Control method and device and intelligent driving equipment
By obtaining the probability distribution of obstacles entering the lane, the control strategy of intelligent driving equipment is determined, which solves the problem of behavioral mutations of autonomous driving vehicles in uncertain scenarios, realizes the continuity and consistency of behavior, and improves the driving of users Riding experience.
Patent Information
- Application Number
- CN202310637657.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2024-12-17
AI Technical Summary
When an autonomous vehicle faces an uncertain interactive object, the jump in the prediction results or decision results leads to a mutation in behavior, affecting the user's driving experience.
By obtaining the probability distribution of obstacles entering the lane, the game results of the intelligent driving equipment against obstacles are determined, and the equipment is controlled based on the probability distribution to achieve continuity and consistency of behavior and avoid jumps in prediction results or decision results.
It improves the user's driving experience, and through the probability distribution, the prediction, decision-making and planning process are connected, the continuous consistency of the behavior of intelligent driving equipment is ensured, overly aggressive driving strategies are reduced, and driving safety is improved.
Smart Images
Figure CN119142359A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent driving, and more specifically, to a control method, device and intelligent driving equipment. Background Art
[0002] In the field of autonomous driving, vehicles will face a variety of potential interactive objects when driving on the road, such as cutting in, sideways squeezing, using lanes to avoid obstacles, and other behaviors that merge into the lane where the vehicle is located. These potential interactive behaviors are highly uncertain. Currently, if the vehicle's prediction results or decision results for obstacles change suddenly, the behavior of the autonomous driving vehicle (braking / acceleration / obstacle avoidance) will change suddenly, which will affect the user's driving experience. Summary of the invention
[0003] The present application provides a control method, device and intelligent driving equipment, which help to improve the ability of autonomous driving equipment to handle uncertain scenarios, achieve continuity and consistency in the behavior of intelligent driving equipment, and help improve the user's driving experience.
[0004] In the first aspect, the present application provides a control method, which can be executed by an intelligent driving device; or, it can also be executed by a computing platform of the intelligent driving device; or, it can also be executed by a chip, processor or circuit used for the intelligent driving device, which is not limited in the present application.
[0005] The intelligent driving equipment involved in this application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving equipment can be a vehicle, which is a vehicle in a broad sense, and can be a vehicle (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. The embodiment of this application does not specifically limit the type of vehicle. For another example, the intelligent driving equipment can be a vehicle such as an airplane or a ship.
[0006] The control method includes: obtaining a probability distribution of an obstacle merging into a lane where an intelligent driving device is located, the probability distribution indicating the probability of the obstacle merging into the lane within a period of time in the future; determining a game result of the intelligent driving device on the obstacle based on the probability distribution; and controlling the intelligent driving device based on the probability distribution when the game result indicates that the intelligent driving device gives way to the obstacle.
[0007] Based on the above technical solution, the game result of the intelligent driving device on the obstacle can be determined through the probability distribution of the obstacle merging into the lane where the intelligent driving device is located. And when the game result indicates to give way to the obstacle, the intelligent driving device is controlled through the probability distribution. In this way, the prediction process, decision process and planning process are connected in series through the probability distribution, and the continuous consistency of the behavior of the intelligent driving device is achieved. It helps to avoid sudden changes in the behavior of the intelligent driving device when there is a jump in the prediction result or decision result, and helps to improve the user's driving experience.
[0008] In some possible implementations, the probability distribution result includes the probability of an obstacle merging into the lane where the intelligent driving device is located at multiple moments in the future, and the probability is between (0, 1).
[0009] In some possible implementations, the obstacle may include a vehicle, a pedestrian, etc.
[0010] In some possible implementations, the intelligent driving device is in an automatic driving state.
[0011] In combination with the first aspect, in some implementations of the first aspect, controlling the intelligent driving device according to the probability distribution includes: determining, according to the probability distribution, the constraints imposed by the obstacle on the intelligent driving device; and controlling the intelligent driving device according to the constraints.
[0012] In the current technical solution, the decision unit of the intelligent driving device only obtains the decision result of whether the obstacle is merged or not based on the predicted intention of the obstacle. If there is a jump in the decision result, the regulation and control module may output a more aggressive driving strategy (for example, emergency braking). Based on the above technical solution, constraints on the intelligent driving device can be generated through probability distribution, which helps to improve the accuracy of the generated constraints and avoid overly aggressive driving strategies of the intelligent driving device, thereby helping to improve the user's driving experience.
[0013] In combination with the first aspect, in certain implementations of the first aspect, determining the constraint imposed by the obstacle on the intelligent driving device based on the probability distribution includes: determining the first constraint imposed by the obstacle on the intelligent driving device when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold; or determining the second constraint imposed by the obstacle on the intelligent driving device when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold; wherein the breakability of the first constraint is less than the breakability of the second constraint.
[0014] Based on the above technical solution, when the probability distribution indicates that the obstacle converges, the comparison with the preset threshold value is used to adjust the breakability of the constraints generated by the intelligent driving device, which helps to improve the accuracy of the generated constraints. For example, when the probability of convergence is greater than the preset threshold value, the intelligent driving device can use a smaller acceleration to drive; and when the probability of convergence is less than the preset threshold value, the intelligent driving device can use a larger acceleration to drive.
[0015] Exemplarily, the preset threshold may be 0.6.
[0016] In combination with the first aspect, in certain implementations of the first aspect, controlling the intelligent driving device according to the probability distribution includes: controlling a display device to display a curved red wall, where the curved red wall indicates the constraint.
[0017] In some possible implementations, controlling the display device to display the curved red wall includes: controlling the display device to display the virtuality and reality degree and the opening size of the curved red wall, wherein the virtuality and reality degree and the opening size are associated with the breakability of the constraint.
[0018] Based on the above technical solution, the intelligent driving device can control the display device to display the curved red wall according to the probability distribution. The curved red wall displayed by the display device can make the driver clear about the constraints caused by obstacles, which helps the driver understand the probability of surrounding obstacles merging. When encountering a situation that the driver considers to be more urgent, the driver can take over the intelligent driving device in time, which helps to improve driving safety.
[0019] In combination with the first aspect, in certain implementations of the first aspect, obtaining the probability distribution of an obstacle merging into a lane where the intelligent driving device is located includes: obtaining historical observations of the intelligent driving device and the obstacle, the historical observations including positions and orientation angles; determining a predicted trajectory of the obstacle based on the historical observations of the intelligent driving device and the obstacle; and determining the probability distribution based on a planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
[0020] In some possible implementations, the probability distribution is determined according to the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle, including: determining the probability distribution according to the planned trajectory of the intelligent driving device, the predicted trajectory of the probability object and prior information, wherein the prior information includes one or more of the road topology structure of the scene in which the intelligent driving device is located, the turn signal information of the obstacle, and the positional relationship between the obstacle and the lane line.
[0021] Based on the above technical solution, prior information can be combined when determining the probability distribution, which helps to further improve the accuracy of the calculated probability distribution.
[0022] In combination with the first aspect, in certain implementations of the first aspect, determining the game result of the intelligent driving device with respect to the obstacle according to the probability distribution, including: performing a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; and determining the game result according to the cost evaluation result and the probability distribution.
[0023] Based on the above technical solution, by performing cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle, and determining the game result based on the cost evaluation result, it helps to improve the accuracy of the game result obtained by the decision-making module.
[0024] In combination with the first aspect, in certain implementations of the first aspect, the cost evaluation result includes at least two cost evaluation results among a safety cost evaluation result, a passability cost evaluation result, a right of way evaluation result and a comfort evaluation result, and the game result is determined based on the cost evaluation result and the probability distribution, including: determining the weight of each of the at least two cost evaluation results based on the probability distribution; determining the game result based on the weight of each cost evaluation result of the at least two cost evaluation results and the at least two cost evaluation results.
[0025] Based on the above technical solution, the weight of each evaluation result is determined by probability distribution, which helps to further improve the accuracy of the game results obtained by decision-making. For example, a high probability of convergence indicates that the obstacle has a strong convergence intention, a low degree of cooperation, and a low gameability. At this time, the weight of the safety cost evaluation can be increased. A low probability of convergence indicates that the obstacle has a weak convergence intention. At this time, the weight of the comfort cost evaluation can be increased.
[0026] In a second aspect, the present application provides a control device, which includes: an acquisition unit, used to obtain the probability distribution of an obstacle merging into a lane where an intelligent driving device is located, and the probability distribution indicates the probability of the obstacle merging into the lane within a period of time in the future; a determination unit, used to determine the game result of the intelligent driving device on the obstacle based on the probability distribution; and a control unit, used to control the intelligent driving device according to the probability distribution when the game result indicates that the intelligent driving device gives way to the obstacle.
[0027] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is used to: determine, based on the probability distribution, the constraints imposed by the obstacle on the intelligent driving device; and the control unit is used to: control the intelligent driving device based on the constraints.
[0028] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is used to: determine a first constraint imposed on the intelligent driving device by the obstacle when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold; or determine a second constraint imposed on the intelligent driving device by the obstacle when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold; wherein the breakability of the first constraint is less than the breakability of the second constraint.
[0029] In combination with the second aspect, in some implementations of the second aspect, the control unit is used to: control the display device to display a curved red wall, where the curved red wall indicates the constraint.
[0030] In combination with the second aspect, in certain implementations of the second aspect, the acquisition unit is used to: obtain historical observations of the intelligent driving device and the obstacle, the historical observations including positions and orientation angles; determine a predicted trajectory of the obstacle based on the historical observations of the intelligent driving device and the obstacle; and determine the probability distribution based on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
[0031] In combination with the second aspect, in certain implementations of the second aspect, the determination unit is used to: perform a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; and determine the game result based on the cost evaluation result and the probability distribution.
[0032] In combination with the second aspect, in certain implementations of the second aspect, the cost evaluation result includes at least two cost evaluation results among a safety cost evaluation result, a passability cost evaluation result, a right of way evaluation result and a comfort evaluation result, and the determination unit is used to: determine the weight of each of the at least two cost evaluation results according to the probability distribution; determine the game result according to the weight of each cost evaluation result of the at least two cost evaluation results and the at least two cost evaluation results.
[0033] In a third aspect, the present application provides a control device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit to enable the device to perform any possible control method in the first aspect.
[0034] In a fourth aspect, the present application provides a control system, which includes a sensor and a computing platform, and the computing platform includes any possible control device in the second aspect, or includes the control device described in the third aspect.
[0035] In combination with the fourth aspect, in certain implementations of the fourth aspect, the control system also includes a display device.
[0036] In combination with the fourth aspect, in certain implementations of the fourth aspect, the computing platform is located in a cloud server.
[0037] In a fifth aspect, the present application provides an intelligent driving device, which includes any possible control device in the second aspect, or includes the control device described in the third aspect, or includes the control system described in the fourth aspect.
[0038] In some possible implementations, the intelligent driving device is a vehicle.
[0039] In a sixth aspect, the present application provides a server, which includes any possible control device in the second aspect or the third aspect.
[0040] In combination with the sixth aspect, in some implementations of the sixth aspect, the server also includes a communication unit, which is used to receive information sent by the intelligent driving device, or send information to the intelligent driving device.
[0041] In a seventh aspect, the present application provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any possible control method in the first aspect.
[0042] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or separately packaged with the processor, and the embodiments of the present application do not specifically limit this.
[0043] In an eighth aspect, the present application provides a computer-readable medium storing a program code, and when the computer program code runs on a computer, the computer executes any possible control method in the first aspect.
[0044] In a ninth aspect, the present application provides a chip, comprising a circuit for executing any possible control method in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a functional block diagram of the intelligent driving device provided in an embodiment of the present application.
[0046] Figure 2 It is a schematic diagram of an application scenario provided by an embodiment of the present application.
[0047] Figure 3 It is a schematic flow chart of the control method provided in the embodiment of the present application.
[0048] Figure 4 It is a schematic diagram of a reference trajectory pair between an intelligent driving device and an obstacle provided in an embodiment of the present application.
[0049] Figure 5 It is a schematic diagram of a three-dimensional surface function of the prior probability of an obstacle in a merging scene provided in an embodiment of the present application.
[0050] Figure 6 It is a schematic diagram of the constraints of the intelligent driving device provided in an embodiment of the present application.
[0051] Figure 7 It is a schematic diagram of the human-machine interface HMI provided in an embodiment of the present application.
[0052] Figure 8 It is another schematic flow chart of the control method provided in an embodiment of the present application.
[0053] Fig. 9 It is a curve of changes in speed and acceleration of an intelligent driving device in different scenarios by using the technical solution of the embodiment of the present application and not using the technical solution of the embodiment of the present application.
[0054] Fig.10 It is a schematic block diagram of a control device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0055] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.
[0056] The prefixes such as "first" and "second" used in the embodiments of the present application are only used to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers used to distinguish description objects in the embodiments of the present application does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.
[0057] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0058] Figure 1 It is a functional block diagram of the intelligent driving device 100 provided in an embodiment of the present application. The intelligent driving device 100 may include a perception system 120, a display device 130 and a computing platform 150, wherein the perception system 120 may include one or more sensors for sensing information about the environment around the intelligent driving device 100. For example, the perception system 120 may include a positioning system, and the positioning system may be a global positioning system (GPS), or a Beidou system or other positioning systems. The perception system 120 may also include one or more of an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera device.
[0059] Some or all functions of the intelligent driving device 100 may be controlled by the computing platform 150. The computing platform 150 may include one or more processors, such as processors 151 to 15n (n is a positive integer). The processor is a circuit with signal processing capability. In one implementation, the processor may be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement certain functions through the logical relationship of the hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by a processor as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which may be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory, the memory is used to store instructions, and some or all of the processors 151 to 15n may call the instructions in the memory to implement corresponding functions.
[0060] The display device 130 in the cockpit is mainly divided into two categories. The first category is the vehicle display screen; the second category is the projection display screen, such as a head up display (HUD). The vehicle display screen is a physical display screen and an important part of the vehicle infotainment system. Multiple display screens can be set in the cockpit, such as a digital instrument display screen, a central control screen, a display screen in front of the passenger in the co-pilot seat (also called the front passenger), a display screen in front of the left rear passenger, and a display screen in front of the right rear passenger. Even the window can be used as a display screen for display. Head-up display, also known as a head-up display system. It is mainly used to display driving information such as speed and navigation on a display device in front of the driver (such as a windshield). To reduce the driver's line of sight transfer time, avoid pupil changes caused by the driver's line of sight transfer, and improve driving safety and comfort. HUD includes, for example, a combined head-up display (C-HUD) system, a windshield head-up display (W-HUD) system, and an augmented reality head-up display system (AR-HUD). It should be understood that other types of HUD systems may appear as technology evolves, and this application is not limited to this.
[0061] As mentioned above, in the field of autonomous driving, vehicles will face a variety of potential interactive objects when driving on the road, such as cutting in, sideways squeezing, using lanes to avoid obstacles, and other behaviors that merge into the lane where the vehicle is located. These potential interactive behaviors are highly uncertain. Currently, if the vehicle's prediction results or decision results for obstacles change suddenly, the vehicle's behavior (braking / acceleration / obstacle avoidance) will change suddenly, which will affect the user's driving experience.
[0062] The embodiments of the present application provide a control method, device and intelligent driving device. The probability distribution of obstacles merging into the lane where the intelligent driving device is located can determine the game result of the intelligent driving device on the obstacle. And when the game result indicates to give way to the obstacle, the intelligent driving device is controlled by the probability distribution. In this way, the continuous consistency of the behavior of the intelligent driving device is achieved by connecting the prediction process, decision-making process and planning process in series through the probability distribution. It helps to avoid sudden changes in the behavior of the intelligent driving device when there is a jump in the prediction result or decision result, and helps to improve the user's driving experience.
[0063] Figure 2 A schematic diagram showing an application scenario provided by an embodiment of the present application is shown.
[0064] like Figure 2As shown in (a) in FIG. 1 , vehicle 1 is located in the left lane and vehicle 2 is located in the right lane. During the driving process, vehicle 1 can judge the probability distribution of vehicle 2 merging into the lane where vehicle 1 is located, so as to obtain the game result of vehicle 1 versus vehicle 2. For example, the game result indicates that vehicle 1 should overtake vehicle 2, or the game result indicates that vehicle 1 should yield to vehicle 2. When the game result indicates that vehicle 1 should yield to vehicle 2, vehicle 1 can control the driving of vehicle 1 according to the probability distribution.
[0065] In the above game results, if vehicle 1 determines that vehicle 2 is overtaking and merging into the lane where vehicle 1 is located, then vehicle 1 can give way to vehicle 2; or, if vehicle 1 determines that vehicle 2 is giving way and merging into the lane shown by vehicle 1, then vehicle 1 can overtake vehicle 2.
[0066] like Figure 2 As shown in (b) in FIG. 1 , vehicle 2 is preparing to merge into the lane where vehicle 1 is located. Figure 2 Similar to (b) in FIG. 1 , vehicle 1 can judge the probability distribution of vehicle 2 merging into the lane where vehicle 1 is located during driving, so as to obtain the game result of vehicle 1 versus vehicle 2. When the game result indicates that vehicle 1 yields to vehicle 2, vehicle 1 can control its driving according to the probability distribution.
[0067] like Figure 2 As shown in (c) in the figure, vehicle 1 determines that a pedestrian may cross the lane where vehicle 1 is located during driving. Vehicle 1 can judge the probability distribution of the pedestrian entering the lane, and thus obtain the game result of vehicle 1 on the pedestrian based on the probability distribution. For example, the game result indicates that vehicle 1 rushes to the pedestrian, or the game result indicates that vehicle 1 yields to the pedestrian. When the game result indicates that vehicle 1 yields to the pedestrian, vehicle 1 can control the driving of vehicle 1 based on the probability distribution.
[0068] Figure 3 FIG. 3 is a schematic flow chart of a control method 300 provided in an embodiment of the present application. The method 300 may be Figure 1 The method 300 may be performed by the intelligent driving device 100 shown in the figure, or the method 300 may be performed by the computing platform 150, or the method 300 may be performed by a system consisting of the computing platform 150 and a sensor, or the method 300 may be performed by a system-on-chip (SoC) in the computing platform 150, or the method 300 may be performed by a processor in the computing platform 150. The method 300 includes:
[0069] S310, obtaining a probability distribution of an obstacle merging into a lane where the intelligent driving device is located, where the probability distribution indicates a probability of the obstacle merging into the lane within a future period of time.
[0070] The above intelligent driving device may be the above intelligent driving device 100, and the obstacle may also be understood as an obstacle around the intelligent driving device (for example, a motor vehicle, a non-motor vehicle or a pedestrian, etc.).
[0071] Optionally, obtaining the probability distribution of an obstacle merging into a lane where the intelligent driving device is located includes: obtaining historical observations of the intelligent driving device and the obstacle, the historical observations including positions and orientation angles; determining a predicted trajectory of the obstacle based on the historical observations of the intelligent driving device and the obstacle; and determining the probability distribution based on a planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
[0072] Exemplarily, the historical observations of the intelligent driving device and the obstacle (including xy coordinates and orientation angles) can be connected to the following Bayesian formula using the Gaussian conditional density equation:
[0073]
[0074] Among them, P(Cutin|Observation) can also be called the posterior probability, which represents the probability that the obstacle will merge into the lane where the intelligent driving device is located in a certain frame in the future. The value range of P(Cutin|Observation) is (0, 1). P(Cutin) represents the prior probability of the obstacle in the merge scenario. P(d|Cutin) represents the distance between the obstacle and the reference line in the Euclidean space in the merge scenario. P(θ|Cutin) represents the direction angle of the obstacle in the SL coordinate system in the merge scenario. P(Keep) represents the prior probability of the obstacle in the non-merge scenario and P(Keep) is equal to 1 minus P(Cutin). P(d|Keep) represents the distance between the obstacle and the reference line in the Euclidean space in the non-merge scenario. P(θ|Keep) represents the direction angle of the obstacle in the SL coordinate system in the non-merge scenario. Among them, the SL coordinate system is different in the merge scenario and the non-merge scenario.
[0075] The above P(d|Cutin) and P(θ|Cutin) can be understood as the position information and orientation angle of the obstacle at a certain time T1 in the future, and P(Cutin|Observation) can be understood as the probability that the obstacle will merge into the lane where the intelligent driving device is located at time T1.
[0076] Figure 4 A schematic diagram of a reference track pair between an intelligent driving device and an obstacle provided in an embodiment of the present application is shown, wherein a reference line of obstacle 1 in a merging scenario and a reference line in a non-merging scenario are shown, and a reference line of obstacle 2 in a merging scenario and a reference line in a non-merging scenario are shown.
[0077] For example, the prior probability P(Cutin) of an obstacle in the merged scene can be obtained by the following formula:
[0078]
[0079] Among them, α and β are constants; BoxDis tan ceToLane represents the distance between the obstacle and the lane line where the obstacle is located (for example, the lane line close to the side of the intelligent driving device), and centerDist represents half the width of the lane where the intelligent driving device is located.
[0080] The above is explained by using the Gaussian conditional density equation to access the following Bayesian formula as an example, and the embodiments of the present application are not limited to this. For example, the chain rule can also be used to determine the probability distribution. For example, the joint distribution of multiple feature quantities is split by the chain rule, and the joint distribution includes the Bayesian prior probability and the Gaussian mixture function.
[0081] Figure 5 The figure shows a three-dimensional surface function diagram of the prior probability of an obstacle in a merging scenario provided by an embodiment of the present application. If the obstacle continues to run along the lane line within [T0, T1], the prior probability P(Cutin) will continue to decrease. As the prior probability P(Cutin) continues to decrease, P(Cutin|Observation) will also gradually decrease.
[0082] The above prior probability is explained by taking the distance between the obstacle and the lane line as an example, and the embodiments of the present application are not limited to this. For example, the semantic information can be integrated as the prior probability using logistic regression. For example, taking the obstacle as vehicle 2 as an example, the semantic information can be the distance between vehicle 2 and the lane line, the information of the turn signal of vehicle 2, the type of vehicle 2 (for example, a large truck, a bus or a family car, etc.), the degree of congestion of the road where vehicle 2 is located, the type of lane where vehicle 2 is located (for example, a bus lane), and one or more of the road topology.
[0083] The above S310 can also be understood as a prediction stage.
[0084] S320: Determine a gaming result of the intelligent driving device with respect to the obstacle according to the probability distribution.
[0085] Optionally, determining a game result of the intelligent driving device with respect to the obstacle according to the probability distribution includes: performing a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; and determining the game result according to the cost evaluation result and the probability distribution.
[0086] Optionally, the cost evaluation result includes at least two cost evaluation results among a safety cost evaluation result, a passability cost evaluation result, a right of way evaluation result and a comfort evaluation result. The game result is determined based on the cost evaluation results and the probability distribution, including: determining the weight of each cost evaluation result of the at least two cost evaluation results based on the probability distribution; determining the game result based on the weight of each cost evaluation result of the at least two cost evaluation results and the at least two cost evaluation results.
[0087] For example, the safety cost evaluation result is cost1, the trafficability cost evaluation result is cost2, the road right evaluation result is cost3, and the comfort evaluation result is cost4. The planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle are evaluated, and the calculation formula of the cost evaluation result cost can be shown in the following formula:
[0088] Cost=w1cost1+w2cost2+w3cost3+w4cost4
[0089] Among them, cost is the cost evaluation result, w1 is the weight of the safety cost evaluation result, w2 is the weight of the trafficability cost evaluation result, w3 is the weight of the road right evaluation result, and w4 is the weight of the comfort evaluation result.
[0090] Optionally, based on the probability distribution, the weight of each of the at least two cost evaluation results is determined, including: when the probability of the obstacle entering at a second moment in the future is greater than or equal to a first preset threshold, w1 is increased and w4 is decreased; or, when the probability of the obstacle entering at the second moment is less than a second preset threshold, w1 is decreased and w4 is increased.
[0091] Exemplarily, the first preset threshold may be 0.6.
[0092] Exemplarily, the second preset threshold may be 0.3.
[0093] For example, initially w1 is 0.3 and w4 is 0.3. At a certain time T2 in the future, the probability of the obstacle entering is 0.7, so w1 can be adjusted to 0.5 and w4 can be adjusted to 0.1. A high probability of entering indicates that the obstacle has a strong intention to enter, a low degree of cooperation, and low gameability. At this time, it can be ensured that the safety cost assessment is the main reference factor for the final decision.
[0094] The above S320 can be understood as a decision-making stage.
[0095] S330: When the game result indicates that the intelligent driving device should give way to the obstacle, control the intelligent driving device according to the probability distribution.
[0096] Optionally, controlling the intelligent driving device according to the probability distribution includes: determining, according to the probability distribution, a constraint imposed by the obstacle on the intelligent driving device; and controlling the intelligent driving device according to the constraint.
[0097] Optionally, determining the constraint imposed by the obstacle on the intelligent driving device based on the probability distribution includes: determining a first constraint imposed by the obstacle on the intelligent driving device when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold; or determining a second constraint imposed by the obstacle on the intelligent driving device when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold; wherein the breakability of the first constraint is less than the breakability of the second constraint.
[0098] Figure 6 FIG. 1 is a schematic diagram showing the constraints of the intelligent driving device provided in the embodiment of the present application. Figure 6 As shown, in a multi-vehicle (vehicle 1, vehicle 2, vehicle 3, and vehicle 4) interaction scenario, the merging probability of obstacles (e.g., vehicle 2, vehicle 3, and vehicle 4) can affect the weight adjustment of the constraint term of the trajectory optimization equation of the intelligent driving device (e.g., vehicle 1).
[0099] For example, there is a vehicle 2 with a high probability of merging into the intelligent driving device in the distance. In the optimization equation, vehicle 2 is represented as a deterministic constraint (dashed line 1) under the planning map of vehicle 1, which cannot be broken; while for vehicles 3 and 4 with ambiguous intentions nearby, they are represented as uncertain soft constraints (dashed lines 2 and 3), which can be broken. The extent to which the constraints can be broken can be determined by the probability of the obstacle merging into the vehicle.
[0100] Optionally, the method 300 further includes: controlling a display device to display a curved red wall, wherein the curved red wall indicates the constraint.
[0101] Figure 7 The schematic diagram of the human machine interface (HMI) provided by the embodiment of the present application is shown. The above constraints can be converted into curved red walls, so that the user can easily view the distance between the intelligent driving device and the curved red wall corresponding to the obstacle.
[0102] For example, Figure 7 As shown in (a), when the vehicle 1 continues to cross the line, the edge of the curved red wall is small and the virtuality and reality degree of the curved red wall is 30%.
[0103] The virtuality or reality degree of the above curved red wall can be used to indicate the breakability of the constraint imposed by the obstacle on the intelligent driving device. The lower the virtuality or reality degree, the higher the breakability of the constraint, and the higher the virtuality or reality degree, the lower the breakability of the constraint.
[0104] For example, Figure 7 As shown in (b) in FIG. 1 , when the vehicle 1 turns left and the front of the vehicle deviates to the left, the opening of the curved red wall becomes larger and the virtuality of the curved red wall increases to 50%. Figure 7 The curved red wall shown in (a) Figure 7 The red wall shown in the curve (b) has a reduced breakthrough capability.
[0105] For example, Figure 7 As shown in (c), when vehicle 1 has entered the lane where the intelligent driving device is located, the curved red wall becomes a straight line and the virtuality of the curved red wall is increased to 90%. Figure 7 The curved red wall shown in (b) Figure 7 The breakability of the red wall shown in (c) is further reduced.
[0106] Figure 8 FIG. 8 is a schematic flow chart of a control method 800 provided in an embodiment of the present application. Figure 8 As shown, the method 800 includes:
[0107] S801, the obstacle screening module performs region of interest (ROI) screening.
[0108] The obstacle screening module can obtain information about obstacles around the intelligent driving device through ROI screening. The obstacle screening module can output the screened obstacle information to the prediction module.
[0109] Optionally, the number of the obstacle may be one or more.
[0110] Optionally, the information of one or more obstacles may include historical observations of one or more obstacles.
[0111] S802: The prediction module determines a predicted trajectory of the obstacle based on the historical observations of the obstacle.
[0112] Optionally, the predicted trajectory may include location information and orientation angles of the obstacle at multiple moments in the future.
[0113] S803, the prediction module determines the probability distribution of the obstacle merging into the lane where the intelligent driving device is located according to the prior information, the predicted trajectory of the obstacle and the planned trajectory of the intelligent driving device.
[0114] The prediction module can input the obtained probability distribution into the decision module and the regulation and control module respectively.
[0115] The above process of S803 can be combined with the description in the above embodiment and will not be repeated here.
[0116] S804: The decision module determines a game result according to the probability distribution, where the game result includes whether the intelligent driving device gives way to the obstacle or rushes to pass the obstacle.
[0117] Optionally, the decision module may determine the game result through cost evaluation results in different dimensions.
[0118] S805, the regulation and control module may generate constraints on the intelligent driving device according to the probability distribution output by the prediction module and the game result output by the decision module.
[0119] Optionally, the regulation and control module may also control the display device to display a curved red wall, which may indicate the constraint.
[0120] Table 1 shows a comparison of the miles per intervention (MPI) obtained by using the technical solution of the embodiment of the present application and not using the technical solution of the embodiment of the present application.
[0121] Table 1
[0122]
[0123] Through the technical solution provided in the embodiment of the present application, when the time to collision (TTC) reaches 2.1 seconds (s), the MPI caused by the merging scene is increased from 56.51km to 270.71km. At the same time, by adopting the technical solution provided in the embodiment of the present application, the takeover rate in the continuous merging scene is reduced by 11%, and the heavy braking rate (-2m / s 2 ) decreased by 31%, heavy braking rate (-3m / s 2 ) decreased by 7%. Both the takeover rate and heavy braking rate have been improved, thus enhancing the user's driving experience.
[0124] Fig. 9 The graphs show the change curves of the speed and acceleration of the intelligent driving device in different scenarios by using the technical solution of the embodiment of the present application and not using the technical solution of the embodiment of the present application.
[0125] like Fig. 9As shown in (a), taking the case where an obstacle on an urban road changes lanes from other lanes to the lane where the intelligent driving device is located as an example, curves 1 and 3 respectively represent the speed curve and acceleration curve of the intelligent driving device when the obstacle changes from other lanes to the lane where the intelligent driving device is located without using the technical solution provided by the embodiment of the present application. Curves 2 and 4 respectively represent the speed curve and acceleration curve of the intelligent driving device when the obstacle changes from other lanes to the lane where the intelligent driving device is located when using the technical solution provided by the embodiment of the present application.
[0126] like Fig. 9 As shown in (b), taking the case where an obstacle on a highway merges into the lane where the intelligent driving device is located as an example, curves 5 and 7 respectively represent the speed curve and acceleration curve of the intelligent driving device when the obstacle changes from other lanes to the lane where the intelligent driving device is located without using the technical solution provided by the embodiment of the present application. Curves 6 and 8 respectively represent the speed curve and acceleration curve of the intelligent driving device when the obstacle changes from other lanes to the lane where the intelligent driving device is located when using the technical solution provided by the embodiment of the present application.
[0127] It can be seen that by using the technical solution provided in the embodiment of the present application, when an obstacle merges into the lane where the intelligent driving device is located, the speed and acceleration of the intelligent driving device can be reduced in advance, thereby achieving risk reduction and smooth braking sensation.
[0128] Fig.10 FIG. 1 is a schematic block diagram of a control device 1000 provided in an embodiment of the present application. Fig.10 As shown, the device 1000 includes: an acquisition unit 1010, used to obtain the probability distribution of an obstacle merging into the lane where the intelligent driving device is located, and the probability distribution indicates the probability of the obstacle merging into the lane in the future; a determination unit 1020, used to determine the game result of the intelligent driving device on the obstacle according to the probability distribution; and a control unit 1030, used to control the intelligent driving device according to the probability distribution when the game result indicates that the intelligent driving device gives way to the obstacle.
[0129] Optionally, the determination unit 1020 is used to determine, based on the probability distribution, the constraints imposed by the obstacle on the intelligent driving device; and the control unit 1030 is used to control the intelligent driving device based on the constraints.
[0130] Optionally, the determination unit 1020 is used to: determine a first constraint imposed on the intelligent driving device by the obstacle when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold; or determine a second constraint imposed on the intelligent driving device by the obstacle when the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold; wherein the breakability of the first constraint is less than the breakability of the second constraint.
[0131] Optionally, the control unit 1030 is used to control the display device to display a curved red wall, where the curved red wall indicates the constraint.
[0132] Optionally, the acquisition unit 1010 is used to: obtain historical observations of the intelligent driving device and the obstacle, the historical observations including positions and orientation angles; determine a predicted trajectory of the obstacle based on the historical observations of the intelligent driving device and the obstacle; and determine the probability distribution based on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
[0133] Optionally, the determination unit 1020 is used to: perform a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; and determine the game result according to the cost evaluation result and the probability distribution.
[0134] Optionally, the cost evaluation result includes at least two cost evaluation results among a safety cost evaluation result, a passability cost evaluation result, a right of way evaluation result and a comfort evaluation result, and the determination unit 1020 is used to: determine the weight of each of the at least two cost evaluation results according to the probability distribution; determine the game result according to the weight of each of the at least two cost evaluation results and the at least two cost evaluation results.
[0135] For example, the acquisition unit 1010 may be Figure 1 The computing platform or the processing circuit, processor or controller in the computing platform. Taking the acquisition unit 1010 as the processor 151 in the computing platform as an example, the processor 151 can obtain the probability distribution of the obstacle merging into the lane where the intelligent driving device is located.
[0136] For another example, the determining unit 1020 may be Figure 1 The computing platform in the computing platform or the processing circuit, processor or controller in the computing platform. Taking the determination unit 1020 as the processor 152 in the computing platform as an example, the processor 152 can determine the game result of the intelligent driving device against the obstacle, or the game result of the obstacle against the intelligent driving device according to the probability distribution obtained by the processor 151.
[0137] For another example, the control unit 1030 may be Figure 1 The computing platform in the computing platform or the processing circuit, processor or controller in the computing platform. Taking the control unit 1030 as the processor 153 in the computing platform as an example, the processor 153 can control the intelligent driving device according to the game result determined by the processor 152 and the probability distribution obtained by the processor 151. For example, the display device can be controlled to display the curved red wall; or the lateral and / or longitudinal movement of the intelligent driving device can be controlled.
[0138] The functions implemented by the acquisition unit 1010, the functions implemented by the determination unit 1020, and the functions implemented by the control unit 1030 may be implemented by different processors, or may be implemented by the same processor, or some functions may be implemented by the same processor. This embodiment of the application does not limit this.
[0139] It should be understood that the division of the units in the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. In addition, the units in the device can be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the units of the device, wherein the processor is, for example, a general-purpose processor, such as a CPU or a microprocessor, and the memory is a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD. Taking FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through the configuration file, so as to realize the functions of some or all of the above units. All units of the above device may be implemented entirely in the form of a processor calling software, or entirely in the form of a hardware circuit, or partially in the form of a processor calling software and the rest in the form of a hardware circuit.
[0140] Each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
[0141] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of SoC. The SoC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.
[0142] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps executed by the above embodiment.
[0143] Alternatively, if the device is located in a vehicle, the processing unit may be Figure 1 Processors 151-15n are shown.
[0144] An embodiment of the present application also provides a control system, which includes one or more sensors and a computing platform, wherein the computing platform includes the above-mentioned device 1000.
[0145] Exemplarily, the one or more sensors may be located in a vehicle, and the computing platform may be located in a cloud server or in the vehicle.
[0146] An embodiment of the present application also provides an intelligent driving device, which may include the above-mentioned device 1000 or the above-mentioned system.
[0147] Exemplarily, the intelligent driving device may be a vehicle.
[0148] The embodiment of the present application further provides a server, which may include the above-mentioned device 1000 or the above-mentioned system.
[0149] The embodiment of the present application further provides a computer program product, which includes: a computer program code, and when the computer program code is executed on a computer, the computer executes the above method.
[0150] The embodiment of the present application further provides a computer-readable medium, wherein the computer-readable medium stores a program code. When the computer program code is executed on a computer, the computer executes the above method.
[0151] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.
[0152] It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.
[0153] It should also be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0154] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0155] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0156] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0158] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0159] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0160] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered. Within the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A control method, characterized in that: include: Obtaining a probability distribution of an obstacle merging into a lane where the intelligent driving device is located, wherein the probability distribution indicates a probability of the obstacle merging into the lane within a future period of time; Determining, according to the probability distribution, a gaming result of the intelligent driving device on the obstacle; When the game result indicates that the intelligent driving device gives way to the obstacle, the intelligent driving device is controlled according to the probability distribution.
2. The method according to claim 1, characterized in that The controlling the intelligent driving device according to the probability distribution includes: Determining, according to the probability distribution, constraints imposed by the obstacle on the intelligent driving device; The intelligent driving device is controlled according to the constraint.
3. The method according to claim 2, characterized in that The determining, according to the probability distribution, the constraint imposed by the obstacle on the intelligent driving device includes: When the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold, determining a first constraint generated by the obstacle on the intelligent driving device; or, When the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold, determining a second constraint generated by the obstacle on the intelligent driving device; The breakability of the first constraint is less than the breakability of the second constraint.
4. The method according to claim 2 or 3, characterized in that: The controlling the intelligent driving device according to the probability distribution includes: The display device is controlled to display a curved red wall, wherein the curved red wall indicates the constraint.
5. The method according to any one of claims 1 to 4, characterized in that The obtaining of the probability distribution of the obstacle merging into the lane where the intelligent driving device is located includes: Acquire historical observations of the intelligent driving device and the obstacle, wherein the historical observations include positions and orientation angles; Determining a predicted trajectory of the obstacle based on the intelligent driving device and the historical observations of the obstacle; The probability distribution is determined according to the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
6. The method according to claim 5, characterized in that The determining, according to the probability distribution, a gaming result of the intelligent driving device on the obstacle includes: Performing a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; The game result is determined according to the cost evaluation result and the probability distribution.
7. The method according to claim 6, characterized in that The cost evaluation result includes at least two cost evaluation results of a safety cost evaluation result, a trafficability cost evaluation result, a road right evaluation result, and a comfort evaluation result. The determining of the game result according to the cost evaluation results and the probability distribution includes: Determining a weight of each of the at least two cost evaluation results according to the probability distribution; The game result is determined according to the weight of each of the at least two cost evaluation results and the at least two cost evaluation results.
8. A control device, characterized in that: include: An acquisition unit, used to acquire a probability distribution of an obstacle merging into a lane where the intelligent driving device is located, wherein the probability distribution indicates a probability of the obstacle merging into the lane within a future period of time; A determination unit, configured to determine a gaming result of the intelligent driving device on the obstacle according to the probability distribution; A control unit is used to control the intelligent driving device according to the probability distribution when the game result indicates that the intelligent driving device gives way to the obstacle.
9. The device according to claim 8, characterized in that The determining unit is used to: determine the constraint imposed by the obstacle on the intelligent driving device according to the probability distribution; The control unit is used to control the intelligent driving device according to the constraint.
10. The device according to claim 9, characterized in that The determining unit is used for: When the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is greater than or equal to a preset threshold, determining a first constraint generated by the obstacle on the intelligent driving device; or, When the probability distribution indicates that the probability of the obstacle merging into the lane at the first moment is less than the preset threshold, determining a second constraint generated by the obstacle on the intelligent driving device; The breakability of the first constraint is less than the breakability of the second constraint.
11. The device according to claim 9 or 10, characterized in that The control unit is used for: The display device is controlled to display a curved red wall, wherein the curved red wall indicates the constraint.
12. The device according to any one of claims 8 to 11, characterized in that The acquisition unit is used to: Acquire historical observations of the intelligent driving device and the obstacle, wherein the historical observations include positions and orientation angles; Determining a predicted trajectory of the obstacle based on the intelligent driving device and the historical observations of the obstacle; The probability distribution is determined according to the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle.
13. The device according to claim 12, characterized in that The determining unit is used for: Performing a cost evaluation on the planned trajectory of the intelligent driving device and the predicted trajectory of the obstacle to obtain a cost evaluation result; The game result is determined according to the cost evaluation result and the probability distribution.
14. The device according to claim 13, characterized in that The cost evaluation result includes at least two cost evaluation results of a safety cost evaluation result, a trafficability cost evaluation result, a road right evaluation result, and a comfort evaluation result. The determining unit is used to: Determining a weight of each of the at least two cost evaluation results according to the probability distribution; The game result is determined according to the weight of each of the at least two cost evaluation results and the at least two cost evaluation results.
15. A control device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 7.
16. A control system, characterized in that: The device comprises a sensor and a computing platform, wherein the computing platform comprises a control device as claimed in any one of claims 8 to 15.
17. An intelligent driving device, characterized in that: The method comprises a control device as claimed in any one of claims 8 to 15, or a control system as claimed in claim 16.
18. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a computer, the method according to any one of claims 1 to 7 is implemented.
19. A chip, characterized in that: include: A circuit for executing the method according to any one of claims 1 to 7.