle-mounted communication device 105, and the position information of its own and the predicted trajectory of other surrounding vehicles are sent to the human-computer interaction system 108.
- AI artificial intelligence
- Vehicle-mounted communication device 105 a device that communicates with other vehicles, receives other vehicle trajectory prediction information (also can be described as predicted trajectory, trajectory information, etc.) and sends it to the intelligent driving domain controller 104, and sends its own trajectory to other surrounding vehicles; Communicate with the cloud 100, send the sensor information, positioning information and other controller information on the vehicle to the cloud 100, and receive the model parameters trained by the cloud 100.
- the vehicle-mounted communication device 105 may be a telematics BOX (TBOX).
- the distance and speed of the obstacle are the relative distance and relative speed of the obstacle with respect to the vehicle.
- any vehicle may perform information transmission with vehicles within a preset range, and the preset range may be a circular area with its own vehicle as a center and a set value as a radius. The set value of the radius may be set based on the range of V2X communication that the vehicle can support.
- mutual trust between vehicles can be established through authentication, specifically through mutual authentication information, and after the authentication is passed, they can communicate and share information.
- the vehicle can transmit information within a set time period.
- the vehicle can follow the automobile information safety standard 21434, etc., and the received information of other vehicles is only used for self-driving, and no recording is made.
- this application will not list them one by one here.
- Cloud 100 Train a model according to sensor information, positioning information, and other controller information, and send the trained model parameters to the vehicle-mounted communication device 105.
- the cloud 100 may be a cloud data center that can implement model training, or a physical device or virtual machine that can implement model training, which is not limited in this application.
- any vehicle can obtain the trajectory of surrounding vehicles within a preset period of time during the driving process to constrain the trajectory planning of the vehicle, thereby improving safety.
- the three vehicles will predict their own vehicle's trajectory based on their own driving patterns.
- take the trajectory planning of vehicle 1 as an example.
- vehicle 1 can obtain the predicted driving trajectory of vehicle 2 and vehicle 3 through V2X technology, and then combine its predicted driving trajectory to perform trajectory planning . This can improve the accuracy of its own trajectory planning, thereby improving the safety of driving.
- the aforementioned preset time period can be determined based on the delay required by the V2X transmission technology, or can be a preset empirical value, such as 5-10 seconds (s); of course, it can also be determined in other ways.
- the application is not limited.
- an embodiment of the present application provides a method for vehicle trajectory planning, which is applicable to the system shown in FIG. 1 and the scene shown in FIG. 2.
- the method can be used for trajectory planning of a first vehicle, which is a smart car.
- the method may be implemented by the intelligent driving domain controller of the first vehicle. Referring to FIG. 3, the specific process of the method may include:
- Step 301 The intelligent driving domain controller of the first vehicle obtains the first trajectory of the first vehicle.
- the specific method may be: the intelligent driving domain controller of the first vehicle determines the current driving mode of the first vehicle, so The driving mode includes an automatic driving mode and a manual driving mode; then, the intelligent driving domain controller obtains the first trajectory of the first vehicle according to the driving mode of the first vehicle.
- the driving domain controller may communicate with other vehicles through an in-vehicle communication device, for example, Send a driving mode query message, and then other vehicles will notify the first vehicle of its driving mode in the form of a response message.
- the first vehicle can also collect images of other vehicles through the camera, and then analyze the status of the drivers in other vehicles (for example, whether the driver holds the steering wheel, is in a resting state, etc.) to determine whether the vehicle is in automatic driving mode.
- the intelligent driving domain controller of the first vehicle obtains the first trajectory of the first vehicle according to the driving mode of the first vehicle, which may specifically include the following two situations:
- Case 1 When the intelligent driving domain controller determines that it is in the automatic driving mode, the intelligent driving domain controller obtains the automatic driving trajectory of the first vehicle, and uses the automatic driving trajectory as the first trajectory.
- Case 2 When the intelligent driving domain controller determines that it is in the manual driving mode, the intelligent driving domain controller predicts the manual driving trajectory of the first vehicle, and uses the predicted manual driving trajectory as the first Trajectory.
- the intelligent driving domain controller predicts the manual driving trajectory of the first vehicle.
- the specific method may be: the intelligent driving domain controller obtains the first vehicle A parameter set, the first parameter set includes the position of the first vehicle, the travel data of the obstacles around the first vehicle relative to the first vehicle, and the travel state of the first vehicle, the first vehicle
- the driving state of a vehicle is used to indicate the driving habits of the user currently driving the first vehicle; the intelligent driving domain controller obtains the trajectory prediction model corresponding to the first vehicle, and the trajectory prediction model is based on the current driving
- the historical data of the driving habits of the user of the first vehicle is obtained through training; the intelligent driving domain controller predicts the trajectory point of the first vehicle according to the first parameter set and the trajectory prediction model; the intelligent driving domain control
- the device determines the manual driving trajectory of the first vehicle according to the trajectory point of the first vehicle.
- the position of the first vehicle may include the longitude (P_long) and the latitude (P_lati) in the earth coordinate system that identify the current position of the first vehicle.
- the predicted result can be compared with the position of the first vehicle to confirm whether the prediction result is accurate, and to continuously adjust the model to make the trained trajectory prediction model The accuracy is higher.
- the obstacles around the first vehicle include one or more obstacles, and the driving data of any obstacle may include a relative speed (Obj_v) and a relative distance (Obj_d) of the any obstacle relative to the first vehicle.
- any obstacle here may be a vehicle, such as a second vehicle.
- the driving state of the first vehicle may include the current lane attributes of the road on which the first vehicle is located, road radius (road_radius), speed, acceleration, accelerator pedal opening (Acc_ped), and brake pedal of the first vehicle. Opening (Bra_ped), right front wheel brake cylinder (P_(Cy, FR)), left front wheel brake cylinder (P_(Cy, FL)), right rear wheel brake cylinder (P_(Cy, RR)), left Rear brake wheel cylinder (P_(Cy, RL)), steering wheel angle (Ste_ang), steering wheel angular velocity (Ste_angv), steering wheel torque (Ste_torq), gear position (gear), turn signal (Turn_sig).
- the current lane attribute of the road may be the number of lanes of the current road, whether the lane is a curve or a straight road, and so on.
- the road radius may be a curve radius; when the current lane is a straight road, the road radius may be zero or infinite.
- the accelerator pedal opening degree refers to the percentage of accelerator pedal opening and closing, where the accelerator pedal can be regarded as 100% when the accelerator pedal is fully depressed, and it can be regarded as zero when the accelerator pedal is not depressed.
- the right front wheel brake cylinder, the left front wheel brake cylinder, the right rear wheel brake cylinder and the left rear wheel brake cylinder are respectively control parameters on each wheel of the first vehicle.
- the gears are different levels divided in the forward gears of the automatic driving vehicle during the driving process, and the different levels correspond to different speeds.
- the trajectory point of the first vehicle predicted by the intelligent driving domain controller of the first vehicle based on the above parameters may include the predicted longitude and prediction included in the predicted driving trajectory of the first vehicle (that is, the predicted manual driving trajectory) latitude.
- the trajectory point of the first vehicle further includes the confidence of the predicted longitude and the confidence of the predicted latitude.
- the trajectory points of the first vehicle may be a set of trajectory points, which may include trajectory points within a period of time (for example, 5s).
- the confidence of the prediction accuracy indicates the accuracy of the prediction accuracy
- the confidence of the predicted latitude indicates the accuracy of the predicted latitude. In this way, when the predicted trajectory is obtained from the trajectory points, the accuracy of the trajectory points can be understood and the accuracy of the predicted trajectory can be clearly understood. Accuracy. So that the intelligent driving domain controller selects the predicted trajectory with higher accuracy for subsequent trajectory planning.
- different users have different driving habits, and the relevant parameters when different users drive the first vehicle are different.
- the relative distance of obstacles, relative speed, lane attributes of the road, and road radius describe the environment where the driver (ie, the user) is located
- the speed and acceleration of the vehicle describe the state of the vehicle
- the accelerator pedal opening describes the current environment and The driver’s habit of stepping on the accelerator in the vehicle state.
- the brake pedal opening, right front brake wheel cylinder, left front brake wheel cylinder, right rear brake wheel cylinder, and left rear brake wheel cylinder describe the current environment and vehicle conditions.
- the driver’s habit of stepping on the brakes, steering wheel angle, steering wheel steering angle speed, steering wheel torque, and turn signal signals describe the driver’s steering habit under the current environment and vehicle conditions.
- the above parameters are different.
- training is performed according to the driving habits of each user, and the parameters of the preset neural network model of the user are trained, so that a trajectory that meets its own characteristics can be predicted.
- the aforementioned driving state related to the first vehicle only indicates the driving habits of the user currently driving the first vehicle
- the predictive neural network model is also trained on the driving habits of the user driving the first vehicle.
- model training can be performed through a cloud server, and the cloud server sends the trained model parameters to the intelligent driving domain controller.
- the training set used includes an input set and an output set, where the input set may be the previous period recorded by the intelligent driving domain controller of the first vehicle that the user currently driving the first vehicle Multiple parameter sets acquired during driving the first vehicle in time or in real time, each parameter set is the same as the parameters included in the first parameter set; the trajectory point of the first vehicle corresponding to each parameter set is used as the output set , Which is the expected output during model training.
- the intelligent driving domain controller sends the above-mentioned training set to the cloud server through V2X.
- the training process of the cloud server may be as follows:
- Network determination that is, the size of the predictive neural network model is determined.
- the trial and error method is used to determine the number of neurons in the hidden layer. Specifically, first set a smaller number of neurons to train the network, and then increase one by one, use the same sample set for training, compare the results, and when the results no longer improve When, stop increasing the number of neurons and determine the optimal number of neurons.
- the predictive neural network model may include an input layer, a hidden layer and an output layer.
- the number of neurons in the hidden layer can be determined first according to an empirical formula, and then increase one by one.
- the empirical formula can refer to the following formula 1 or other formulas:
- m is the dimension of the input set (that is, the number of parameters of the input set), and l is the dimension of the output set.
- Training model that is, determining the model parameters of the predictive neural network model.
- the output set of the hidden layer is ⁇ S 0 , S 1 , ..., St , S t+1 , ... ⁇ ; among them, the output set of the hidden layer is after the input set of the training set is input to the model,
- the set of intermediate values in the training process obtained according to the function of the set hidden layer, where the input set may be the record of the user who is currently driving the first vehicle in the past period recorded by the intelligent driving domain controller of the first vehicle.
- the multiple parameter sets acquired during driving of the first vehicle in time or in real time, each parameter set is the same as the parameters included in the first parameter set; the output function of the specific hidden layer conforms to the following formula 2:
- X t is the input set in the training set, and U and W are the weight coefficients;
- softmax (VS t ) is the planning exponential function, where the planning exponential function is used to process the book output set of the hidden layer to obtain the final output result of the trajectory prediction model; V is the weight matrix.
- the loss function is used to make the trained model meet the model accuracy requirements. Use the training set to train the model, and use the untrained data set to test the trained model. When the accuracy of the model meets the requirements, determine the model parameters U, W, and V to obtain the driving habits of the user currently driving the first vehicle Forecast trajectory model.
- the loss function J may conform to the following formula 4:
- N is the number of input set and output set pairs included in the training set.
- the cloud server completes the training of the predictive neural network model, and then the cloud server transmits the finally determined model parameters U, W, and V to the intelligent driving domain controller of the first vehicle, so that the intelligent driving The domain controller predicts the trajectory point of the first vehicle.
- the intelligent driving domain controller of the first vehicle may send the first parameter set and the trajectory point of the first vehicle to a cloud server, so that the cloud server can The first parameter set and the trajectory points of the first vehicle correct the trajectory prediction model; then the intelligent driving domain controller receives the corrected trajectory prediction model sent by the cloud server, and uses the corrected trajectory prediction model
- the trajectory prediction model and the second parameter set predict the trajectory point of the first vehicle, and the second parameter set is the position of the first vehicle collected at the current moment, and the obstacles around the first vehicle are relative to the The driving data of the first vehicle and the data of the driving state of the first vehicle.
- the cloud server can continuously update the previously trained trajectory prediction model according to the driving data sent by the smart driving domain controller of the smart car or the controller of the non-smart car, so as to make the model training more and more accurate, thereby making the vehicle
- the trajectory prediction is becoming more and more accurate, so that more accurate trajectory planning can be carried out and safety can be improved.
- the on-board controller can collect the current driver’s driving data and send the data to the cloud server, and then the cloud server can obtain customized driving matching the current driver’s driving habits based on the driving data training Model and send the customized driving model to the on-board controller.
- the intelligent driving domain controller of the first vehicle may determine the self-vehicle's travel trajectory according to the predicted travel trajectory sent by each vehicle.
- the intelligent driving domain controller of the first vehicle may also obtain the driving model of the surrounding vehicles and the driving data of the driver at the current moment, and respectively predict the driving trajectory of each vehicle based on the driving model and driving data.
- the above-mentioned prediction process of the driving trajectory of each vehicle can also be completed by a cloud server.
- Each vehicle sends the driving data of the driver at the current time of its own vehicle to the cloud server, and the cloud server corresponds to each vehicle.
- the customized driving model predicts the driving trajectory, and sends the predicted driving trajectory to the intelligent driving domain controller of the first vehicle, so that the intelligent driving domain controller determines the driving trajectory of the first vehicle.
- the intelligent driving domain controller of the first vehicle after acquiring the first trajectory, sends the first trajectory to the at least one second vehicle, so that the Any one of the at least one second vehicle performs trajectory planning in combination with its own trajectory.
- Step 302 The intelligent driving domain controller of each second vehicle in at least one second vehicle obtains the second trajectory of each second vehicle.
- two second vehicles are shown in FIG. 3, but it should be understood that the number of vehicles in FIG. 3 is not a limitation on the number of at least one, and it may be one or more second vehicles than two.
- the method for acquiring the second trajectory by the intelligent driving domain controller of any second vehicle is the same as the method for acquiring the first trajectory by the intelligent driving domain controller of the first vehicle in step 301, and can refer to each other , Will not be described in detail here.
- Step 303 The intelligent driving domain controller of the first vehicle obtains the second trajectory of the at least one second vehicle based on the first communication technology.
- the intelligent driving domain controller of the first vehicle may use the first communication technology involved in step 303 when acquiring data of other vehicles or sending data to other vehicles, for example,
- the first communication technology may be V2X technology.
- the intelligent driving domain controller of the first vehicle acquires data of other vehicles (for example, at least one second vehicle) or sends data to other vehicles
- the intelligent driving domain controls The intelligent driving domain controller determines that the current time is within the preset time period for communicating with other vehicles; or, the intelligent driving domain controller determines that it has passed safety certification with other vehicles, that is, establish mutual trust through the authentication result, that is, the intelligent driving The domain controller needs to establish mutual trust between the first vehicle and the at least one second vehicle. In other words, if the first vehicle needs to obtain the driving trajectory of other vehicles, it needs to obtain the safety certification of the other vehicle first.
- the first vehicle can learn the driving trajectory of the other vehicle, thereby improving the vehicle’s Safety while driving on the road.
- the first vehicle may establish mutual trust with other vehicles in the following manner: the intelligent driving domain controller determines that the at least one second vehicle is within a preset range, and the preset range is based on the first A vehicle is a circular area with the center of the circle, and the radius of the circular area is a set value; then, the intelligent driving controller sends a safety certification message to the vehicles within a preset range, wherein the safety certification message includes the safety certification Type (such as password-based authentication, digital signature authentication), the identification of the first vehicle (such as vehicle device number); other vehicles are processed and responded according to the safety authentication message, and then the intelligent driving domain controller responds according to the response
- the message establishes a trust relationship with surrounding vehicles, and then obtains the predicted driving trajectory of surrounding vehicles.
- the process of mutual trust authentication between different vehicles needs to be confirmed within a preset time.
- vehicles can periodically confirm the status of mutual trust, or maintain a mutual trust link after mutual trust is established for the first time, and the status of safety certification can be monitored in real time through the mutual trust link.
- step 302 and step 303 may be performed first and then step 301; or the order of execution may be step 302, step 301, step 303, and so on.
- Step 304 The intelligent domain driving controller of the first vehicle determines the trajectory plan of the first vehicle according to the first trajectory and the second trajectory of the at least one second vehicle.
- the intelligent driving domain controller of the first vehicle may comply with the following principles: ensure that traffic rules cannot be violated, such as not running a red light or speeding ⁇ Can not drive in emergency lanes, can not compact lines, etc.; ensure that the distance to obstacles (such as other vehicles) needs to be greater than the preset value to reserve an effective braking range; ensure that the distance between obstacles (such as other vehicles) ) Are in the same location at the same time.
- traffic rules such as not running a red light or speeding ⁇ Can not drive in emergency lanes, can not compact lines, etc.
- ensure that the distance between obstacles (such as other vehicles) ) Are in the same location at the same time.
- the intelligent driving domain controller of the first vehicle can mark the corresponding trajectory specifically, so as to achieve Make way for special vehicles.
- the smart driving domain controller of the first vehicle can obtain the driving trajectory of the own vehicle, and the driving trajectory determined by other vehicles according to the customized trajectory prediction model, and then based on the obtained customization Trajectory planning for the first vehicle.
- the above method can obtain a customized trajectory prediction model for each driver in a smart car or a non-smart car in the manual driving mode, and predict their driving trajectory according to their respective driving habits. Compared with the traditional technology that uses uniform rules for trajectory prediction Method, the prediction result is closer to the trajectory of the vehicle.
- the intelligent driving domain controller can determine the driving trajectory of the self-vehicle according to the predicted trajectory obtained by the above-mentioned acquisition prediction model, reasonably plan the driving trajectory of the self-vehicle, reduce the risk of collision with other vehicles, and improve the driving safety of the intelligent vehicle.
- a specific example is used to describe a trajectory planning method provided by the embodiment of the present application.
- vehicle 1 is an autonomous vehicle in manual driving mode
- vehicle 2 is an autonomous vehicle in automatic driving mode
- vehicle 3 is a manually driven vehicle.
- the manually driven vehicle mentioned here refers to A device for self-driving vehicles, but the driver controls the driving of the vehicle.
- vehicle 1, vehicle 2 and vehicle 3 first obtain mutual trust through each other's safety certification, and then obtain each other's driving trajectory to realize trajectory planning.
- the following takes the trajectory planning process of the vehicle 1 as an example for description.
- the intelligent driving domain controller of vehicle 1 determines that vehicle 2 and vehicle 3 are in a circular area with vehicle 1 as the center and a radius as the set value, and then sends safety authentication messages to vehicles 2 and 3, the safety authentication message It includes the type of safety certification and the identification of vehicle 1. Then, after vehicle 2 and vehicle 3 confirm that they can communicate with vehicle 1 according to the safety certification message sent by vehicle 1, they respectively send safety certification response messages to vehicle 1 to inform vehicle 1 of the establishment of mutual trust. success. After mutual trust is established, the intelligent driving domain controller of vehicle 1 obtains the longitude and latitude of the current location of vehicle 1, and then obtains the relative speed and relative distance of vehicle 2 and vehicle 3 to vehicle 1, as well as the current lane attributes and road radius of the road.
- Vehicle 1 speed, acceleration, accelerator pedal opening, brake pedal opening, right front brake wheel cylinder, left front brake wheel cylinder, right rear brake wheel cylinder, left rear brake wheel cylinder, steering wheel angle, steering wheel steering Angular speed, steering wheel torque, gear position, turn signal; then, the intelligent driving domain controller of vehicle 1 obtains a trajectory prediction model that meets the current driving habits of the driver of vehicle 1 from the cloud server, and inputs the above data into the obtained
- the trajectory prediction model obtains the predicted trajectory points of the vehicle 1, and then obtains the manual driving trajectory of the vehicle 1, and sends the predicted manual driving trajectory to the vehicle 2 and the vehicle 3.
- the intelligent driving domain controller of the vehicle 1 obtains the automatic driving trajectory of the vehicle 2 and obtains the trajectory prediction model based on the driving habits of the driver driving the vehicle 3 to obtain the manual driving trajectory of the vehicle 3. In this way, the vehicle 1 can perform its own trajectory planning according to its predicted trajectory and the trajectories of the vehicle 2 and the vehicle 3 within the preset time period.
- the trajectory obtained by vehicle 1 is to keep the current lane straight for a preset period of time
- the trajectory of vehicle 3 obtained by vehicle 1 for the preset period of time is to keep straight on the adjacent right lane of vehicle 1, and vehicle 1
- the acquired travel trajectory of the vehicle 2 for the preset time period is to drive in the same lane as the vehicle 3 and go straight behind the vehicle 3 and then overtake the vehicle 3 in the lane where the vehicle 1 is located.
- vehicle 1 can continue to go straight on the premise that the lane change distance is reserved for vehicle 2, for example, we can slow down during straight going, until vehicle 2 successfully changes lanes and then resumes an appropriate increase in speed to continue going straight , To avoid collision with vehicle 2; or, after vehicle 1 determines that the distance from vehicle 3 is large enough, update the predicted trajectory, for example, it can change from straight to vehicle at the same time when vehicle 2 changes lanes or after vehicle 2 changes lanes.
- update the predicted trajectory for example, it can change from straight to vehicle at the same time when vehicle 2 changes lanes or after vehicle 2 changes lanes.
- the vehicle can combine the trajectory of other vehicles within the preset time period and its own trajectory for trajectory planning, where the trajectory of each vehicle matches the current driving state of the vehicle, and the vehicles driven by the driver are based on their own driving.
- the driving trajectory obtained by accustomed, compared with the traditional method of using unified rules to predict the trajectory the prediction result is closer to the driving trajectory of the vehicle, and the predicted trajectory used by the vehicle for trajectory planning is closer to the driving trajectory of the vehicle, which can make trajectory planning comparison Accuracy can ensure that the self-vehicle does not appear in the same position with any other vehicle at the same time, avoid collisions, and improve driving safety.
- FIG. 4 is a schematic structural diagram of a vehicle trajectory planning device provided by this application.
- the vehicle trajectory planning device 400 may include an acquiring unit 401 and a processing unit 402, specifically:
- the acquiring unit 401 is configured to acquire the first trajectory of the first vehicle; and acquire the second trajectory of at least one second vehicle based on the first communication technology;
- the processing unit 402 is configured to determine the trajectory plan of the first vehicle according to the first trajectory and the second trajectory of the at least one second vehicle.
- the acquiring unit 401 acquires the first trajectory of the first vehicle, it is specifically configured to: determine the current driving mode of the first vehicle, where the driving mode includes an automatic driving mode and a manual driving mode; Acquire the first trajectory of the first vehicle according to the driving mode of the first vehicle.
- the acquiring unit 401 acquires the first trajectory of the first vehicle according to the driving mode of the first vehicle, it is specifically configured to: when it is determined to be the automatic driving mode, acquire the An automatic driving trajectory, using the automatic driving trajectory as the first trajectory.
- the acquiring unit 401 acquires the first trajectory of the first vehicle according to the driving mode of the first vehicle, it is specifically configured to: when it is determined to be the manual driving mode, predict the driving mode of the first vehicle.
- Manual driving trajectory the predicted manual driving trajectory is used as the first trajectory.
- the acquiring unit 401 is specifically configured to: acquire a first parameter set, where the first parameter set includes the position of the first vehicle, the first parameter set The driving data of the obstacles around the vehicle relative to the first vehicle and the driving state of the first vehicle, where the driving state of the first vehicle is used to indicate the driving habits of the user currently driving the first vehicle;
- the trajectory prediction model corresponding to the first vehicle, the trajectory prediction model is obtained by training based on historical data of the driving habits of the user currently driving the first vehicle; the prediction model is based on the first parameter set and the trajectory prediction model The trajectory point of the first vehicle; the manual driving trajectory of the first vehicle is determined according to the trajectory point of the first vehicle.
- the location of the first vehicle includes the longitude and latitude that identify the location of the first vehicle; the obstacles around the first vehicle include one or more obstacles, and the driving data of any obstacle includes all the obstacles.
- the relative speed and relative distance of any obstacle relative to the first vehicle; the driving state of the first vehicle includes the current lane attributes of the road on which the first vehicle is located, the road radius, and the speed of the first vehicle , Acceleration, accelerator pedal opening, brake pedal opening, right front brake wheel cylinder, left front brake wheel cylinder, right rear brake wheel cylinder, left rear brake wheel cylinder, steering wheel angle, steering wheel angle speed, steering wheel torque , Gear position, turn signal.
- the driving data of any obstacle further includes the confidence level of the relative speed of the any obstacle.
- the trajectory point of the first vehicle includes the predicted longitude and the predicted latitude included in the predicted travel trajectory of the first vehicle.
- the trajectory point of the first vehicle further includes the confidence of the predicted longitude and the confidence of the predicted latitude.
- the device 400 for vehicle trajectory planning further includes a sending unit 403, configured to send the first parameter set and the trajectory point of the first vehicle to a cloud server, so that the cloud server is A parameter set and the trajectory points of the first vehicle are used to correct the trajectory prediction model; the acquisition unit 401 is also configured to receive the corrected trajectory prediction model sent by the cloud server, and use the corrected trajectory prediction
- the model and a second parameter set predict the trajectory point of the first vehicle, and the second parameter set is collected at the current moment, including the position of the first vehicle, and the relative obstacles around the first vehicle relative to the first vehicle.
- the driving data of the vehicle and the data of the driving state of the first vehicle is a sending unit 403, configured to send the first parameter set and the trajectory point of the first vehicle to a cloud server, so that the cloud server is A parameter set and the trajectory points of the first vehicle are used to correct the trajectory prediction model; the acquisition unit 401 is also configured to receive the corrected trajectory prediction model sent by the cloud server, and use the corrected trajectory prediction
- the model and a second parameter set predict the
- the device 400 for vehicle trajectory planning further includes a sending unit 403, configured to send the first trajectory to the at least one second vehicle.
- the processing unit 402 is further configured to: determine that the at least one second vehicle is within a set range, where the set range is a circular area centered on the first vehicle, and the circle The radius of the shaped area is a set value; or, it is determined that the at least one second vehicle has passed the safety certification.
- the first communication technology is V2X, a wireless communication technology for vehicles.
- the vehicle trajectory planning apparatus 400 of the embodiment of the present application may be implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), and the above PLD may be Complex programmable logical device (CPLD), field-programmable gate array (FPGA), generic array logic (GAL) or any combination thereof.
- ASIC application-specific integrated circuit
- PLD programmable logic device
- CPLD Complex programmable logical device
- FPGA field-programmable gate array
- GAL generic array logic
- the device 400 for vehicle trajectory planning may correspond to the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the device 400 for vehicle trajectory planning are to implement FIG. 3 For the sake of brevity, the corresponding process of each method in the method will not be repeated here.
- the driving trajectory of the self-vehicle can be obtained, and the driving trajectory determined by other vehicles according to the customized trajectory prediction model can be obtained, and then based on the obtained customized driving trajectory pair Self-vehicle trajectory planning.
- the above device it is possible to obtain a customized trajectory prediction model for each driver in a smart car or a non-smart car in the manual driving mode, and predict their driving trajectory according to their driving habits, which is compared with the traditional technology that adopts unified rules for trajectory Prediction, the prediction result is closer to the trajectory of the vehicle.
- the above-mentioned device can determine the driving trajectory of the self-vehicle according to the predicted trajectory obtained by the above-mentioned acquisition prediction model, reasonably plan the driving trajectory of the self-vehicle, reduce the risk of collision with other vehicles, and improve the driving safety of the smart car.
- the acquisition unit 401 and the processing unit 402 in FIG. 4 may realize their functions through more detailed one or more functional modules or units. 5 shows each unit to achieve.
- the acquisition unit 401 may use the millimeter wave radar data processing unit 501, the lidar data processing unit 502, the camera image data processing unit 503, the vehicle body data processing unit 504, and the positioning data processing unit in the device shown in FIG. 505.
- the data recording unit 506 and the trajectory prediction unit 507 are implemented;
- the sending unit 403 may be implemented by the data transceiving unit 508 and the human machine interface (HMI) signal sending unit 509 shown in FIG. 5.
- HMI human machine interface
- the millimeter wave radar data processing unit 501 used to receive data sent by a millimeter wave radar (for example, the millimeter wave radar 101 shown in FIG. 1).
- a millimeter wave radar for example, the millimeter wave radar 101 shown in FIG. 1.
- the coordinate system is converted to a unified vehicle body coordinate system, and the time stamp is sent to the data recording unit 506 and the trajectory prediction unit 507;
- the data is the transmission time of the beam to the obstacle and the speed of the beam, the distance and speed of the surrounding obstacles are calculated first, and then sent to the data recording unit 506 and the trajectory prediction unit 507.
- the laser radar data processing unit 502 used to receive data sent by a laser radar (for example, the laser radar 102 shown in FIG. 1).
- a laser radar for example, the laser radar 102 shown in FIG. 1
- the coordinate system is converted to a unified vehicle body coordinate system, and the time stamp is sent to the data recording unit 506 and the trajectory prediction unit 507;
- the data is the signal reflected from the obstacle and the transmitted signal, the distance, speed and other data of the surrounding obstacles are first calculated and sent to the data recording unit 506 and the trajectory prediction unit 507.
- Camera image processing unit 503 receives data transmitted by a camera (for example, the camera 103 shown in FIG. 1). When receiving data such as the speed and distance of surrounding obstacles sent by the smart camera, the coordinate system is converted into a unified vehicle body coordinate system, and the time stamp is sent to the data recording unit 506 and the trajectory prediction unit 507; when When an image or video is received, the image or video is first analyzed to obtain data such as the speed and distance of surrounding obstacles, and then sent to the data recording unit 506 and the trajectory prediction unit 507.
- a camera for example, the camera 103 shown in FIG. 1
- the coordinate system is converted into a unified vehicle body coordinate system
- the time stamp is sent to the data recording unit 506 and the trajectory prediction unit 507
- the image or video is first analyzed to obtain data such as the speed and distance of surrounding obstacles, and then sent to the data recording unit 506 and the trajectory prediction unit 507.
- the body data processing unit 504 obtains data of the vehicle (own vehicle), for example, obtains the data sent by the other controller 107 of the vehicle shown in FIG. 1, and sends the obtained data to the data recording unit 506 and the trajectory prediction unit 507.
- the positioning data processing unit 505 receives positioning data (for example, obtained from the high-precision positioning device shown in FIG. 1), and sends it to the data recording unit 506 and the trajectory prediction unit 507.
- positioning data for example, obtained from the high-precision positioning device shown in FIG. 1
- the data recording unit 506 stores the received data in a memory (for example, read-only memory (ROM)), and sends it to the data transceiver unit 508 periodically.
- a memory for example, read-only memory (ROM)
- Data transceiver unit 508 periodically sends the data received from the data recording unit 506 to the cloud (for example, the cloud 100 shown in FIG. 1), regularly receives cloud model parameters, and sends them to the trajectory prediction unit 507, which will be obtained in real time The predicted trajectory is sent to surrounding vehicles.
- the cloud for example, the cloud 100 shown in FIG. 1
- the trajectory prediction unit 507 which will be obtained in real time The predicted trajectory is sent to surrounding vehicles.
- Trajectory prediction unit 507 predict the trajectory of the vehicle through a model based on the parameters returned from the cloud, and send the trajectory to the HMI signal sending unit 509 and the data transceiver unit 508.
- HMI signal sending unit 509 Send the received trajectory to the display unit so that the driver can know the driving trajectory of the smart car. Optionally, the driver can also change the driving trajectory through the display unit.
- the above-mentioned device can determine the driving trajectory of the self-vehicle according to the predicted trajectory obtained by the above-mentioned acquisition prediction model, reasonably plan the driving trajectory of the self-vehicle, reduce the risk of collision with other vehicles, and improve the driving safety of the smart car.
- FIG. 6 is a schematic structural diagram of an intelligent driving domain controller provided by an embodiment of the application.
- the intelligent driving domain controller is applied to the system shown in FIG. 1 to implement the vehicle trajectory planning shown in FIG. 3 method.
- the intelligent driving domain controller 600 may include: a processor 601, a memory 602, and a bus 603. Wherein, the processor 601 and the memory 602 communicate through the bus 603, and may also communicate through other means such as wireless transmission.
- the memory 602 is used to store instructions, and the processor 601 is used to execute instructions stored in the memory 602.
- the memory 602 stores program codes, and the processor 601 can call the program codes stored in the memory 602 to perform the following operations:
- the intelligent driving domain controller 600 shown in FIG. 6 further includes a memory and a communication interface (not shown in FIG. 6), where the memory may be physically integrated with the processor, or in the processor or independent
- the computer program can be stored in memory or storage.
- the computer program code for example, the kernel, the program to be debugged, etc. stored in the memory is copied to the memory, and then executed by the processor.
- the processor 601 may be a central processing unit (CPU), and the processor 601 may also be other general-purpose processors or digital signal processing (DSPDSP). , Application-specific integrated circuit (ASIC), programmable logic device (programmable logic device, PLD); the above-mentioned PLD can be a complex programmable logic device (complex programmable logic device, CPLD), field programmable gate array ( Field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof; or the processor 601 may be other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or any conventional processor.
- the memory 602 may include a read-only memory and a random access memory, and provides instructions, programs, data, and the like to the processor 601.
- the program may include program code, and the program code includes computer operation instructions.
- the memory 602 may also include a non-volatile random access memory.
- the memory 602 may also store device type information.
- the memory 602 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
- the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
- the volatile memory may be random access memory (RAM), which is used as an external cache.
- RAM random access memory
- SRAM static random access memory
- DRAM dynamic random access memory
- SDRAM synchronous dynamic random access memory
- Double data rate synchronous dynamic random access memory double data date SDRAM, DDR SDRAM
- enhanced SDRAM enhanced synchronous dynamic random access memory
- SLDRAM synchronous connection dynamic random access memory
- direct rambus RAM direct rambus RAM
- the bus 603 may also include an address bus, a power bus, a control bus, and a status signal bus.
- the bus 603 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc., or it can be a controller area network (CAN), and It can be a vehicle-mounted Ethernet (Ethernet) or other internal bus to realize the connection of the various devices/devices shown in FIG. 6.
- PCI peripheral component interconnect
- EISA extended industry standard architecture
- CAN controller area network
- Ethernet vehicle-mounted Ethernet
- the intelligent driving domain controller 600 may correspond to the device 400 for vehicle trajectory planning in the embodiment of the present application, and may correspond to the intelligent driving domain controller that executes the method shown in FIG. 3 as the main body.
- the above-mentioned and other operations and/or functions of the various modules in the intelligent driving domain controller 600 are used to implement the corresponding procedures of the various methods in FIG. 3, and are not repeated here for brevity.
- the driving trajectory of the vehicle can be obtained, and the driving trajectory determined by other vehicles according to the customized trajectory prediction model can be obtained, and then based on the obtained customized driving trajectory pair Self-vehicle trajectory planning.
- the intelligent driving domain controller 600 it is possible to obtain a customized trajectory prediction model for each driver in a smart car or a non-smart car in the manual driving mode, and predict their driving trajectory according to their driving habits, which is compared with the traditional technology. Using uniform rules for trajectory prediction, the prediction result is closer to the trajectory of the vehicle.
- the smart driving domain controller 600 can determine the driving trajectory of the self-vehicle based on the predicted trajectory obtained by the acquisition prediction model, reasonably plan the driving trajectory of the self-vehicle, reduce the risk of collision with other vehicles, and improve the driving safety of the smart car.
- the present application also provides a smart car, which may include the above-mentioned smart driving domain controller or vehicle trajectory planning device.
- the smart car may be the first vehicle involved in this application.
- the present application also provides a trajectory prediction system as shown in FIG. 1.
- the trajectory prediction system includes a first vehicle, at least one second vehicle, and the cloud.
- Each of the above-mentioned components or devices is used to execute the corresponding method in the above-mentioned method shown in FIG.
- the operation steps of the main body are not repeated here.
- the foregoing embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination.
- the above-mentioned embodiments may be implemented in the form of a computer program product in whole or in part.
- the computer program product includes one or more computer instructions.
- the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
- the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
- the computer instructions may be transmitted from a website, computer, server, or data center.
- 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 or a data center that includes one or more sets of available media.
- the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium.
- the semiconductor medium may be a solid state drive (SSD).
- the disclosed system, device, and method can be implemented in other ways.
- the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
- the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the technical solution of the present application.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Optics & Photonics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
一种车辆轨迹规划的方法、装置、智能驾驶域控制器(104)和智能车,用以实现智能车准确进行轨迹规划。方法包括:第一车辆的智能驾驶域控制器(104)获取第一车辆的第一轨迹,并基于第一通信技术获取至少一辆第二车辆的第二轨迹;然后,根据第一轨迹和至少一辆第二车辆的第二轨迹确定第一车辆的轨迹规划。以此实现车辆利用不同规则预测车辆轨迹,进而更准确的规划自车的行驶轨迹的目的,提高智能车行驶的安全性。
Description
相关申请的交叉引用
本申请要求在2019年12月24日提交中国专利局、申请号为201911348578.5、申请名称为“车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及智能车领域,尤其涉及一种车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车。
智能车(smart/intelligent car)在自动驾驶(automated driving,ADS)过程中会根据周围环境,规划出一条无碰撞的安全路径。其中,障碍物信息是路径规划的重要输入之一。传统技术中,缺少对障碍物的轨迹预测,仅就当前时刻障碍物的行驶情况进行分析和预测,是一种静态分析过程。但是,随着时间的变化,障碍物的行驶轨迹是动态变化的过程,障碍物的行驶轨迹可能会发生跳变甚至是与其他人或物的碰撞。而随着汽车产业的发展,未来相当长一段时间内,道路上会存在自动驾驶车辆和人工驾驶车辆共存的现象,智能车需要对周围车辆的行驶轨迹进行预测,进而规划自车的行驶轨迹。当前轨迹预测主要是智能车依靠自身配备的传感器,根据周围车辆的历史数据及道路拓扑等信息,并假设障碍物将会保持当前的运动状态,速度和方向都不会有较大改变,采用统一的规则(如默认前车遇到障碍物优先从左侧避让)对周围车辆的轨迹进行预测。但是,实际道路上车辆运动有很大不确定性,例如,人工驾驶车辆的行为由驾驶员主观决定,而自动驾驶车辆的行为在同一场景下存在多种行为决策的可能。采用上述方法难以做出确定性预测,从而会导致自动驾驶车辆无法准确进行轨迹规划。因此,如何提供一种准确预测车辆轨迹的方法成为智能车领域亟待解决的技术问题。
发明内容
本申请提供一种车辆轨迹规划的方法及装置,用以智能车准确进行轨迹规划。
第一方面,本申请提供了一种车辆轨迹规划的方法,所述方法可以应用于第一车辆的智能驾驶域控制器,所述智能驾驶域控制器获取所述第一车辆的第一轨迹,并基于第一通信技术获取至少一辆第二车辆的第二轨迹;然后根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。以此避免传统技术中仅以车辆当前时刻的运行轨迹进行轨迹预测造成的判断错误,本方法可以识别其他车辆轨迹的变化,确保第一车辆不与其他任一车辆在同一时刻出现在同一位置,避免发生碰撞,从而可以提高智能车行驶安全性。
在一个可能的设计中,所述智能驾驶域控制器在获取所述第一车辆的第一轨迹时具体方法可以为:所述智能驾驶域控制器先确定所述第一车辆当前的驾驶模式,然后根据所述 第一车辆的驾驶模式获取所述第一车辆的第一轨迹,其中,所述驾驶模式包括自动驾驶模式和人工驾驶模式。通过上述方法,智能驾驶域控制器可以根据第一车辆的实际驾驶模式准确地获取所述第一车辆的第一轨迹,进而后续准确地进行轨迹规划。
在另一个可能的设计中,所述智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹时,具体方法可以为:当所述智能驾驶域控制器确定所述第一车辆当前的驾驶模式为自动驾驶模式时,所述智能驾驶域控制器获取所述第一车辆的自动驾驶轨迹,然后将所述自动驾驶轨迹作为所述第一轨迹。这样,所述第一车辆可以获得与所述第一车辆的自动驾驶模式匹配的轨迹,进而完成后续准确地进行轨迹规划。
在另一个可能的设计中,所述智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹时,具体方法可以为:当所述智能驾驶域控制器确定所述第一车辆当前的驾驶模式为人工驾驶模式时,所述智能驾驶域控制器可以预测所述第一车辆的人工驾驶轨迹,然后将预测得到的所述人工驾驶轨迹作为所述第一轨迹。当第一车辆为人工驾驶模式时,智能驾驶域控制器能够根据预测获得的与当前驾驶员的驾驶习惯匹配的第一轨迹,进而完成后续准确地进行轨迹规划。
在另一个可能的设计中,所述智能驾驶域控制器预测所述第一车辆的人工驾驶轨迹时具体方法可以为:所述智能驾驶域控制器获取第一参数集合以及所述第一车辆对应的轨迹预测模型,并根据所述第一参数集合和所述轨迹预测模型预测所述第一车辆的轨迹点,最后根据所述第一车辆的轨迹点确定所述第一车辆的人工驾驶轨迹;其中,所述第一参数集合包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态,所述第一车辆的行驶状态用于指示当前驾驶所述第一车辆的用户的驾驶习惯;所述轨迹预测模型为根据当前驾驶所述第一车辆的用户的驾驶习惯的历史数据训练获得。通过上述方法,所述智能驾驶域控制器在预测自车行驶轨迹时,可以结合当前驾驶员驾驶所述第一车辆的驾驶习惯,使得到的轨迹更符合实际的轨迹,准确性更高。
在另一个可能的设计中,所述第一车辆的位置可以包括标识所述第一车辆所在位置的经度和纬度;所述第一车辆周围障碍物可以包括一个或多个障碍物,任一个障碍物的行驶数据可以包括所述任一个障碍物相对所述第一车辆的相对速度和相对距离;所述第一车辆的行驶状态包括所述第一车辆所在的道路的当前车道属性、道路半径、所述第一车辆的速度、加速度、加速踏板开度、制动踏板开度、右前制动轮缸、左前制动轮缸、右后制动轮缸、左后制动轮缸、方向盘转角、方向盘转向角速度、方向盘转矩、档位、转向灯信号。
在另一个可能的设计中,所述第一车辆的轨迹点包括所述第一车辆预测行驶轨迹中包括的预测经度和预测纬度。这样每个轨迹点包含的预测精度和预测维度就可以得到一个第一车辆的预测位置,预测位置就可以组成一条预测行驶轨迹。
在另一个可能的设计中,所述第一车辆的轨迹点还包括所述预测经度的置信度和所述预测纬度的置信度。其中,预测精度的置信度标识了预测精度的准确率,预测纬度的置信度标识了预测纬度的准确率,这样在根据轨迹点得到预测轨迹时,可以了解轨迹点的准确率,明确预测轨迹的准确率。
在另一个可能的设计中,所述智能驾驶域控制器可以向云服务器发送所述第一参数集合和所述第一车辆的轨迹点,以使所述云服务器根据所述第一参数集合和所述第一车辆的轨迹点校正所述轨迹预测模型;并接收所述云服务器发送的校正后的轨迹预测模型,然后,所述智能驾驶域控制器利用所述校正后的轨迹预测模型和第二参数集合预测所述第一车 辆的轨迹点,所述第二参数集为当前时刻收集的包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态的数据。以此获得根据每个驾驶员的驾驶习惯确定的轨迹预测模型,上述方法能够获得人工驾驶模式的智能车或非智能车中每个驾驶员定制化的轨迹预测模型,并按照各自的驾驶习惯预测其行驶轨迹,相比于传统技术中采用统一规则进行轨迹预测的方法,预测结果更接近车辆的行驶轨迹。进一步地,智能驾驶域控制器可以根据上述获取预测模型获得的预测轨迹确定自车的行驶轨迹,合理规划自车行驶轨迹,降低与其他车辆碰撞的风险。
在另一个可能的设计中,所述智能驾驶域控制器向所述至少一辆第二车辆发送所述第一轨迹。这样,可以使至少一辆第二车辆结合所述第一轨迹进行轨迹规划。
在另一个可能的设计中,所述智能驾驶域控制器在与所述至少一辆第二车辆通信之前,确定所述至少一辆第二车辆在设定范围内,或者,所述智能驾驶域控制器确定与所述至少一辆第二车辆已通过安全认证;其中,所述设定范围为以所述第一车辆为圆心的圆形区域,所述圆形区域的半径为设定值。以此保证车辆间数据传输的安全性。
在另一个可能的设计中,所述第一通信技术为车用无线通信技术V2X。
在另一个可能的设计中,智能驾驶域控制器按照如下规则中至少一种规则确定所述第一车辆的行驶轨迹:规则一:不违反交通规则;规则二:与障碍物(如其他车辆)之间的距离需要大于预设值;规则三:不与障碍物(如其他车辆)在同一时刻位于同一个位置。
第二方面,本申请提供了一种智能驾驶域控制器,所述智能驾驶域控制器包括用于执行第一方面或第一方面任一种可能设计中的车辆轨迹规划方法的各个模块或单元,例如处理单元和获取单元。
第三方面,本申请提供了一种智能驾驶域控制器,所述智能驾驶域控制器包括处理器和存储器,智能驾驶域控制器运行时,所述处理器执行所述存储器中所存储的计算机执行计算机程序或指令,以使所述智能驾驶域控制器执行如上述第一方面或第一方面任一种可能设计中所示的相应的方法。
第四方面,本申请提供了一种智能车,所述智能车可以包括上述第二方面或第三方面中任一所述的智能驾驶域控制器。所述智能车可以为上述第一方面涉及的第一车辆。
第五方面,本申请提供了一种系统,所述系统可以包括上述涉及的第一车辆和至少一辆第二车辆。
第六方面,本申请提供一种计算机可读存储介质,所述计算机可读存储介质中存储有程序或指令,当其在计算机上运行时,使得计算机执行第一方面或第一方面任一种可能的设计中所述的方法。
第七方面,本申请提供了一种包含指令的计算机程序产品,当其在计算机上运行时,使得计算机执行第一方面或第一方面任一种可的设计中所述的方法。
图1为本申请提供的一种车辆轨迹规划的方法适用的系统的架构示意图;
图2为本申请提供的一种车辆行驶的场景示意图;
图3为本申请提供的一种车辆轨迹规划的方法的流程图;
图4为本申请提供的一种车辆轨迹规划的装置的结构示意图;
图5为本申请提供的一种装置的结构示意图;
图6为本申请提供的一种智能驾驶域控制器的结构图。
下面将结合附图对本申请实施例作进一步地描述说明。
图1示出了本申请实施例提供的一种车辆轨迹规划的方法适用的系统的架构示意图,所述系统的架构中包括至少两辆车辆以及云端100。其中,在图1中以n辆车辆示出,分别为车辆(vehicle)1、车辆2……车辆n,n为大于或者等于2的整数。具体的:n辆车辆中包括智能车和非智能车;所述至少两辆车辆为具备人工驾驶模式的自动驾驶车辆,在实际行驶中,每辆车辆可以工作在自动驾驶模式下,也可以工作在人工驾驶模式下。
其中,任一辆车辆的均可以包括传感器、智能驾驶域控制器104、车载通信设备105、高精度定位设备106、车辆其他控制器107和人机交互系统108。其中,传感器包括以下设备中一种或多种:至少一个毫米波雷达101、至少一个激光雷达102、至少一个相机103具体地,在图1中仅以车辆1示出。下面对车辆包含的上述模块的功能进行详细解释:
毫米波雷达101:是工作在毫米波段(millimeter wave)探测的雷达,用于采集到达障碍物的光束传输时间和光束的速度,并将采集的数据发送给所述智能驾驶域控制器104;或者用于在采集光束传输时间和光束的速度后,计算周围障碍物的距离、速度等数据,并将计算得到的数据发送给所述智能驾驶域控制器104。
激光雷达102:是以发射激光束探测目标的位置、速度等特征量的雷达系统。其工作原理是向目标发射探测信号(激光束),然后将接收到的从目标反射回来的信号(目标回波)与发射信号进行比较,作适当处理后,就可获得目标的有关数据,如目标距离、方位、高度、速度、姿态、甚至形状等参数。在本申请中,激光雷达102用于采集从障碍物反射回来的信号,并将反射回来的信号和发射信号发送给所述智能驾驶域控制器104;或者采集从障碍物反射回来的信号后,与发射信号对比,处理得到周围障碍物的距离、速度等数据,并将处理得到的数据发送给所述智能驾驶域控制器104。
相机103:用于采集周围图像或视频,并将采集的图像或视频发送给所述智能驾驶域控制器104;其中,当相机103是智能摄像头时,相机103可以采集图像或视频后,分析图像或视频得周围障碍物的速度和距离等,并将分析得到的数据发送给所述智能驾驶域控制器104。
高精度定位设备106:采集当前车辆的精确位置信息(误差小于20cm),及所述精确位置信息对应的全球定位系统(global positioning system,GPS)时间信息,并将采集的信息发送给所述智能驾驶域控制器104。其中,所述高精度定位设备106可以是组合定位系统或组合定位模块。所述高精度定位设备106可以包括全球导航卫星系统(global navigation satellite system,GNSS)、惯性测量单元(inertial measurement unit,IMU)等设备和传感器。全球导航卫星系统能够输出一定精度(例如,5-10Hz)的全局定位信息,惯性测量单元频率一般较高(例如,1000Hz),所述高精度定位设备106可以通过融合惯性测量单元和全球导航卫星系统的信息,输出高频的精准定位信息(一般要求200Hz以上)。
车辆其他控制器107:执行所述智能驾驶域控制器104的控制命令,将车辆转向、档位、加速、减速等相关信息发送给所述智能驾驶域控制器104。
人机交互系统108:提供智能车与驾驶员消息交互的音视频方式,可以利用显示屏显示本车辆与其他车辆的轨迹。
智能驾驶域控制器104:可以设置于车辆内的,智能驾驶域控制器104具体由处理器实现,处理器包括中央处理器(central processing unit,CPU)或者具备处理功能的设备或模块。例如,智能驾驶域控制器104可以是车载移动数据中心(mobile data center,MDC)。执行自动驾驶功能时,即在自动驾驶模式下,智能驾驶域控制器104将轨迹规划信息发送到车载通信设备105,将自身位置信息及周围其他车辆预测轨迹发送至所述人机交互系统108;人驾驶车辆时,即在人工驾驶模式下,将传感器信息和车辆实际轨迹及自身预测轨迹(根据传感器信息、车辆其他控制器传来的信息由神经网络或其他人工智能(artificial intelligence,AI)算法预测)发送到车载通信设备105,将自身位置信息及周围其他车辆的预测轨迹发送至人机交互系统108。
车载通信设备105:与其他车辆通信的设备,接收其他车辆轨迹预测信息(也可描述成预测轨迹、轨迹信息等)并发送给智能驾驶域控制器104,并将自身轨迹发送给周围其他车辆;与云端100通信,将车辆上传感器信息、定位信息及其他控制器信息发送到云端100,接收云端100训练好的模型参数。例如车载通信设备105可以是远程信息处理器(telematics BOX,TBOX)。
需要说明的是,上述涉及的周围障碍物在这里指的是其他车辆。障碍物的距离和速度分别为障碍物相对于自车的相对距离和相对速度。
需要说明的是,在车辆进行通信的过程中,为了提高智能车行驶的安全性,车辆间的信息传输可以建立互信。例如,任一辆车辆可以与预设范围内的车辆进行信息传输,所述预设范围可以是以自车为圆心,设定值为半径的圆形区域。其中所述半径的设定值可以基于车辆可支持的V2X通信的范围设定。又例如,车辆间可以通过鉴权建立互信,具体可以通过交互认证信息,认证通过后则可以进行通信,共享信息。又例如,车辆见可以在设定时间周期内进行信息传输。又例如,车辆间可以遵循汽车信息安全标准21434等,接收的其他车辆的信息仅用于自车驾驶使用,不做记录。当然,还有其他方式,本申请此处不再一一列举。
云端100:根据传感器信息、定位信息及其他控制器信息训练模型,将训练好的模型参数发送给所述车载通信设备105。其中,云端100可以是能实现模型训练的云数据中心,还可以是能够进行模型训练的物理设备或虚拟机等,本申请对此不作限定。
基于上述系统,在车辆行驶过程中,任何一辆车辆均可以获取周围车辆预设时段内的行驶轨迹,来约束本车辆的轨迹规划,从而提高安全性。例如,图2所示的场景示意图中,该场景中有车辆1,车辆2和车辆3共三辆自动驾驶车辆,其中三辆车辆中至少有一辆车辆处于人工驾驶模式。其中,三辆车辆均会根据自身的驾驶模式来预测自车的行驶轨迹。例如,以车辆1进行轨迹规划为例说明,在车辆1进行轨迹规划的过程中,车辆1可以通过V2X技术获取车辆2和车辆3预测的行驶轨迹,然后结合自身预测的行驶轨迹来进行轨迹规划。这样可以提高自身轨迹规划的准确性,从而提高行驶的安全性。
应理解,车辆2和车辆3进行轨迹规划的方法与车辆1进行轨迹规划的方法类似,可以相互参见。
需要说明的是,上述涉及的预设时段可以基于V2X传输技术所需的时延确定,还可以是预设的经验值,例如5-10秒(s);当然还可以是其他方式确定,本申请对此不作限定。
基于上述描述,本申请实施例提供了一种车辆轨迹规划的方法,适用于图1所示的系统,以及图2所示的场景。所述方法可以用于第一车辆的轨迹规划,所述第一车辆为智能 车。所述方法可以由所述第一车辆的智能驾驶域控制器实现。参阅图3所示,所述方法的具体流程可以包括:
步骤301:所述第一车辆的智能驾驶域控制器获取所述第一车辆的第一轨迹。
具体的,所述第一车辆的智能驾驶域控制器获取所述第一轨迹时,具体方法可以为:所述第一车辆的智能驾驶域控制器确定所述第一车辆当前的驾驶模式,所述驾驶模式包括自动驾驶模式和人工驾驶模式;然后,所述智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹。
在一种可能的实现方式中,所述第一车辆的智能驾驶域控制器确定所述第一车辆的驾驶模式时,所述驾驶域控制器可以通过车载通信装置与其他车辆进行通信,例如,发送驾驶模式查询消息,再由其他车辆以应答消息的形式通知第一车辆其驾驶模式。可选地,第一车辆还可以通过相机采集其他车辆的图像,进而分析其他车辆中驾驶员的状态(例如,驾驶员是否手握方向盘,是否处于休息状态等形式)判断该车辆是否处于自动驾驶模式。
示例性的,所述第一车辆的智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹,具体可以包含以下两种情况:
情况1:当所述智能驾驶域控制器确定为自动驾驶模式时,所述智能驾驶域控制器获取所述第一车辆的自动驾驶轨迹,将所述自动驾驶轨迹作为所述第一轨迹。
情况2:当所述智能驾驶域控制器确定为人工驾驶模式时,所述智能驾驶域控制器预测所述第一车辆的人工驾驶轨迹,将预测得到的所述人工驾驶轨迹作为所述第一轨迹。
在一种示例中,当所述第一车辆处于人工驾驶模式时,所述智能驾驶域控制器预测所述第一车辆的人工驾驶轨迹,具体方法可以为:所述智能驾驶域控制器获取第一参数集合,所述第一参数集合包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态,所述第一车辆的行驶状态用于指示当前驾驶所述第一车辆的用户的驾驶习惯;所述智能驾驶域控制器获取所述第一车辆对应的轨迹预测模型,所述轨迹预测模型根据当前驾驶所述第一车辆的用户的驾驶习惯的历史数据训练获得;所述智能驾驶域控制器根据所述第一参数集合和所述轨迹预测模型预测所述第一车辆的轨迹点;所述智能驾驶域控制器根据所述第一车辆的轨迹点确定所述第一车辆的人工驾驶轨迹。
示例性地,所述第一车辆的位置可以包括标识所述第一车辆当前时刻所在位置在地球坐标系中的经度(P_long)和纬度(P_lati)。可选地,在轨迹预测模型训练的过程中,可以将预测的结果和所述第一车辆的位置进行对比,来确认预测结果是否准确,来不断调整模型,来使训练的到的轨迹预测模型的准确性较高。
所述第一车辆周围障碍物包括一个或多个障碍物,任一个障碍物的行驶数据可以包括所述任一个障碍物相对所述第一车辆的相对速度(Obj_v)和相对距离(Obj_d)。需要说明的是,任一个障碍物在这里可以是一辆车辆,例如第二车辆。
所述第一车辆的行驶状态可以包括所述第一车辆所在的道路的当前车道属性、道路半径(road_radius)、所述第一车辆的速度、加速度、加速踏板开度(Acc_ped)、制动踏板开度(Bra_ped)、右前制动轮缸(P_(Cy,FR))、左前制动轮缸(P_(Cy,FL))、右后制动轮缸(P_(Cy,RR))、左后制动轮缸(P_(Cy,RL))、方向盘转角(Ste_ang)、方向盘转向角速度(Ste_angv)、方向盘转矩(Ste_torq)、档位(gear)、转向灯信号(Turn_sig)。
其中,所述道路的当前车道属性可以是当前道路的车道数量、车道是弯道还是直道等 等。在当前车道是弯道时,所述道路半径可以是弯道半径;在当前车道为直道时,所述道路半径可以是零,或者无穷大。所述加速踏板开度是指加速踏板开合的百分比,其中,可以将加速踏板被踩到底时认为是百分之百,将加速踏板没有被踩下时认为是零。所述右前制动轮缸、所述左前制动轮缸、所述右后制动轮缸和所述左后制动轮缸分别为第一车辆每个车轮上的控制参数。所述档位为自动驾驶车辆在行驶过程中前进档中划分的不同级别,不同的级别对应不同速度。
基于上述参数所述第一车辆的智能驾驶域控制器预测的所述第一车辆的轨迹点可以包括所述第一车辆预测行驶轨迹(也即预测的人工驾驶轨迹)中包括的预测经度和预测纬度。可选的,所述第一车辆的轨迹点还包括所述预测经度的置信度和所述预测纬度的置信度。其中,所述第一车辆的轨迹点可以是轨迹点集合,可以包含一段时间内(例如5s)内的轨迹点。其中,预测精度的置信度标识了预测精度的准确率,预测纬度的置信度标识了预测纬度的准确率,这样在根据轨迹点得到预测轨迹时,可以了解轨迹点的准确率,明确预测轨迹的准确率。以使智能驾驶域控制器选择准确率较高的预测轨迹进行后续的轨迹规划。
在具体实施时,不同用户有不同的驾驶习惯,不同用户驾驶第一车辆时的相关参数也不相同。其中,障碍物的相对距离、相对速度、道路的车道属性、道路半径描述了驾驶员(即用户)所处的环境,车辆的速度、加速度描述了车辆状态,加速踏板开度描述了当前环境和车辆状态下驾驶员踩油门的习惯,制动踏板开度、右前制动轮缸、左前制动轮缸、右后制动轮缸、左后制动轮缸描述了当前环境和车辆状态下驾驶员踩刹车的习惯,方向盘转角、方向盘转向角速度、方向盘转矩、转向灯信号描述了当前环境和车辆状态下驾驶员转向的习惯。不同的驾驶员在驾驶车辆时,上述参数是不相同的。本申请中,针对不同用户,根据每个用户的驾驶习惯分别进行训练,训练符合该用户的预设神经网络模型的参数,从而可以预测出符合自身特性的轨迹。
具体地,上述涉及所述第一车辆的行驶状态仅指示了当前驾驶所述第一车辆的用户的驾驶习惯,所述预测神经网络模型也是针对驾驶所述第一车辆的用户的驾驶习惯训练得到的。例如,在具体训练时,可以通过云服务器进行模型训练,云服务器将训练好的模型参数发送给所述智能驾驶域控制器。在云服务器进行模型训练时,所用的训练集包括输入集和输出集,其中,输入集可以是所述第一车辆的智能驾驶域控制器记录的当前驾驶所述第一车辆的用户在过去一段时间内或实时驾驶所述第一车辆时获取的多个参数集合,每个参数集合均与所述第一参数集合包括的参数相同;每个参数集合对应的第一车辆的轨迹点作为输出集,也即模型训练时的期望输出。具体的,所述智能驾驶域控制器将上述训练集通过V2X发送到所述云服务器。示例性的,所述云服务器的训练过程可以如下:
(1)网络确定:即确定所述预测神经网络模型的尺寸。其中,采用试凑法确定隐含层的神经元数目,具体地,先设置较少的神经元数目来训练网络,然后逐个增加,用同一样本集进行训练,对比结果,当结果不再有改善时,停止增加神经元数目,确定最佳的神经元数目。在本申请中,所述预测神经网络模型可以包含一个输入层,一个隐含层和一个输出层。
其中,隐含层神经元数目可以先根据经验公式确定,然后逐个增加。可选地,经验公式可参考下述公式一或其他公式:
其中,m为输入集维数(也即输入集的参数个数),l为输出集维数。
(2)训练模型:即确定预测神经网络模型的模型参数。
例如,隐含层的输出集为{S
0,S
1,……,S
t,S
t+1,……};其中,隐含层的输出集是将训练集的输入集输入模型后,根据设定的隐含层的函数得到的训练过程中的中间值集合,其中,输入集可以是所述第一车辆的智能驾驶域控制器记录的当前驾驶所述第一车辆的用户在过去一段时间内或实时驾驶所述第一车辆时获取的多个参数集合,每个参数集合均与所述第一参数集合包括的参数相同;具体的隐含层的输出函数符合如下述公式二:
S
t=f(U×X
t+W×S
t-1) 公式二;
其中,X
t为训练集中的输入集,U和W为权重系数;
则得到训练集中的输出集O
t符合以下公式三:
O
t=softmax(VS
t) 公式三;
其中,softmax(VS
t)是规划指数函数,其中,规划指数函数用于将隐含层的书输出集处理得到轨迹预测模型的最终输出结果;V为权重矩阵。
进一步地,通过损失函数,计算损失值,调整模型参数,直至损失函数几乎不再改善。其中,损失函数用于使训练好的模型达到模型精度要求。使用训练集训练模型,使用未训练的数据集测试训练好的模型,当模型精度达到要求时,确定模型参数U、W、V,即得到针对当前驾驶所述第一车辆的用户的驾驶习惯的预测轨迹模型。示例性的,所述损失函数J可以符合以下公式四:
其中,N为训练集包含的输入集和输出集对的数目。
基于上述过程,云服务器就完成了预测神经网络模型的训练,然后云服务器将最后确定的模型参数U、W、V传输给所述第一车辆的智能驾驶域控制器,以使所述智能驾驶域控制器预测所述第一车辆的轨迹点。
在一种可选的实施方式中,所述第一车辆的智能驾驶域控制器可以向云服务器发送所述第一参数集合和所述第一车辆的轨迹点,以使所述云服务器根据所述第一参数集合和所述第一车辆的轨迹点校正所述轨迹预测模型;之后所述智能驾驶域控制器接收所述云服务器发送的校正后的轨迹预测模型,并利用所述校正后的轨迹预测模型和第二参数集合预测所述第一车辆的轨迹点,所述第二参数集为当前时刻收集的包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态的数据。也就是说所述云服务器可以根据智能车的智能驾驶域控制器或非智能车的控制器发送的驾驶数据不断更新之前训练好的轨迹预测模型,以使模型训练越来越准确,进而使车辆的轨迹预测越来越准确,从而可以进行更加准确的轨迹规划,提高安全性。
对于每个车辆而言,可以由其车载控制器收集当前驾驶员的驾驶数据,并将该数据发送至云服务器,再由云服务器根据驾驶数据训练获得与当前驾驶员驾驶习惯匹配的定制化驾驶模型,并将该定制化驾驶模型发送给车载控制器。当第一车辆的智能驾驶域控制器进行自车轨迹预测时,可以根据各个车辆发送的预测的行驶轨迹确定自车的行驶轨迹。可选地,第一车辆的智能驾驶域控制器也可以获取周围车辆的驾驶模型和当前时刻驾驶员的驾驶数据,并根据上述驾驶模型和驾驶数据分别预测各个车辆的行驶轨迹。作为一种可能的实施例,上述各个车辆的行驶轨迹的预测过程也可以由云服务器完成,各个车辆将自车当 前时刻驾驶员的驾驶数据发送至云服务器,由云服务器分别根据每辆车对应的定制化驾驶模型预测行驶轨迹,并将该预测的行驶轨迹发送给第一车辆的智能驾驶域控制器,以使得该智能域驾驶域控制器确定第一车辆的行驶轨迹。
在一种具体的实施方式中,所述第一车辆的智能驾驶域控制器在获取了所述第一轨迹之后,向所述至少一辆第二车辆发送所述第一轨迹,以使所述至少一辆第二车辆中的任一辆第二车辆结合自身的轨迹进行轨迹规划。
步骤302:至少一辆第二车辆中每辆第二车辆的智能驾驶域控制器分别获取所述每辆第二车辆的第二轨迹。其中,图3中以两辆第二车辆示意,但是应理解,图3中车辆的数量并不作为对至少一辆的数量的限定,可以为一辆,或者比两辆多的第二车辆。
具体的,任一辆第二车辆的智能驾驶域控制器获取第二轨迹的方法,与步骤301中所述第一车辆的智能驾驶域控制器获取所述第一轨迹的方法相同,可以相互参见,此处不再详细描述。
步骤303:所述第一车辆的智能驾驶域控制器基于第一通信技术获取所述至少一辆第二车辆的第二轨迹。
在一种示例性的实现方式中,所述第一车辆的智能驾驶域控制器在获取其他车辆的数据或者向其他车辆发送数据时,均可以采用步骤303涉及的第一通信技术,例如,所述第一通信技术可以是V2X技术。
在一种可选的实施方式中,所述第一车辆的智能驾驶域控制器在获取其他车辆(例如至少一辆第二车辆)的数据或者向其他车辆发送数据之前,所述智能驾驶域控制器确定当前时刻处于预设的与其他车辆通信的时间周期内;或者,所述智能驾驶域控制器确定与其他车辆已通过安全认证,也即通过鉴权结果建立互信,也即所述智能驾驶域控制器需要建立所述第一车辆与所述至少一辆第二车辆之间的互信。也就是说,第一车辆如果需要获取其他车辆的行驶轨迹,需要先取得对方的安全认证,在双方通过彼此的安全认证取得互信后,第一车辆才能获知对方的行驶轨迹,以此提升车辆在道路上行驶中安全性。可选地,第一车辆可以通过如下方式与其他车辆建立互信:所述智能驾驶域控制器确定所述至少一辆第二车辆在预设范围内,所述预设定范围为以所述第一车辆为圆心的圆形区域,所述圆形区域的半径为设定值;然后,智能驾驶控制器向预设范围内的车辆发送安全认证消息,其中,该安全认证消息中包括安全认证的类型(如,基于口令的认证、数字签名(digital signature)认证)、第一车辆的标识(如车辆设备号);其他车辆根据安全认证消息进行处理和应答,再由智能驾驶域控制器根据应答消息建立与周围车辆的信任关系,进而获取周围车辆预测的行驶轨迹。另一方面,不同车辆之间互信认证的过程需要在预设时间内进行确认。例如,车辆间可以周期性确认互信状态,或者,在第一次建立互信后即维持互信链路,通过该互信链路实时监控安全认证的状态。
需要说明的是,上述步骤301-步骤303的排序并不对方案执行的先后顺序进行限定。应理解,可以先执行步骤302、步骤303然后再执行步骤301;或者执行顺序可以是步骤302、步骤301、步骤303等。
步骤304:所述第一车辆的智能域驾驶控制器根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。
在一种可选的实施方式中,所述第一车辆的智能驾驶域控制器在确定所述第一车辆的轨迹规划时,可以符合以下原则:确保不能违反交通规则,例如不能闯红灯、不能超速、 不能在应急车道行驶,不能压实线等等;确保与障碍物(如其他车辆)之间的距离需要大于预设值,以预留有效的刹车范围;确保不与障碍物(如其他车辆)在同一时刻位于同一个位置。当然,还有其他原则或者规则,本申请此处不再一一列举。
在轨迹规划过程中,当任一第二车辆为特殊车辆,例如救护车、消防车等的轨迹时,所述第一车辆的智能驾驶域控制器可以对相应的轨迹进行特殊标记,从而可以实现为特殊车辆让路。
采用上述方法,在智能车行驶过程中,第一车辆的智能驾驶域控制器可以获取自车的行驶轨迹,以及获取其他车辆根据定制化的轨迹预测模型确定的行驶轨迹,然后基于获取的定制化的行驶轨迹对第一车辆进行轨迹规划。上述方法能够获得人工驾驶模式的智能车或非智能车中每个驾驶员定制化的轨迹预测模型,并按照各自的驾驶习惯预测其行驶轨迹,相比于传统技术中采用统一规则进行轨迹预测的方法,预测结果更接近车辆的行驶轨迹。进一步地,智能驾驶域控制器可以根据上述获取预测模型获得的预测轨迹确定自车的行驶轨迹,合理规划自车行驶轨迹,降低与其他车辆碰撞的风险,提升智能车行驶安全。
基于以上实施例,以一个具体的示例,对本申请实施例提供的一种轨迹规划方法进行说明。以图2为例,假设车辆1为处于人工驾驶模式的自动驾驶车辆,车辆2为处于自动驾驶模式的自动驾驶车辆,车辆3为人工驾驶车辆,其中,这里提到的人工驾驶车辆是指包含自动驾驶车辆的设备,但是由驾驶员控制车辆的行驶。在三辆车辆的行驶过程中,车辆1、车辆2和车辆3之间先分别通过彼此的安全认证取得互信,然后,获取彼此的行车轨迹进而实现轨迹规划。具体的,下面以车辆1的轨迹规划过程为例进行说明。车辆1的智能驾驶域控制器确定车辆2和车辆3在以车辆1为圆心的,半径为设定值的圆形区域内,然后向车辆2和车辆3发送安全认证消息,所述安全认证消息中包括安全认证类型、车辆1的标识,之后在车辆2和车辆3根据车辆1发送的安全认证消息确认可以和车辆1进行通信后分别向车辆1发送安全认证应答消息,以告知车辆1互信建立成功。互信建立后,车辆1的智能驾驶域控制器获取车辆1当前位置所在的经度和维度,再分别获取车辆2和车辆3相对车辆1的相对速度和相对距离,以及道路的当前车道属性、道路半径、车辆1的速度、加速度、加速踏板开度、制动踏板开度、右前制动轮缸、左前制动轮缸、右后制动轮缸、左后制动轮缸、方向盘转角、方向盘转向角速度、方向盘转矩、档位、转向灯信号;然后,车辆1的智能驾驶域控制器从云服务器获取符合当前即使车辆1的驾驶员的驾驶习惯的轨迹预测模型,并将上述数据输入获取的该轨迹预测模型得到预测的车辆1的轨迹点,进而得到车辆1的人工驾驶轨迹,并将预测的人工驾驶轨迹发送给车辆2和车辆3。车辆1的智能驾驶域控制器获取车辆2的自动驾驶轨迹,以及获取基于驾驶车辆3的驾驶员的驾驶习惯的轨迹预测模型得到车辆3人工驾驶轨迹。这样车辆1就可以根据自身预测的轨迹以及车辆2和车辆3预设时段内的轨迹进行自身的轨迹规划。具体地,车辆1获取的自身的轨迹在预设时段内是保持当前车道直行,车辆1获取的车辆3的预设时段的行驶轨迹是保持在车辆1的相邻右侧车道保持直行,车辆1获取的车辆2的预设时段的行驶轨迹是在与车辆3相同车道并在车辆3后边先直行后在车辆1所在的车道超越车辆3行驶。基于上述预测的行驶轨迹,车辆1可以在给车辆2预留变道距离的前提下,继续保持直行,例如们可以在直行过程中减速,直至车辆2成功变道后再恢复适当提高速度继续直行,以避免与车辆2发生碰撞;或者,车辆1在确定与车辆3的距离足够大后,更新预测的轨迹,例如,可以在车辆2变道的同时或者在车辆2变道后从直行变为变道行驶,变到车辆3所 在的车道后,在车辆3后边保持直线行驶,且与车辆3保持设定距离,以避免与车辆2和车辆3发生碰撞。
通过上述方法,车辆可以结合预设时段内其他车辆的轨迹以及自身的轨迹进行轨迹规划,其中每辆车辆的轨迹都与车辆的当前驾驶状态匹配,有驾驶员驾驶的车辆更是基于各自的驾驶习惯得到的行驶轨迹,相对于传统技术采用统一规则进行轨迹预测的方法,预测结果更接近车辆的行驶轨迹,是车辆用来进行轨迹规划的预测轨迹更接近车辆行驶轨迹,从而可以使轨迹规划比较准确,可以确保自车不与其他任一车辆在同一时刻出现在同一位置,避免发生碰撞,从而可以提高行驶安全性。
上文中结合图1至图3,详细描述了根据本申请所提供的车辆轨迹规划的方法,下面将结合图4至图6,描述根据本申请所提供的轨迹规划的装置、智能驾驶域控制器和智能车。
图4为本申请提供的一种车辆轨迹规划的装置的结构示意图,如图所示,所述车辆轨迹规划的装置400可以包括获取单元401和处理单元402,具体的:
所述获取单元401用于获取所述第一车辆的第一轨迹;以及基于第一通信技术获取至少一辆第二车辆的第二轨迹;
所述处理单元402用于根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。
可选地,所述获取单元401在获取所述第一车辆的第一轨迹时,具体用于:确定所述第一车辆当前的驾驶模式,所述驾驶模式包括自动驾驶模式和人工驾驶模式;根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹。
可选地,所述获取单元401在根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹时,具体用于:当确定为自动驾驶模式时,获取所述第一车辆的自动驾驶轨迹,将所述自动驾驶轨迹作为所述第一轨迹。
可选地,所述获取单元401在根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹时,具体用于:当确定为人工驾驶模式时,预测所述第一车辆的人工驾驶轨迹,将预测得到的所述人工驾驶轨迹作为所述第一轨迹。
具体的,所述获取单元401在预测所述第一车辆的人工驾驶轨迹时,具体用于:获取第一参数集合,所述第一参数集合包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态,所述第一车辆的行驶状态用于指示当前驾驶所述第一车辆的用户的驾驶习惯;获取所述第一车辆对应的轨迹预测模型,所述轨迹预测模型为根据当前驾驶所述第一车辆的用户的驾驶习惯的历史数据训练获得;根据所述第一参数集合和所述轨迹预测模型预测所述第一车辆的轨迹点;根据所述第一车辆的轨迹点确定所述第一车辆的人工驾驶轨迹。
示例性的,所述第一车辆的位置包括标识所述第一车辆所在位置的经度和纬度;所述第一车辆周围障碍物包括一个或多个障碍物,任一个障碍物的行驶数据包括所述任一个障碍物相对所述第一车辆的相对速度和相对距离;所述第一车辆的行驶状态包括所述第一车辆所在的道路的当前车道属性、道路半径、所述第一车辆的速度、加速度、加速踏板开度、制动踏板开度、右前制动轮缸、左前制动轮缸、右后制动轮缸、左后制动轮缸、方向盘转角、方向盘转向角速度、方向盘转矩、档位、转向灯信号。
可选的,所述任一个障碍物的行驶数据还包括所述任一个障碍物的相对速度的置信度。
可选地,所述第一车辆的轨迹点包括所述第一车辆预测行驶轨迹中包括的预测经度和预测纬度。
可选的,所述第一车辆的轨迹点还包括所述预测经度的置信度和所述预测纬度的置信度。
可选地,所述车辆轨迹规划的装置400还包括发送单元403,用于向云服务器发送所述第一参数集合和所述第一车辆的轨迹点,以使所述云服务器根据所述第一参数集合和所述第一车辆的轨迹点校正所述轨迹预测模型;所述获取单元401还用于接收所述云服务器发送的校正后的轨迹预测模型,并利用所述校正后的轨迹预测模型和第二参数集合预测所述第一车辆的轨迹点,所述第二参数集为当前时刻收集的包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态的数据。
可选地,所述车辆轨迹规划的装置400还包括发送单元403,用于向所述至少一辆第二车辆发送所述第一轨迹。
可选地,所述处理单元402还用于:确定所述至少一辆第二车辆在设定范围内,所述设定范围为以所述第一车辆为圆心的圆形区域,所述圆形区域的半径为设定值;或者,确定与所述至少一辆第二车辆已通过安全认证。
可选地,所述第一通信技术为车用无线通信技术V2X。
应理解的是,本申请实施例的车辆轨迹规划的装置400可以通过专用集成电路(application-specific integrated circuit,ASIC)实现,或可编程逻辑器件(programmable logic device,PLD)实现,上述PLD可以是复杂程序逻辑器件(complex programmable logical device,CPLD),现场可编程门阵列(field-programmable gate array,FPGA),通用阵列逻辑(generic array logic,GAL)或其任意组合。也可以通过软件实现图3所示的轨迹规划的方法时,车辆轨迹规划的装置400及其各个模块也可以为软件模块。
根据本申请实施例的车辆轨迹规划的装置400可对应于执行本申请实施例中描述的方法,并且车辆轨迹规划的装置400中的各个单元的上述和其它操作和/或功能分别为了实现图3中的各个方法的相应流程,为了简洁,在此不再赘述。
通过上述车辆轨迹规划的装置400,在智能车行驶过程中,可以获取自车的行驶轨迹,以及获取其他车辆根据定制化的轨迹预测模型确定的行驶轨迹,然后基于获取的定制化的行驶轨迹对自车进行轨迹规划。通过上述装置,能够获得人工驾驶模式的智能车或非智能车中每个驾驶员定制化的轨迹预测模型,并按照各自的驾驶习惯预测其行驶轨迹,相比于传统技术中采用统一规则进行轨迹预测,预测结果更接近车辆的行驶轨迹。进一步地,上述装置可以根据上述获取预测模型获得的预测轨迹确定自车的行驶轨迹,合理规划自车行驶轨迹,降低与其他车辆碰撞的风险,提升智能车行驶安全。
在一种可选的实施方式中,图4中的所述获取单元401和处理单元402可以通过更细化的一个或多个功能模块或单元共同来实现其功能,可选地,可以通过图5示出的各个单元来实现。例如,所述获取单元401可以通过如图5示出的装置中的毫米波雷达数据处理单元501、激光雷达数据处理单元502、相机图像数据处理单元503、车身数据处理单元504、定位数据处理单元505、数据记录单元506和轨迹预测单元507实现;所述发送单元403可以通过图5示出的数据收发单元508和人机接口(human machine interface,HMI)信号发送单元509。
其中,毫米波雷达数据处理单元501:用于接收毫米波雷达(例如图1所示的毫米波 雷达101)发送的数据。当接收到的数据是周围障碍物的距离、速度等数据时,将坐标系转换为统一的车体坐标系,并打时间戳后发送给数据记录单元506和轨迹预测单元507;当接收到的数据是到达障碍物的光束传输时间和光束的速度时,先计算得到周围障碍物的距离、速度等数据,并发送给数据记录单元506和轨迹预测单元507。
激光雷达数据处理单元502:用于接收激光雷达(例如图1所示的激光雷达102)发送的数据。当接收到的数据是周围障碍物的距离、速度等数据时,将坐标系转换为统一的车体坐标系,并打时间戳后发送给数据记录单元506和轨迹预测单元507;当接收到的数据是从障碍物反射回来的信号和发射信号时,先计算得到周围障碍物的距离、速度等数据,并发送给数据记录单元506和轨迹预测单元507。
相机图像处理单元503:接收相机(例如图1所示的相机103)传输的数据。当接收到的是智能摄像头发送的周围障碍物的速度和距离等数据时,将坐标系转换为统一的车体坐标系,并打时间戳后发送给数据记录单元506和轨迹预测单元507;当接收到的是图像或视频时,先分析图像或视频得周围障碍物的速度和距离等数据,并发送给数据记录单元506和轨迹预测单元507。
车身数据处理单元504:获取车辆(自车)的数据,例如获取图1所示的车辆其他控制器107发送的数据,并将获取的数据发送至数据记录单元506和轨迹预测单元507。
定位数据处理单元505:接收定位数据(例如从图1所示的高精度定位设备获取),发送至数据记录单元506和轨迹预测单元507。
数据记录单元506:将收到的数据存储到存储器(例如只读存储器(read-only memory,ROM))中,定期发送给数据收发单元508。
数据收发单元508:定期将收到的数据记录单元506发送的数据发送至云端(例如图1所示的云端100),定期接收云端模型参数,并发送给轨迹预测单元507,实时的将获取到的预测轨迹发送到周围车辆。
轨迹预测单元507:根据云端回传的参数,通过模型预测本车轨迹,并将轨迹发送给HMI信号发送单元509和数据收发单元508。
HMI信号发送单元509:将收到的轨迹发送给显示单元,以便驾驶员获知智能车的行驶轨迹。可选地,驾驶员也可以通过显示单元更改行驶轨迹。
通过上述装置,能够获得人工驾驶模式的智能车或非智能车中每个驾驶员定制化的轨迹预测模型,并按照各自的驾驶习惯预测其行驶轨迹,相比于传统技术中采用统一规则进行轨迹预测,预测结果更接近车辆的行驶轨迹。进一步地,上述装置可以根据上述获取预测模型获得的预测轨迹确定自车的行驶轨迹,合理规划自车行驶轨迹,降低与其他车辆碰撞的风险,提升智能车行驶安全。
图6为本申请实施例提供的一种智能驾驶域控制器的结构示意图,所述智能驾驶域控制器应用于如图1所示的系统,用于实现如图3所示的车辆轨迹规划的方法。参阅图6所示,所述智能驾驶域控制器600可以包括:处理器601、存储器602和总线603。其中,处理器601和存储器602通过总线603进行通信,也可以通过无线传输等其他手段实现通信。该存储器602用于存储指令,该处理器601用于执行该存储器602存储的指令。该存储器602存储程序代码,且处理器601可以调用存储器602中存储的程序代码执行以下操作:
获取所述第一车辆的第一轨迹,以及第一通信技术获取至少一辆第二车辆的第二轨迹; 并根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。
可选地,图6所示的智能驾驶域控制器600还包括内存和通信接口(图6中未示出),其中,内存可以与处理器物理集成在一起,或在处理器内或以独立单元形式存在。计算机程序可以存储至内存或存储器。可选地,存储至存储器的计算机程序代码(例如,内核,要调试的程序等)被复制到内存,进而由处理器执行。
应理解,在本申请实施例中,该处理器601可以是中央处理器(central processing unit,CPU),该处理器601还可以是其他通用处理器、数字信号处理器(digital signal processing,DSPDSP)、专用集成电路(application-specific integrated circuit,ASIC)、可编程逻辑器件(programmable logic device,PLD);上述PLD可以是复杂可编程逻辑器件(complex programmable logic device,CPLD),现场可编程门阵列(field-programmable gate array,FPGA)、通用阵列逻辑(generic array logic,GAL)或其任意组合;或者该处理器601可以是其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。
该存储器602可以包括只读存储器和随机存取存储器,并向处理器601提供指令、程序和数据等。例如,程序可以包括程序代码,该程序代码包括计算机操作指令。存储器602还可以包括非易失性随机存取存储器。例如,存储器602还可以存储设备类型的信息。
该存储器602可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM,DR RAM)。
该总线603除包括数据总线之外,还可以包括地址总线、电源总线、控制总线和状态信号总线等。该总线603可以是外设部件互连标准(peripheral component interconnect,PCI)总线或扩展工业标准结构(extended Industry standard architecture,EISA)总线等,也可以是控制区域网络(controller area network,CAN),还可以是车载以太(Ethernet),或者其他内部总线实现图6所示的各个器件/设备的连接。但是为了清楚说明起见,在图6中将各种总线都标为总线603。为便于表示,图6中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。
应理解,根据本申请实施例的智能驾驶域控制器600可对应于本申请实施例中的车辆轨迹规划的装置400,并可以对应于执行图3所示方法中的智能驾驶域控制器作为主体的操作步骤,并且智能驾驶域控制器600中的各个模块的上述和其它操作和/或功能分别为了实现图3中的各个方法的相应流程,为了简洁,在此不再赘述。
通过上述智能驾驶域控制器600,在智能车行驶过程中,可以获取自车的行驶轨迹,以及获取其他车辆根据定制化的轨迹预测模型确定的行驶轨迹,然后基于获取的定制化的 行驶轨迹对自车进行轨迹规划。通过上述智能驾驶域控制器600,能够获得人工驾驶模式的智能车或非智能车中每个驾驶员定制化的轨迹预测模型,并按照各自的驾驶习惯预测其行驶轨迹,相比于传统技术中采用统一规则进行轨迹预测,预测结果更接近车辆的行驶轨迹。进一步地,上述智能驾驶域控制器600可以根据上述获取预测模型获得的预测轨迹确定自车的行驶轨迹,合理规划自车行驶轨迹,降低与其他车辆碰撞的风险,提升智能车行驶安全。
本申请还提供了一种智能车,所述智能车可以包含上述涉及的智能驾驶域控制器或者车辆轨迹规划的装置。在一种示例中,所述智能车可以为本申请涉及的第一车辆。
本申请还提供一种如图1所示的轨迹预测系统,该轨迹预测系统包括第一车辆、至少一个第二车辆和云端,上述各个部件或设备分别用于执行上述图3所示方法中相应执行主体的操作步骤,为了简洁,在此不再赘述。
上述实施例,可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时,上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载或执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质。半导体介质可以是固态硬盘(solid state drive,SSD)。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本申请的技术方案的目的。
以上所述,仅为本申请的具体实施方式。熟悉本技术领域的技术人员根据本申请提供的具体实施方式,可想到变化或替换,都应涵盖在本申请的保护范围之内。
Claims (13)
- 一种车辆轨迹规划的方法,其特征在于,所述方法应用于第一车辆的智能驾驶域控制器,所述第一车辆为智能车,所述方法包括:所述智能驾驶域控制器获取所述第一车辆的第一轨迹;所述智能驾驶域控制器基于第一通信技术获取至少一辆第二车辆的第二轨迹;所述智能驾驶域控制器根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。
- 如权利要求1所述的方法,其特征在于,所述智能驾驶域控制器获取所述第一车辆的第一轨迹,包括:所述智能驾驶域控制器确定所述第一车辆当前的驾驶模式,所述驾驶模式包括自动驾驶模式和人工驾驶模式;所述智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹。
- 如权利要求1或2所述的方法,其特征在于,所述智能驾驶域控制器根据所述第一车辆的驾驶模式获取所述第一车辆的第一轨迹,包括:当所述智能驾驶域控制器确定为人工驾驶模式时,所述智能驾驶域控制器预测所述第一车辆的人工驾驶轨迹,将预测得到的所述人工驾驶轨迹作为所述第一轨迹。
- 如权利要求1至3中任一所述的方法,其特征在于,所述智能驾驶域控制器预测所述第一车辆的人工驾驶轨迹,包括:所述智能驾驶域控制器获取第一参数集合,所述第一参数集合包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态,所述第一车辆的行驶状态用于指示当前驾驶所述第一车辆的用户的驾驶习惯;所述智能驾驶域控制器获取所述第一车辆对应的轨迹预测模型,所述轨迹预测模型为根据当前驾驶所述第一车辆的用户的驾驶习惯的历史数据训练获得;所述智能驾驶域控制器根据所述第一参数集合和所述轨迹预测模型预测所述第一车辆的轨迹点;所述智能驾驶域控制器根据所述第一车辆的轨迹点确定所述第一车辆的人工驾驶轨迹。
- 如权利要求1至4中任一所述的方法,其特征在于,所述第一车辆的位置包括标识所述第一车辆所在位置的经度和纬度;所述第一车辆周围障碍物包括一个或多个障碍物,任一个障碍物的行驶数据包括所述任一个障碍物相对所述第一车辆的相对速度和相对距离;所述第一车辆的行驶状态包括所述第一车辆所在的道路的当前车道属性、道路半径、所述第一车辆的速度、加速度、加速踏板开度、制动踏板开度、右前制动轮缸、左前制动轮缸、右后制动轮缸、左后制动轮缸、方向盘转角、方向盘转向角速度、方向盘转矩、档位、转向灯信号。
- 如权利要求1至5中任一项所述的方法,其特征在于,所述第一车辆的轨迹点包括所述第一车辆预测行驶轨迹中包括的预测经度和预测纬度。
- 如权利要求1至6中任一项所述的方法,其特征在于,所述方法还包括:所述智能驾驶域控制器向云服务器发送所述第一参数集合和所述第一车辆的轨迹点, 以使所述云服务器根据所述第一参数集合和所述第一车辆的轨迹点校正所述轨迹预测模型;所述智能域控制器接收所述云服务器发送的校正后的轨迹预测模型;所述智能驾驶域控制器利用所述校正后的轨迹预测模型和第二参数集合预测所述第一车辆的轨迹点,所述第二参数集为当前时刻收集的包括所述第一车辆的位置、所述第一车辆周围障碍物相对于所述第一车辆的行驶数据和所述第一车辆的行驶状态的数据。
- 如权利要求1至7中任一项所述的方法,其特征在于,所述方法还包括:所述智能驾驶域控制器向所述至少一辆第二车辆发送所述第一轨迹。
- 如权利要求1至8中任一项所述的方法,其特征在于,所述方法还包括:所述智能驾驶域控制器确定所述至少一辆第二车辆在设定范围内,所述设定范围为以所述第一车辆为圆心的圆形区域,所述圆形区域的半径为设定值;或者所述智能驾驶域控制器确定与所述至少一辆第二车辆已通过安全认证。
- 如权利要求1至9中任一项所述的方法,其特征在于,所述方法还包括:所述智能驾驶域控制器按照如下规则中至少一种规则确定所述第一车辆的行驶轨迹:规则一:不违反交通规则;规则二:与障碍物(如其他车辆)之间的距离需要大于预设值;规则三:不与障碍物(如其他车辆)在同一时刻位于同一个位置。
- 一种车辆轨迹规划的装置,其特征在于,包括获取单元和处理单元,其中:所述获取单元,用于获取所述第一车辆的第一轨迹;以及基于第一通信技术获取至少一辆第二车辆的第二轨迹;所述处理单元,用于根据所述第一轨迹和所述至少一辆第二车辆的第二轨迹确定所述第一车辆的轨迹规划。
- 一种智能驾驶域控制器,其特征在于,包括处理器和存储器,所述存储中存储计算机程序指令,所述智能驾驶域控制器运行时,所述处理器执行所述存储其中存储的所述计算机程序指令以实现上述权利要求1至10中任一所述的方法的操作步骤。
- 一种智能车,其特征在于,所述智能车包括智能驾驶域控制器,所述智能驾驶域控制器用于执行权利要求12所述的智能驾驶域控制器的功能。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP20906290.0A EP4075227B1 (en) | 2019-12-24 | 2020-11-27 | Method and device for vehicle path planning, associated controller and vehicle |
US17/848,216 US20220324481A1 (en) | 2019-12-24 | 2022-06-23 | Method and apparatus for planning vehicle trajectory, intelligent driving domain controller, and intelligent vehicle |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911348578.5 | 2019-12-24 | ||
CN201911348578.5A CN111123933B (zh) | 2019-12-24 | 2019-12-24 | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/848,216 Continuation US20220324481A1 (en) | 2019-12-24 | 2022-06-23 | Method and apparatus for planning vehicle trajectory, intelligent driving domain controller, and intelligent vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021129309A1 true WO2021129309A1 (zh) | 2021-07-01 |
Family
ID=70501923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/132412 WO2021129309A1 (zh) | 2019-12-24 | 2020-11-27 | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20220324481A1 (zh) |
EP (1) | EP4075227B1 (zh) |
CN (1) | CN111123933B (zh) |
WO (1) | WO2021129309A1 (zh) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114291116A (zh) * | 2022-01-24 | 2022-04-08 | 广州小鹏自动驾驶科技有限公司 | 周围车辆轨迹预测方法、装置、车辆及存储介质 |
CN115042823A (zh) * | 2022-07-29 | 2022-09-13 | 浙江吉利控股集团有限公司 | 一种代客泊车方法、装置、电子设备及存储介质 |
WO2024047626A1 (en) * | 2022-09-01 | 2024-03-07 | Imagry Israel Ltd. | Alternative driving models for autonomous vehicles |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111123933B (zh) * | 2019-12-24 | 2021-10-01 | 华为技术有限公司 | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 |
CN113741384B (zh) * | 2020-05-29 | 2023-12-29 | 华为技术有限公司 | 检测自动驾驶系统的方法和装置 |
CN111766822A (zh) * | 2020-07-22 | 2020-10-13 | 天津优控智行科技有限公司 | 一种无人驾驶配送车辆远程调试方法 |
CN112306059B (zh) * | 2020-10-15 | 2024-02-27 | 北京三快在线科技有限公司 | 一种控制模型的训练方法、控制方法以及装置 |
CN112269385B (zh) * | 2020-10-23 | 2021-09-07 | 北京理工大学 | 云端无人车动力学控制系统和方法 |
CN114440908B (zh) * | 2020-10-31 | 2023-07-28 | 华为技术有限公司 | 一种规划车辆驾驶路径的方法、装置、智能车以及存储介质 |
JP2022082359A (ja) * | 2020-11-20 | 2022-06-01 | 国立大学法人東海国立大学機構 | 走行制御管理システム、走行制御管理方法、および走行制御管理プログラム |
CN112550315A (zh) * | 2020-12-21 | 2021-03-26 | 北京百度网讯科技有限公司 | 车辆轨迹规划方法、装置、电子设备及存储介质 |
CN113071520B (zh) * | 2021-04-16 | 2024-01-16 | 阿波罗智联(北京)科技有限公司 | 车辆行驶控制方法及装置 |
CN113479219B (zh) * | 2021-09-06 | 2021-11-26 | 智己汽车科技有限公司 | 一种行车轨迹规划方法、装置、计算机设备和介质 |
CN115218902B (zh) * | 2022-04-02 | 2024-02-02 | 广州汽车集团股份有限公司 | 一种轨迹规划方法、装置、设备及存储介质 |
CN114802302A (zh) * | 2022-04-25 | 2022-07-29 | 苏州轻棹科技有限公司 | 一种基于多目标预测轨迹进行轨迹规划的处理方法 |
WO2024020833A1 (zh) * | 2022-07-27 | 2024-02-01 | 华为技术有限公司 | 一种定位系统、方法 |
US20240190481A1 (en) * | 2022-12-08 | 2024-06-13 | Honda Motor Co., Ltd. | Adaptive trust calibration |
CN116339284A (zh) * | 2023-03-29 | 2023-06-27 | 安徽海博智能科技有限责任公司 | 一种无人驾驶矿卡远程点火和熄火控制系统及方法 |
CN116500896B (zh) * | 2023-04-28 | 2024-03-15 | 重庆大学 | 智能网联汽车域控制器多虚拟cpu任务智能实时调度模型和方法 |
CN116743937B (zh) * | 2023-08-14 | 2023-10-27 | 禾昆科技(北京)有限公司 | 域控制器和车辆行驶控制方法 |
CN116985766B (zh) * | 2023-09-27 | 2024-01-30 | 深圳市昊岳科技有限公司 | 一种基于域控制器的碰撞缓解控制系统及方法 |
CN118529082A (zh) * | 2024-06-05 | 2024-08-23 | 南京航空航天大学 | 一种基于非完全信息博弈的人机共驾驾驶权限分配方法 |
CN118587894B (zh) * | 2024-08-05 | 2024-10-15 | 浙江数智交院科技股份有限公司 | 一种预判紧急停车带内车辆驶出和预警的方法 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104590274A (zh) * | 2014-11-26 | 2015-05-06 | 浙江吉利汽车研究院有限公司 | 一种驾驶行为自适应系统及驾驶行为自适应方法 |
US20150338852A1 (en) * | 2015-08-12 | 2015-11-26 | Madhusoodhan Ramanujam | Sharing Autonomous Vehicles |
CN107139917A (zh) * | 2017-04-27 | 2017-09-08 | 江苏大学 | 一种基于混杂理论的无人驾驶汽车横向控制系统和方法 |
US10054455B2 (en) * | 2015-07-07 | 2018-08-21 | Honda Motor Co., Ltd. | Vehicle controller, vehicle control method, and vehicle control program |
CN110146100A (zh) * | 2018-02-13 | 2019-08-20 | 华为技术有限公司 | 轨迹预测方法、装置及存储介质 |
CN111123933A (zh) * | 2019-12-24 | 2020-05-08 | 华为技术有限公司 | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9248834B1 (en) * | 2014-10-02 | 2016-02-02 | Google Inc. | Predicting trajectories of objects based on contextual information |
US9934688B2 (en) * | 2015-07-31 | 2018-04-03 | Ford Global Technologies, Llc | Vehicle trajectory determination |
JP6785859B2 (ja) * | 2015-11-30 | 2020-11-18 | 華為技術有限公司Huawei Technologies Co.,Ltd. | 自動運転ナビゲーション方法、装置、およびシステム、車載端末、ならびにサーバ |
US10796204B2 (en) * | 2017-02-27 | 2020-10-06 | Huawei Technologies Co., Ltd. | Planning system and method for controlling operation of an autonomous vehicle to navigate a planned path |
CN108657176A (zh) * | 2017-04-01 | 2018-10-16 | 华为技术有限公司 | 车辆控制方法、装置及相关计算机程序产品 |
CN108932462B (zh) * | 2017-05-27 | 2021-07-16 | 华为技术有限公司 | 驾驶意图确定方法及装置 |
CN109389847B (zh) * | 2017-08-14 | 2021-05-25 | 上海汽车集团股份有限公司 | 一种道路拥堵信息的处理方法和装置 |
KR101989102B1 (ko) * | 2017-09-13 | 2019-06-13 | 엘지전자 주식회사 | 차량용 운전 보조 장치 및 그 제어 방법 |
CN108022450B (zh) * | 2017-10-31 | 2020-07-21 | 华为技术有限公司 | 一种基于蜂窝网络的辅助驾驶方法及交通控制单元 |
CN109945880B (zh) * | 2017-12-20 | 2022-11-04 | 华为技术有限公司 | 路径规划方法、相关设备及可读存储介质 |
CN108407717A (zh) * | 2018-03-14 | 2018-08-17 | 杭州分数科技有限公司 | 车辆预警方法、系统以及电子设备 |
JP7194755B2 (ja) * | 2018-05-31 | 2022-12-22 | ニッサン ノース アメリカ,インク | 軌道計画 |
CN109910880B (zh) * | 2019-03-07 | 2021-06-29 | 百度在线网络技术(北京)有限公司 | 车辆行为规划的方法、装置、存储介质和终端设备 |
CN109885058B (zh) * | 2019-03-12 | 2022-05-20 | 杭州飞步科技有限公司 | 行车轨迹规划方法、装置、电子设备及存储介质 |
CN110287529B (zh) * | 2019-05-23 | 2023-01-31 | 杭州飞步科技有限公司 | 测试方法、装置、设备以及存储介质 |
CN110379193B (zh) * | 2019-07-08 | 2021-07-20 | 华为技术有限公司 | 自动驾驶车辆的行为规划方法及行为规划装置 |
-
2019
- 2019-12-24 CN CN201911348578.5A patent/CN111123933B/zh active Active
-
2020
- 2020-11-27 WO PCT/CN2020/132412 patent/WO2021129309A1/zh unknown
- 2020-11-27 EP EP20906290.0A patent/EP4075227B1/en active Active
-
2022
- 2022-06-23 US US17/848,216 patent/US20220324481A1/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104590274A (zh) * | 2014-11-26 | 2015-05-06 | 浙江吉利汽车研究院有限公司 | 一种驾驶行为自适应系统及驾驶行为自适应方法 |
US10054455B2 (en) * | 2015-07-07 | 2018-08-21 | Honda Motor Co., Ltd. | Vehicle controller, vehicle control method, and vehicle control program |
US20150338852A1 (en) * | 2015-08-12 | 2015-11-26 | Madhusoodhan Ramanujam | Sharing Autonomous Vehicles |
CN107139917A (zh) * | 2017-04-27 | 2017-09-08 | 江苏大学 | 一种基于混杂理论的无人驾驶汽车横向控制系统和方法 |
CN110146100A (zh) * | 2018-02-13 | 2019-08-20 | 华为技术有限公司 | 轨迹预测方法、装置及存储介质 |
CN111123933A (zh) * | 2019-12-24 | 2020-05-08 | 华为技术有限公司 | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4075227A4 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114291116A (zh) * | 2022-01-24 | 2022-04-08 | 广州小鹏自动驾驶科技有限公司 | 周围车辆轨迹预测方法、装置、车辆及存储介质 |
CN114291116B (zh) * | 2022-01-24 | 2023-05-16 | 广州小鹏自动驾驶科技有限公司 | 周围车辆轨迹预测方法、装置、车辆及存储介质 |
CN115042823A (zh) * | 2022-07-29 | 2022-09-13 | 浙江吉利控股集团有限公司 | 一种代客泊车方法、装置、电子设备及存储介质 |
WO2024047626A1 (en) * | 2022-09-01 | 2024-03-07 | Imagry Israel Ltd. | Alternative driving models for autonomous vehicles |
Also Published As
Publication number | Publication date |
---|---|
US20220324481A1 (en) | 2022-10-13 |
CN111123933B (zh) | 2021-10-01 |
EP4075227A1 (en) | 2022-10-19 |
CN111123933A (zh) | 2020-05-08 |
EP4075227B1 (en) | 2024-07-10 |
EP4075227A4 (en) | 2023-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021129309A1 (zh) | 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车 | |
EP3300047A1 (en) | Dynamic traffic guide based on v2v sensor sharing method | |
WO2021133743A1 (en) | Systems and methods for semantic map-based adaptive auto-exposure | |
US20210191394A1 (en) | Systems and methods for presenting curated autonomy-system information of a vehicle | |
CN113613980A (zh) | 控制自我和社会对象的安全性的方法和系统 | |
CN112512887B (zh) | 一种行驶决策选择方法以及装置 | |
CN111833597A (zh) | 具有规划控制的交通情形中的自主决策 | |
GB2598411A (en) | Simulation of autonomous vehicle to improve safety and reliability of autonomous vehicle | |
Mo et al. | Simulation and analysis on overtaking safety assistance system based on vehicle-to-vehicle communication | |
US20220289198A1 (en) | Automated emergency braking system | |
EP3896639A1 (en) | Methods and systems for managing an automated driving system of a vehicle | |
US11691634B1 (en) | On-vehicle driving behavior modelling | |
CN114787010A (zh) | 驾驶安全性系统 | |
JP2022526666A (ja) | 車両の挙動を予測するシステム | |
US11433923B2 (en) | Systems and methods for long-term prediction of lane change maneuver | |
WO2023213200A1 (zh) | 一种会车方法及相关装置 | |
US20230399008A1 (en) | Multistatic radar point cloud formation using a sensor waveform encoding schema | |
US20230192077A1 (en) | Adjustment of object trajectory uncertainty by an autonomous vehicle | |
US20230256994A1 (en) | Assessing relative autonomous vehicle performance via evaluation of other road users | |
WO2021229671A1 (ja) | 走行支援装置および走行支援方法 | |
US11564116B2 (en) | Asynchronous observation matching for object localization in connected vehicles | |
WO2020241273A1 (ja) | 車両用通信システム、車載機、制御方法及びコンピュータプログラム | |
WO2024225024A1 (ja) | 情報処理装置、情報処理方法、及び、プログラム | |
WO2022202001A1 (ja) | 処理方法、処理システム、処理プログラム | |
US20230195830A1 (en) | Calibration metrics for measuring trajectory prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20906290 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2020906290 Country of ref document: EP Effective date: 20220711 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |