CN114644016A - Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium - Google Patents
Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium Download PDFInfo
- Publication number
- CN114644016A CN114644016A CN202210393556.6A CN202210393556A CN114644016A CN 114644016 A CN114644016 A CN 114644016A CN 202210393556 A CN202210393556 A CN 202210393556A CN 114644016 A CN114644016 A CN 114644016A
- Authority
- CN
- China
- Prior art keywords
- decision
- target vehicle
- transverse
- current
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
- B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
-
- 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
- B60W40/10—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 vehicle motion
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a vehicle automatic driving decision-making method, a device, a vehicle-mounted terminal and a storage medium, wherein current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs are obtained; when the distance between the current position information of the target vehicle and the target intersection is larger than or equal to a preset distance threshold, acquiring a road transverse decision strategy, and acquiring a first transverse decision result of the target vehicle according to the road transverse decision strategy; otherwise, acquiring an intersection transverse decision strategy, and acquiring a second transverse decision result of the target vehicle according to the intersection transverse decision strategy; and determining the running track of the target vehicle according to the first transverse decision result and the second transverse decision result. According to the method and the device, different decision methods are adopted under the road working condition and the intersection working condition, so that the problem that an automatic driving decision model is complex is solved, the complexity of the decision model under the road working condition is reduced, and the decision efficiency and accuracy are improved.
Description
Technical Field
The present application relates to the field of vehicle automatic driving technologies, and in particular, to a vehicle automatic driving decision method, an apparatus, a vehicle-mounted terminal, and a storage medium.
Background
The automatic driving vehicle is an intelligent vehicle which senses road environment through a vehicle-mounted sensing system, automatically plans a driving route and controls the vehicle to reach a preset destination, and the automatic driving system is generally divided into a map positioning part, a sensing prediction part, a path navigation part, a decision planning part, a vehicle control part and the like, wherein the decision planning module can also comprise a transverse decision and a longitudinal decision.
The conventional vehicle decision module generally extracts various factors affecting the driving behavior of the vehicle, such as the type of a road line, the speed of surrounding obstacles, the distance between the vehicle and the vehicle, traffic signs, predicted tracks of the obstacles and the like, sets quantitative indexes of the related factors, and determines the condition of decision state transition based on the quantitative indexes. However, the decision-making method has high difficulty, needs to consume a large amount of computing resources, and has low algorithm performance, thereby causing low decision-making efficiency.
Disclosure of Invention
In order to solve the technical problems of high difficulty, high consumed computing resources and low algorithm performance and decision efficiency of the existing decision method, the invention provides a vehicle automatic driving decision method, a vehicle-mounted terminal and a storage medium.
In one aspect, an embodiment of the present application provides a vehicle automatic driving decision method, including:
acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, wherein the driving scene comprises a road driving scene and an intersection driving scene;
when the driving scene of the target vehicle is the road driving scene, processing the current driving condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle;
when the driving scene of the target vehicle is the intersection driving scene, processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle;
and determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
Further, the determining the driving scene of the target vehicle based on the current position information of the target vehicle and the current road environment information comprises:
the current road environment information comprises information of a front target intersection and a rear target intersection of the target vehicle;
and under the condition that the distance between the current position information of the target vehicle and the front target intersection is greater than or equal to a first distance threshold value or the distance between the current position information of the target vehicle and the rear target intersection is greater than or equal to a second distance threshold value, determining that the driving scene of the target vehicle is the road driving scene.
Further, the air conditioner is provided with a fan,
the determining the driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle comprises:
the current road environment information comprises information of a front target intersection and a rear target intersection of the target vehicle;
and under the condition that the distance between the current position information of the target vehicle and the front target intersection is smaller than a first distance threshold value or the distance between the target position information and the rear target intersection is smaller than a second distance threshold value, determining that the driving scene of the target vehicle is the intersection driving scene.
Further, the obtaining a road transverse decision-making strategy and processing the current running condition information and the current road environment information of the target vehicle according to the road transverse decision-making strategy to obtain a first transverse decision-making result of the target vehicle includes:
receiving a road transverse decision model sent by a server;
taking the received road transverse decision model as the road transverse decision strategy;
processing the current running condition information and the current road environment information of the target vehicle according to the road transverse decision model to obtain the first transverse decision result of the target vehicle;
the road transverse decision model is obtained by training a preset model based on sample data of a sample vehicle, the preset model is a Markov reinforcement learning-based model, and the sample data comprises sample running condition information of the sample vehicle and sample road environment information of a road on which the sample vehicle runs.
Further, the method further comprises:
receiving an updated road transverse decision model sent by the server;
taking the updated road transverse decision model as the road transverse decision strategy;
the updated road transverse decision model is obtained by training the preset model based on updated sample data; and updating the sample data based on the current running condition information of the target vehicle and the current road environment information to obtain the updated sample data.
Further, the intersection lateral decision strategy is a finite state machine-based lateral decision strategy, and the method further comprises:
acquiring preset navigation information of a preset vehicle, preset road environment information of a road on which the preset vehicle runs, a preset initial transverse decision result and a preset target transverse decision result;
establishing a mapping relation among the preset navigation information, the preset road environment information, the preset initial transverse decision result and the preset target transverse decision result;
and taking the mapping relation as the intersection transverse decision strategy.
Further, the processing the current navigation information of the target vehicle and the current road environment information according to the intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle includes:
obtaining a current initial transverse decision result of the target vehicle;
acquiring a preset transverse decision result corresponding to the current navigation information, the current road environment information and the current initial transverse decision result according to the mapping relation;
and taking the preset transverse decision result corresponding to the current navigation information, the current road environment information and the current initial transverse decision result as the second transverse decision result.
Further, the determining the driving track of the target vehicle according to the first lateral decision result and/or the second lateral decision result includes:
taking the first lateral decision result and/or the second lateral decision result as a target lateral decision result of the target vehicle;
determining a target longitudinal decision result based on the target transverse decision result;
and determining the running track of the target vehicle according to the target transverse decision result and the target longitudinal decision result.
In another aspect, the present invention provides an automatic vehicle driving decision device, including:
the system comprises an acquisition module, a navigation module and a control module, wherein the acquisition module is used for acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
the scene determining module is used for determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, wherein the driving scene comprises a road driving scene and an intersection driving scene;
the first transverse decision module is used for processing the current running working condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle when the running scene of the target vehicle is the road running scene;
the second transverse decision module is used for processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy when the driving scene of the target vehicle is the intersection driving scene to obtain a second transverse decision result of the target vehicle;
and the track determining module is used for determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
In another aspect, a computer device is provided, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the above-mentioned method for automatic vehicle driving decision.
In another aspect, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the vehicle automatic driving decision method as described above.
In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from the computer-readable storage medium by a processor of the computer device, and the computer instructions are executed by the processor to cause the computer device to perform the method provided in the various alternative implementations of vehicle autopilot decision described above.
The vehicle automatic driving decision method, the device, the vehicle-mounted terminal and the storage medium provided by the embodiment of the application have the following technical effects:
determining a driving scene of a target vehicle based on current position information and current road environment information of the target vehicle by acquiring the current position information, current navigation information, current driving condition information and the current road environment information of a road on which the target vehicle runs, wherein the driving scene comprises a road driving scene and an intersection driving scene; when the driving scene of the target vehicle is the road driving scene, processing the current driving condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle; when the driving scene of the target vehicle is the intersection driving scene, processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle; and determining the running track of the target vehicle according to the first transverse decision result and the second transverse decision result, so that the complexity of an automatic driving decision system under a road working condition is reduced, and the decision efficiency and accuracy are improved.
Drawings
In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flowchart 1 of an automatic vehicle driving decision method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram 2 of a method for automatic vehicle driving decision making provided by an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a vehicle automatic driving decision method provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of an updated road lateral decision-making strategy according to an embodiment of the present application;
fig. 5 is a schematic flow chart of an intersection lateral decision strategy provided in an embodiment of the present application;
FIG. 6 is a schematic structural diagram of an automatic vehicle driving decision-making device according to an embodiment of the present disclosure;
fig. 7 is a block diagram of a hardware structure of a vehicle automatic driving decision vehicle-mounted terminal according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making creative efforts shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, fig. 1 is a schematic flow diagram of a vehicle automatic driving decision method according to an embodiment of the present disclosure, in which a current position information, a current navigation information, a current driving condition information, and a current road environment information of a road on which a target vehicle is driving are obtained, when a distance between the current position information of the target vehicle and a target intersection is greater than or equal to a preset distance threshold, a driving scene of the target vehicle is determined as a road driving scene, and the current driving condition information and the current road environment information of the target vehicle are processed according to a road transverse decision policy to obtain a first transverse decision result; when the distance between the current position information of the target vehicle and the target intersection is smaller than a preset distance threshold value, determining that the driving scene of the target vehicle is an intersection driving scene, and processing the current navigation information and the current road environment information of the target vehicle according to a road intersection transverse decision strategy to obtain a second transverse decision result; and determining the running track of the target vehicle according to the first transverse decision result and the second transverse decision result. The automatic vehicle driving decision method can adopt the corresponding transverse decision strategy according to the driving scene, adopt the road transverse decision strategy in the road driving scene and adopt the intersection transverse decision strategy in the intersection driving scene, thereby avoiding the overhigh complexity of the model in the road driving scene caused by adopting the intersection transverse decision strategy in the road driving scene and improving the efficiency and the accuracy of the automatic vehicle driving decision.
The specification provides the method steps as in the examples or flowcharts, but may include more or fewer steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel or multi-threaded environments) according to the embodiments or methods shown in the drawings. Specifically, as shown in fig. 1, the method may include:
s101: acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
s102: determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, wherein the driving scene comprises a road driving scene and an intersection driving scene;
s103: when the driving scene of the target vehicle is the road driving scene, processing the current driving condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle;
s104: when the driving scene of the target vehicle is the intersection driving scene, processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle;
s105: and determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
In an alternative embodiment of the present application, as shown in fig. 2, the method includes:
s201: acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
specifically, the current position information of the target vehicle may be acquired through a Global Positioning System (GPS); the current running condition information of the target vehicle comprises but is not limited to the speed, the acceleration, the course angle, the center x coordinate, the center y coordinate, the length, the width and the like of the target vehicle based on a rectangular frame, and can be obtained by a sensor arranged on an automobile; the current navigation information comprises navigation path planning information of the target vehicle and can be acquired through a vehicle-mounted navigation system; the current road environment information includes surrounding obstacles (such as vehicles, pedestrians, buildings and the like) of the target vehicle and road information (such as a travelable area, a lane line, a traffic sign, a traffic light and the like), and can be obtained by arranging a sensor (such as a camera, a laser radar, a millimeter wave radar and the like) on the target vehicle.
S202: and determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle.
In the embodiment of the application, the driving conditions of the vehicle driving on the road are divided into the road driving conditions and the intersection driving conditions, correspondingly, the driving scenes of the vehicle are defined to comprise the road driving scenes and the intersection driving scenes, different transverse decision strategies are adopted for different driving scenes, for example, a Markov decision method is adopted for the road driving scenes, and a finite state machine decision method is adopted for the intersection driving scenes constrained by strong rules, so that the advantages of the class 2 decision methods are fully utilized, and the decision is more efficient and intelligent.
In the embodiment of the present application, optionally, the specific method for determining the driving scene of the target vehicle is as follows: and judging whether the distance between the current position information of the target vehicle and the target intersection is greater than or equal to a preset distance threshold value or not.
In this embodiment, optionally, the current road environment information includes target intersection information of the target vehicle, the target intersection includes a front target intersection and a rear target intersection, the front target intersection is an intersection located in front of the target vehicle in the driving direction of the target vehicle, the rear target intersection is an intersection located behind the target vehicle in the driving direction of the target vehicle, and the preset distance threshold includes a first distance threshold and a second distance threshold.
In the embodiment of the application, the current driving scene of the target vehicle is judged by judging the distance between the target vehicle and the intersection in front of the target or the intersection behind the target, and a corresponding transverse decision strategy is adopted according to the current driving scene.
S203: when the distance between the current position information of the target vehicle and the target intersection is larger than or equal to a preset distance threshold value, determining that the driving scene of the target vehicle is a road driving scene, acquiring a road transverse decision strategy, and processing the current driving condition information and the current road environment information of the target vehicle according to the road transverse decision strategy to obtain a first transverse decision result of the target vehicle.
In the embodiment of the application, when the distance between the current position information of the target vehicle and the front target intersection is larger than or equal to the first distance threshold or the distance between the current position information of the target vehicle and the rear target intersection is larger than or equal to the second distance threshold, the target vehicle is judged to be in a road driving scene at the moment, the target vehicle acquires a road transverse decision strategy in an automatic driving process, and the current driving condition information and the current road environment information of the target vehicle are processed according to the acquired road transverse decision strategy to obtain a first transverse decision result of the target vehicle.
S204: and when the distance between the current position information of the target vehicle and the target intersection is small and rain, and a preset distance threshold value is obtained, determining the driving scene of the target vehicle as the intersection driving scene, acquiring an intersection transverse decision strategy, and processing the current navigation information and the current road environment information of the target vehicle according to the intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle.
In the embodiment of the application, when the distance between the current position information of the target vehicle and the front target intersection is smaller than the first distance threshold or the distance between the current position information of the target vehicle and the rear target intersection is smaller than the second distance threshold, it is determined that the target vehicle is in an intersection driving scene, the target vehicle acquires an intersection transverse decision strategy in an automatic driving process, and the current navigation information and the current road environment information of the target vehicle are processed according to the acquired intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle.
S205: and determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
Optionally, the method for determining the driving trajectory of the target vehicle according to the first lateral decision result and/or the second lateral decision result includes:
taking the first transverse decision result and/or the second transverse decision result as a target transverse decision result of the target vehicle; determining the opening degree of an accelerator or a brake pedal to be controlled when the vehicle keeps a safe distance from surrounding obstacles in the process of executing the target transverse decision result based on the target transverse decision result, thereby determining a target longitudinal decision result; and performing longitudinal and transverse dynamic coupling on the target vehicle according to the target transverse decision result and the target longitudinal decision result to determine the running track of the target vehicle.
Fig. 3 is a schematic flow chart of a possible vehicle automatic driving decision method according to the present application, as shown in fig. 3: the automatic vehicle driving decision system comprises five parts, namely map positioning, perception prediction, route navigation, decision planning and vehicle control, wherein the decision planning module comprises a scene scheduling module, a transverse decision module, a comprehensive decision module and a planning module, and the transverse decision module is divided into a road scene transverse decision and an intersection scene transverse decision.
The scene scheduling module monitors the current position information of a target vehicle in real time according to the map positioning module, sets a first distance threshold s1 and a second distance threshold s2, if the current position of the target vehicle is larger than a first distance threshold s1 from a target intersection in front of the target vehicle when the target vehicle runs along a road, determines that the running scene of the target vehicle is the road running scene, keeps the transverse decision of the road scene, adopts a transverse decision strategy to make a transverse decision result, otherwise, enters the transverse decision of the intersection scene, adopts a transverse decision strategy to make a transverse decision result, when the target vehicle leaves the intersection, when the current position information of the target vehicle is smaller than a second distance threshold s2 from the target intersection behind the target intersection, keeps the transverse decision of the intersection scene, and otherwise, enters the transverse decision of the road scene.
The transverse decision module sends a transverse decision result to the comprehensive decision module through a road transverse decision strategy and an intersection transverse decision strategy, the comprehensive decision module carries out longitudinal decision on the basis of the transverse decision result, the transverse decision result and the longitudinal decision result are coordinated and then sent to the planning module, finally a track is generated and issued to the outside, and automatic driving of a target vehicle is achieved.
In the embodiment of the application, the road lateral decision strategy may be a pre-trained road lateral decision model. The target vehicle receives the road transverse decision-making model sent by the cloud server, the received road transverse decision-making model is used as a road transverse decision-making strategy, and the current running condition information and the current road environment information of the target vehicle are processed according to the road transverse decision-making model to obtain a first transverse decision-making result of the target vehicle.
The method for optionally training to obtain the road transverse decision model comprises the step of training a preset Markov reinforcement learning model based on sample data of a sample vehicle, wherein the sample data comprises sample running condition information of the sample vehicle and sample road environment information of a road on which the sample vehicle runs, the sample running condition information comprises a motion state, a space state and a transverse behavior state of the sample vehicle, and the sample vehicle can be a target vehicle or other automatic driving vehicles.
The markov-based road lateral decision model can be expressed as a quadruple (S, a, P, R): where S is a state space, S ═ Sadv，S1，S2，……，Sn]TRunning condition information S of the autonomous vehicleadvIncluding the state of motion and spatial state of the autonomous vehicle itself, Sadv＝[v，a，x，y，θ，l，w]TV, a and theta are respectively the speed, the acceleration and the course angle of the automatic driving vehicle to represent the motion state of the vehicle, and x, y, l and w are respectively the central x coordinate, the central y coordinate, the length and the width of the automatic driving vehicle based on the rectangular frame to represent the space state of the vehicle. State S of other i-th obstacle vehiclei＝[t，b，v，a，x，y，θ，l，w]TWhere t, b are the vehicle type and predicted driving behavior, S, respectivelyiMay represent road environment information of a road on which the autonomous vehicle is traveling.
A is an action space, represents a first transverse decision result of the automatically driven vehicle, defines a road driving transverse driving action command as a discrete set, and respectively represents that the first transverse decision result of the vehicle is lane keeping, left lane changing, right lane changing, left avoidance and right avoidance.
P (s' | s) is a state transition probability model, describes an evolution process of the driving state of the autonomous vehicle over time, and represents a probability that the autonomous vehicle transitions from a current lateral state to a next lateral state after executing a corresponding road lateral driving action instruction:
wherein P (s '| s) represents the probability that the autonomous vehicle transitions from the current state s to the next moment state s';
Padv(s′a|saa) indicates that the autonomous vehicle is driven from the current state s if a certain action a is performedaTransition to the next state of time sa' a probability;
P(s′i|si) Indicating other vehicles by current state siTransition to the next state of time si' probabilistic autonomous vehicle State s at certain action AaCan be expressed as:
va＝v+aaτ
aa＝a+jτ
xa＝x+(v+aτ)cos(θ+Δθ)
ya＝y+(v+aτ)cos(θ+Δθ)
θa＝θ+Δθ
la＝l
wa＝w
wherein tau is a decision period, j is the average jerk in a plurality of past decision periods, and delta theta is the navigation angle increment. For other vehicle states SiSince the perception prediction period is generally not less than the decision-making plan calculation period, the predicted driving behavior and the predicted vehicle type in the driving action generation period can be considered to be unchanged, so that the state transition probability model P of other vehiclesiReference may be made to the autonomous vehicle described above.
R is a reward function based on weight, is an evaluation criterion of a vehicle road transverse decision strategy, and mainly considers 5 dimensions of safety, traffic rules, comfort, traffic efficiency and completion degree of an automatic driving vehicle in an automatic driving process:
R＝γ1fs+γ2fr+γ3fc+γ4fe+γ5ft
wherein gamma isiIs the weight coefficient of the reward function under different dimensions, and is more than or equal to 0 and less than or equal to gammai≤1；fsThe reward function for the safety factor, primarily takes into account the distance of the autonomous vehicle from other vehicles during driving,the larger the distance is, the larger the value of the reward function is; f. ofrA fixed penalty value is given for the driving behavior of the automatic driving vehicle which violates the traffic rule in the driving process according to the reward function which complies with the traffic rule, and the reward function value is reduced; f. ofcThe impact degree of the transverse acceleration and the longitudinal acceleration of the automatic driving vehicle is mainly considered, and the larger the impact degree is, the lower the reward function value is; f. ofeThe speed of the automatic driving vehicle is mainly considered, and the closer the speed of the automatic driving vehicle is to the cruising speed, the larger the reward function value is; f. oftThe reward function for completing the automatic driving task mainly considers whether the automatic driving vehicle reaches the effective range of a target point in the automatic driving process, if the automatic driving vehicle enters the effective range, a fixed reward value is given to increase the reward function value, and otherwise, a penalty value is given to decrease the reward function value.
After the running condition information and the road environment information of the automatic driving vehicle are input into the road transverse decision-making model, after the model automatic driving vehicle executes different road transverse driving action instructions, the automatic driving vehicle has a certain probability of being converted from the current transverse state to the next transverse state, and also has a certain probability of keeping the current transverse state, each transverse state corresponds to a reward value, and the reward value can be calculated through a reward function; optionally, the road lateral driving action command corresponding to the condition that the reward value is greater than the preset reward threshold value may be used as the first lateral decision result output by the model.
According to the road transverse decision-making model in the embodiment of the application, the safety, traffic rules, comfort and traffic efficiency of the automatic driving vehicle in the automatic driving process are used as the evaluation criteria of the road transverse decision-making strategy, the evaluation effect on the road transverse decision-making model is more comprehensive, the driving safety and driving comfort of the automatic driving vehicle are improved, and the riding experience is improved.
In order to ensure that the road transverse decision-making strategy has better applicability, the target vehicle can also receive an updated road transverse decision-making model sent by the cloud server in the automatic driving process, and the updated road transverse decision-making model is used as the road transverse decision-making strategy, as shown in fig. 4:
the vehicle-mounted sensor acquires the current running condition information and the current road environment information of the target vehicle in real time, and continuously transmits the current running condition information and the current road environment information of the target vehicle to the road-side communication equipment through the vehicle-mounted computing unit and the vehicle-mounted communication unit, the data is transmitted to a cloud server through a road-end communication device, a learning system on the cloud server updates sample data of the sample vehicle based on the current running condition information and the current road environment information of the target vehicle which are acquired in real time, the preset Markov model is trained and learned again according to the updated data, iterative optimization is carried out, and feeds the updated road transverse decision model back to the automatic driving vehicle calculation unit for standby, and when the automatic driving system of the vehicle is started next time, the updated road transverse decision model is used as a road transverse decision strategy.
In the embodiment of the present application, the intersection transverse decision policy is a transverse decision policy based on a finite state machine, and a feasible method for constructing the intersection transverse decision policy is as follows:
acquiring preset navigation information of a preset vehicle, preset road environment information of a road on which the preset vehicle runs, a preset initial transverse decision result and a preset target transverse decision result; establishing a mapping relation among preset navigation information, preset road environment information, a preset initial transverse decision result and a preset target transverse decision result; and taking the mapping relation as a crossing transverse decision strategy.
Fig. 5 is a structural diagram of a lateral decision strategy of an intersection, as shown in fig. 5: the transverse decision result of the intersection transverse decision strategy comprises a preparation state SPRGo straight SGSLeft turn STLTurning right STRU-turn SUTAnd when the corresponding conditions are met, transferring the transverse state of the target vehicle from the initial transverse decision result to the target transverse decision result. The transition relationship between the initial lateral decision result and the target lateral decision result is shown in table 1 below:
TABLE 1 transition relationship Table for initial and target lateral decision results
In the present application, when the target vehicle is in the intersection condition, the current navigation information and the current road environment information of the target vehicle are processed by using the intersection transverse decision strategy according to the step of S204, so as to obtain a second transverse decision result of the target vehicle:
obtaining a current initial transverse decision result of a target vehicle; according to a pre-established mapping relation, acquiring a preset transverse decision result corresponding to current navigation information, current road environment information and a current initial transverse decision result in the table 1; and taking a preset transverse decision result corresponding to the current navigation information, the current road environment information and the current initial transverse decision result as a second transverse decision result.
According to the automatic vehicle driving decision method, when the distance between the current position information of a target vehicle and a target intersection is larger than or equal to a preset distance threshold value, the driving scene of the target vehicle is determined to be a road driving scene, and the current driving condition information of the target vehicle and the current road environment information are processed according to a road transverse decision strategy to obtain a first transverse decision result; when the distance between the current position information of the target vehicle and the target intersection is smaller than a preset distance threshold value, determining that the driving scene of the target vehicle is an intersection driving scene, and processing the current navigation information and the current road environment information of the target vehicle according to a road intersection transverse decision strategy to obtain a second transverse decision result; and determining the running track of the target vehicle according to the first transverse decision result and the second transverse decision result. Different transverse decision methods are adopted for different driving scenes, so that the complexity of an automatic driving decision system under a road working condition is reduced, and the efficiency and the accuracy of automatic driving decision are improved.
On the other hand, an embodiment of the present application further provides a vehicle automatic driving decision device, fig. 6 is a schematic structural diagram of the vehicle automatic driving decision device provided in the embodiment of the present application, and as shown in fig. 6, the device includes:
an obtaining module 601, configured to obtain current position information, current navigation information, current driving condition information, and current road environment information of a road on which a target vehicle is driving;
a scene determining module 602, configured to determine a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, where the driving scene includes a road driving scene and an intersection driving scene;
the first transverse decision module 603 is configured to, when a driving scene of a target vehicle is a road driving scene, process current driving condition information of the target vehicle and the current road environment information according to a road transverse decision policy to obtain a first transverse decision result of the target vehicle;
a second transverse decision module 604, configured to, when a driving scene of a target vehicle is an intersection driving scene, process current navigation information of the target vehicle and the current road environment information according to an intersection transverse decision policy to obtain a second transverse decision result of the target vehicle;
a track determining module 605, configured to determine a driving track of the target vehicle according to the first lateral decision result and/or the second lateral decision result.
The device and method embodiments in the embodiments of the present application are based on the same application concept.
The method and the device for automatic vehicle driving decision-making are applied to the technical field of automatic vehicle driving, the current position information, the current navigation information, the current driving working condition information and the current road environment information of a road on which a target vehicle runs are obtained in real time, whether the vehicle is in a road working condition or an intersection working condition is judged, a road transverse decision-making strategy is adopted in the road working condition, and an intersection transverse decision-making strategy is adopted in the intersection working condition, so that the complexity of a decision-making system is reduced, and the decision-making efficiency and accuracy are improved.
The embodiment of the invention provides a vehicle-mounted terminal, which comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the vehicle automatic driving decision method provided by the above method embodiment.
The memory may be used to store software programs and modules, and the processor may execute various functional applications by executing the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.
The method provided by the embodiment of the invention can be executed on the vehicle-mounted terminal. As shown in fig. 7, the internal structure of the in-vehicle terminal may include, but is not limited to: a processor, a network interface, and a memory, wherein the processor, the network interface, and the memory may be connected by a bus or other means.
The processor (or CPU) is a computing core and a control core of the computer device. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.). Memory (Memory) is a Memory device in a computer device used to store programs and data. It is understood that the memory herein may be a high-speed RAM storage device, or may be a non-volatile storage device (non-volatile memory), such as at least one magnetic disk storage device; optionally, at least one memory device located remotely from the processor. The memory provides storage space that stores an operating system of the electronic device, which may include, but is not limited to: a Windows system (an operating system), a Linux system (an operating system), an Android system, an IOS system, etc., which are not limited in the present invention; also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. In this embodiment, the processor loads and executes one or more instructions stored in the memory to implement the method for deciding automatic driving of a vehicle provided in the above method embodiment.
Embodiments of the present invention also provide a computer-readable storage medium, which may be disposed in a terminal to store at least one instruction, at least one program, a code set, or a set of instructions related to implementing a method for vehicle automatic driving decision, where the at least one instruction, the at least one program, the code set, or the set of instructions are loaded and executed by the processor to implement the method for vehicle automatic driving decision provided by the foregoing embodiments of the method.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, as any modifications, equivalents, improvements and the like within the spirit and principle of the present invention should be included in the present invention.
Claims (11)
1. A method for vehicle autopilot decision making, comprising:
acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, wherein the driving scene comprises a road driving scene and an intersection driving scene;
when the driving scene of the target vehicle is the road driving scene, processing the current driving condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle;
when the driving scene of the target vehicle is the intersection driving scene, processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy to obtain a second transverse decision result of the target vehicle;
and determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
2. The vehicle automatic driving decision method according to claim 1, wherein the determining a driving scenario of the target vehicle based on the current location information of the target vehicle and the current road environment information comprises:
the current road environment information comprises information of a front target intersection and a rear target intersection of the target vehicle;
and under the condition that the distance between the current position information of the target vehicle and the front target intersection is greater than or equal to a first distance threshold value or the distance between the current position information of the target vehicle and the rear target intersection is greater than or equal to a second distance threshold value, determining that the driving scene of the target vehicle is the road driving scene.
3. The method for vehicle automatic driving decision-making according to any one of claims 1-2, wherein the determining the driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle comprises:
the current road environment information comprises information of a front target intersection and a rear target intersection of the target vehicle;
and under the condition that the distance between the current position information of the target vehicle and the front target intersection is smaller than a first distance threshold value or the distance between the target position information and the rear target intersection is smaller than a second distance threshold value, determining that the driving scene of the target vehicle is the intersection driving scene.
4. The method for vehicle automatic driving decision-making according to any one of claims 1-3, wherein the processing the current driving condition information of the target vehicle and the current road environment information according to a road lateral decision-making strategy to obtain a first lateral decision-making result of the target vehicle comprises:
receiving a road transverse decision model sent by a server;
taking the received road transverse decision model as the road transverse decision strategy;
processing the current running condition information and the current road environment information of the target vehicle according to the road transverse decision model to obtain the first transverse decision result of the target vehicle;
the road transverse decision model is obtained by training a preset model based on sample data of a sample vehicle, the preset model is a Markov reinforcement learning-based model, and the sample data comprises sample running condition information of the sample vehicle and sample road environment information of a road on which the sample vehicle runs.
5. The vehicle autopilot decision method of claim 4, further comprising:
receiving an updated road transverse decision model sent by the server;
taking the updated road transverse decision model as the road transverse decision strategy;
the updated road transverse decision model is obtained by training the preset model based on updated sample data; and updating the sample data based on the current running condition information of the target vehicle and the current road environment information to obtain the updated sample data.
6. The vehicle autopilot decision method of claim 1 wherein the intersection lateral decision strategy is a finite state machine based lateral decision strategy, the method further comprising:
acquiring preset navigation information of a preset vehicle, preset road environment information of a road on which the preset vehicle runs, a preset initial transverse decision result and a preset target transverse decision result;
establishing a mapping relation among the preset navigation information, the preset road environment information, the preset initial transverse decision result and the preset target transverse decision result;
and taking the mapping relation as the intersection transverse decision strategy.
7. The method for vehicle automatic driving decision-making according to claim 6, wherein the processing the current navigation information and the current road environment information of the target vehicle according to the intersection lateral decision-making policy to obtain a second lateral decision-making result of the target vehicle comprises:
obtaining a current initial transverse decision result of the target vehicle;
acquiring a preset transverse decision result corresponding to the current navigation information, the current road environment information and the current initial transverse decision result according to the mapping relation;
and taking the preset transverse decision result corresponding to the current navigation information, the current road environment information and the current initial transverse decision result as the second transverse decision result.
8. The vehicle autopilot decision method of claim 1, wherein the determining a trajectory of travel of the target vehicle based on the first lateral decision result and/or the second lateral decision result comprises:
taking the first lateral decision result and/or the second lateral decision result as a target lateral decision result of the target vehicle;
determining a target longitudinal decision result based on the target transverse decision result;
and determining the running track of the target vehicle according to the target transverse decision result and the target longitudinal decision result.
9. An automatic vehicle driving decision device, comprising:
the system comprises an acquisition module, a navigation module and a control module, wherein the acquisition module is used for acquiring current position information, current navigation information, current running condition information and current road environment information of a road on which a target vehicle runs;
the scene determining module is used for determining a driving scene of the target vehicle based on the current position information and the current road environment information of the target vehicle, wherein the driving scene comprises a road driving scene and an intersection driving scene;
the first transverse decision module is used for processing the current running working condition information and the current road environment information of the target vehicle according to a road transverse decision strategy to obtain a first transverse decision result of the target vehicle when the running scene of the target vehicle is the road running scene;
the second transverse decision module is used for processing the current navigation information and the current road environment information of the target vehicle according to an intersection transverse decision strategy when the driving scene of the target vehicle is the intersection driving scene to obtain a second transverse decision result of the target vehicle;
and the track determining module is used for determining the running track of the target vehicle according to the first transverse decision result and/or the second transverse decision result.
10. A vehicle-mounted terminal, characterized in that the vehicle-mounted terminal comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded by the processor and executed to implement the vehicle automatic driving decision method according to any claim 1 to 8.
11. A computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the vehicle autopilot decision method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210393556.6A CN114644016A (en) | 2022-04-14 | 2022-04-14 | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210393556.6A CN114644016A (en) | 2022-04-14 | 2022-04-14 | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114644016A true CN114644016A (en) | 2022-06-21 |
Family
ID=81997207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210393556.6A Pending CN114644016A (en) | 2022-04-14 | 2022-04-14 | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114644016A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114821542A (en) * | 2022-06-23 | 2022-07-29 | 小米汽车科技有限公司 | Target detection method, target detection device, vehicle and storage medium |
| CN115437705A (en) * | 2022-08-02 | 2022-12-06 | 广州汽车集团股份有限公司 | Method and device for providing vehicle service, electronic equipment and storage medium |
| CN115771506A (en) * | 2022-11-17 | 2023-03-10 | 清华大学 | Method and device for determining vehicle driving strategy based on passenger risk cognition |
-
2022
- 2022-04-14 CN CN202210393556.6A patent/CN114644016A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114821542A (en) * | 2022-06-23 | 2022-07-29 | 小米汽车科技有限公司 | Target detection method, target detection device, vehicle and storage medium |
| CN115437705A (en) * | 2022-08-02 | 2022-12-06 | 广州汽车集团股份有限公司 | Method and device for providing vehicle service, electronic equipment and storage medium |
| CN115437705B (en) * | 2022-08-02 | 2024-04-12 | 广州汽车集团股份有限公司 | Method, device, electronic equipment and storage medium for providing vehicle service |
| CN115771506A (en) * | 2022-11-17 | 2023-03-10 | 清华大学 | Method and device for determining vehicle driving strategy based on passenger risk cognition |
| CN115771506B (en) * | 2022-11-17 | 2023-06-20 | 清华大学 | Method and device for determining vehicle driving strategy based on passenger risk cognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022052406A1 (en) | Automatic driving training method, apparatus and device, and medium | |
| CN110861650B (en) | Vehicle path planning method and device, vehicle-mounted equipment and storage medium | |
| CN110562258B (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
| CN111653113B (en) | Method, device, terminal and storage medium for determining local path of vehicle | |
| CN114644016A (en) | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium | |
| CN113460042B (en) | Vehicle driving behavior recognition method and recognition device | |
| US11320282B2 (en) | Driving control method and driving control device | |
| US11815891B2 (en) | End dynamics and constraints relaxation algorithm on optimizing an open space trajectory | |
| US11614962B2 (en) | Scheduling vehicle task offloading and triggering a backoff period | |
| CN110673602A (en) | Reinforced learning model, vehicle automatic driving decision method and vehicle-mounted equipment | |
| CN113160547B (en) | Automatic driving method and related equipment | |
| CN112429016B (en) | Automatic driving control method and device | |
| CN111591306A (en) | Driving track planning method of automatic driving vehicle, related equipment and storage medium | |
| CN113492830A (en) | Vehicle parking path planning method and related equipment | |
| CN116457853A (en) | Vehicle track planning method and device and vehicle | |
| EP4119412A1 (en) | Vehicle-based data processing method and apparatus, computer, and storage medium | |
| CN113785252A (en) | Method of parking an autonomously driven vehicle for autonomous charging | |
| CN112829769A (en) | Hybrid planning system for autonomous vehicles | |
| CN114620070A (en) | Driving track planning method, device, equipment and storage medium | |
| CN113968242B (en) | Automatic driving scene generation method, device and system | |
| CN113167038B (en) | Method and device for vehicle to pass through barrier gate cross bar | |
| CN114440908A (en) | Method and device for planning vehicle driving path, intelligent vehicle and storage medium | |
| US20230391356A1 (en) | Dynamic scenario parameters for an autonomous driving vehicle | |
| US20230141801A1 (en) | Systems and methods for maneuvering vehicles using predictive control and automated driving | |
| CN115810291A (en) | Associated target identification method and device, road side equipment and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |