Data generation method, device, computer equipment and storage medium

Abstract

The present invention relates to a data generation method, apparatus, computer equipment, and storage medium. The method comprises: obtaining scene data of a target scene, wherein the target scene includes a vehicle and multiple traffic participants surrounding the vehicle; determining the attention level of each traffic participant based on the scene data; for each target traffic participant, when the attention level of the target traffic participant is greater than an attention level threshold, generating first simulated behavior data of the target traffic participant for the target scene using a first simulated behavior model for the target scene; and when the attention level of the target traffic participant is not greater than the attention level threshold, generating second simulated behavior data of the target traffic participant for the target scene using a second simulated behavior model for the target scene, wherein the first simulated behavior data represents a higher degree of anthropomorphism of the simulated behavior in the target scene than the second simulated behavior data represents a higher degree of anthropomorphism of the simulated behavior in the target scene.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a data generation method, device, computer equipment and storage medium. Background Art

[0002] Constructing anthropomorphic traffic flows for the corresponding scenarios is a core component of simulation testing of the performance of algorithms running on vehicles in the corresponding scenarios. Simulating the behavior of traffic participants in the corresponding scenarios is a core component of constructing anthropomorphic traffic flows for the corresponding scenarios. The simulated behavior of traffic participants in the corresponding scenarios is represented by simulated behavior data. Simulating the behavior of traffic participants in the corresponding scenarios actually involves generating simulated behavior data that represents the simulated behavior of traffic participants in the corresponding scenarios.

[0003] In related technologies, the same simulated behavior model is used to generate simulated behavior data for each traffic participant in the corresponding scenario, resulting in high costs for constructing anthropomorphic traffic flows. How to avoid the high costs of constructing anthropomorphic traffic flows for corresponding scenarios has become a problem that needs to be solved. Summary of the Invention

[0004] One of the purposes of the present invention is to provide a data generation method, apparatus, computer device and storage medium to solve the problem of how to avoid the high cost of constructing anthropomorphic traffic flow of corresponding scenes.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A data generation method, comprising:

[0007] Acquire scene data of a target scene, wherein the target scene includes a self-vehicle and a plurality of traffic participants around the self-vehicle;

[0008] determining, based on the scene data, a degree of attention of each of the plurality of traffic participants, and determining a target traffic participant among the plurality of traffic participants;

[0009] For each target traffic participant, when the target traffic participant's attention is greater than the attention threshold, a first simulated behavior model for the target scene is used to generate first simulated behavior data of the target traffic participant for the target scene; when the target traffic participant's attention is not greater than the attention threshold, a second simulated behavior model for the target scene is used to generate second simulated behavior data of the target traffic participant for the target scene, wherein the degree of anthropomorphism of the simulated behavior in the target scene represented by the first simulated behavior data is higher than the degree of anthropomorphism of the simulated behavior in the target scene represented by the second simulated behavior data.

[0010] According to the above technical means, the attention level of a traffic participant is related to the strength of the interaction between the traffic participant and the vehicle in the target scenario. When the attention level of a target traffic participant is greater than the attention level threshold, it reflects that the interaction between the target traffic participant and the vehicle in the target scenario is strong. A first simulated behavior model for the target scenario that simulates the traffic participant's behavior in the target scenario with a relatively high degree of anthropomorphism is used to generate first simulated behavior data for the target traffic participant in the target scenario. When the attention level of a target traffic participant is not greater than the attention level threshold, it reflects that the interaction between the target traffic participant and the vehicle in the target scenario is weak. A second simulated behavior model that simulates the traffic participant's behavior in the target scenario with a relatively low degree of anthropomorphism is used to generate second simulated behavior data for the target traffic participant in the target scenario.

[0011] Thus, for target traffic participants with strong interactions with the ego vehicle in the target scenario, the behavior of target traffic participants with strong interactions with the ego vehicle in the target scenario is simulated using a first simulated behavior model for the target scenario with a relatively high degree of anthropomorphism of the simulated traffic participants' behavior in the target scenario. For target traffic participants with weak interactions with the ego vehicle in the target scenario, the behavior of target traffic participants with weak interactions with the ego vehicle in the target scenario is simulated using a second simulated behavior model for the target scenario with a relatively low degree of anthropomorphism of the simulated traffic participants' behavior in the target scenario.

[0012] Compared to simulating the behavior of traffic participants in the corresponding scenario using a simulated behavior model for the corresponding scenario with a high degree of anthropomorphism for each traffic participant in the corresponding scenario, the cost of constructing an anthropomorphic traffic flow for the corresponding scenario is low. At the same time, compared to simulating the behavior of traffic participants in the corresponding scenario using a simulated behavior model for the corresponding scenario with a low degree of anthropomorphism for each traffic participant in the corresponding scenario, the realism of the constructed anthropomorphic traffic flow for the corresponding scenario is high. Thus, both the cost of constructing the anthropomorphic traffic flow for the corresponding scenario and the realism of the constructed anthropomorphic traffic flow for the corresponding scenario are taken into account. This avoids the problem of high cost of constructing the anthropomorphic traffic flow for the corresponding scenario and low realism of the constructed anthropomorphic traffic flow for the corresponding scenario.

[0013] Further, determining the attention level of each of the plurality of traffic participants according to the scene data includes:

[0014] For each traffic participant, the position importance of the traffic participant's position and the type importance of the traffic participant's type are determined based on the scene data, and the importance parameter of the traffic participant is determined based on the position importance and the type importance, and the attention level of the traffic participant is determined based on the importance parameter of the traffic participant.

[0015] Furthermore, determining the attention level of the traffic participant according to the importance parameter of the traffic participant includes:

[0016] determining a right-of-way parameter of the traffic participant according to whether the traffic participant is in a target lane of the ego vehicle, wherein the target lane of the ego vehicle is indicated by the scenario data;

[0017] The attention level of the traffic participant is determined according to the importance parameter and the road right parameter of the traffic participant.

[0018] Furthermore, determining the attention level of the traffic participant according to the importance parameter and the right-of-way parameter of the traffic participant includes:

[0019] When the traffic participant is a vehicle, determining the risk parameter of the traffic participant according to associated parameter information used to determine the risk parameter of the traffic participant, the associated parameter information including: a relative distance between the vehicle and the traffic participant, a speed of the vehicle, and a speed of the traffic participant, wherein the associated parameter information is indicated by the scenario data;

[0020] The attention level of the traffic participant is determined according to the importance parameter of the traffic participant, the road right parameter of the traffic participant and the risk parameter of the traffic participant.

[0021] Further, determining the risk parameter of the traffic participant according to the associated parameter information used to determine the risk parameter of the traffic participant includes:

[0022] Acquiring spring damping model parameters for the traffic participant, the spring damping model parameters including: a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant;

[0023] Calculating a longitudinal risk value of the traffic participant relative to the own vehicle and a lateral risk value of the traffic participant relative to the own vehicle based on the spring-damping model parameters for the traffic participant and the associated parameter information for determining the risk parameter of the traffic participant;

[0024] The risk parameter of the traffic participant is determined according to the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle.

[0025] Furthermore, determining the attention level of the traffic participant according to the importance parameter of the traffic participant, the right-of-way parameter of the traffic participant, and the risk parameter of the traffic participant includes:

[0026] The weighted sum of the importance parameter of the traffic participant, the road right parameter of the traffic participant and the risk parameter of the traffic participant is determined as the attention degree of the traffic participant.

[0027] Furthermore, determining the target traffic participant among the multiple traffic participants includes:

[0028] sorting the attention levels of the multiple traffic participants according to the attention levels of the traffic participants from greatest to least;

[0029] The first preset number of traffic participants among the multiple traffic participants are respectively determined as target traffic participants.

[0030] Furthermore, the target scene is any one of the multiple scenes; and before obtaining the scene data of the target scene, the method further includes:

[0031] The label information of the plurality of scene data is clustered to determine the plurality of scenes and the scene to which each scene data in the plurality of scene data belongs.

[0032] A data generating device, comprising:

[0033] an acquisition unit, configured to acquire scene data of a target scene, wherein the target scene includes a vehicle and a plurality of traffic participants around the vehicle;

[0034] a determining unit, configured to determine the attention level of each of the plurality of traffic participants and determine a target traffic participant among the plurality of traffic participants based on the scene data;

[0035] A generation unit is used to, for each target traffic participant, when the target traffic participant's attention is greater than an attention threshold, generate first simulated behavior data of the target traffic participant for the target scene by using a first simulated behavior model for the target scene; when the target traffic participant's attention is not greater than the attention threshold, generate second simulated behavior data of the target traffic participant for the target scene by using a second simulated behavior model for the target scene, wherein the degree of anthropomorphism of the simulated behavior in the target scene represented by the first simulated behavior data is higher than the degree of anthropomorphism of the simulated behavior in the target scene represented by the second simulated behavior data.

[0036] Furthermore, the determination unit is further used to determine, for each traffic participant, the position importance of the traffic participant's position and the type importance of the traffic participant's type based on the scene data, and to determine the importance parameter of the traffic participant based on the position importance and the type importance, and to determine the attention level of the traffic participant based on the importance parameter of the traffic participant.

[0037] Furthermore, the determination unit is further used to determine the right-of-way parameter of the traffic participant based on whether the traffic participant is in the target lane of the own vehicle, wherein the target lane of the own vehicle is indicated by the scene data; and determine the attention level of the traffic participant based on the importance parameter and right-of-way parameter of the traffic participant.

[0038] Furthermore, the determination unit is further used to determine the risk parameters of the traffic participant when the traffic participant is a vehicle based on associated parameter information used to determine the risk parameters of the traffic participant, the associated parameter information including: the relative distance between the vehicle and the traffic participant, the speed of the vehicle, and the speed of the traffic participant, wherein the associated parameter information is indicated by the scene data; and determine the attention level of the traffic participant based on the importance parameter of the traffic participant, the right of way parameter of the traffic participant and the risk parameter of the traffic participant.

[0039] Furthermore, the determination unit is further used to obtain spring damping model parameters for the traffic participant, and the spring damping model parameters include: a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant; based on the spring damping model parameters for the traffic participant and the associated parameter information for determining the risk parameters of the traffic participant, the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle are calculated; based on the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle, the risk parameters of the traffic participant are determined.

[0040] Furthermore, the determination unit is further configured to determine the attention level of the traffic participant by taking a weighted sum of the importance parameter of the traffic participant, the road right parameter of the traffic participant, and the risk parameter of the traffic participant.

[0041] Furthermore, the determination unit is further configured to sort the attention levels of the multiple traffic participants from large to small according to the attention levels of the traffic participants; and determine the first preset number of traffic participants among the multiple traffic participants as target traffic participants.

[0042] Furthermore, the target scene is any one of the multiple scenes; the data generating device further includes:

[0043] The clustering unit is configured to cluster the label information of the plurality of scene data before acquiring the scene data of the target scene, so as to determine the plurality of scenes and the scene to which each of the plurality of scene data belongs.

[0044] A computer device comprising:

[0045] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above method by executing the computer instructions.

[0046] A computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the above method.

[0047] A computer program product, characterized in that it includes computer instructions, wherein the computer instructions are used to enable a computer to execute the above method.

[0048] Beneficial effects of the present invention:

[0049] The traffic participant's attention is related to the strength of the interaction between the traffic participant and the vehicle in the target scenario. When the target traffic participant's attention is greater than the attention threshold, it reflects that the target traffic participant has a strong interaction with the vehicle in the target scenario. A first simulated behavior model for the target scenario that simulates the traffic participant's behavior in the target scenario with a relatively high degree of anthropomorphism is used to generate first simulated behavior data for the target traffic participant in the target scenario. When the target traffic participant's attention is less than the attention threshold, it reflects that the target traffic participant has a weak interaction with the vehicle in the target scenario. A second simulated behavior model that simulates the traffic participant's behavior in the target scenario with a relatively low degree of anthropomorphism is used to generate second simulated behavior data for the target traffic participant in the target scenario.

[0050] Thus, for target traffic participants with strong interactions with the ego vehicle in the target scenario, the behavior of target traffic participants with strong interactions with the ego vehicle in the target scenario is simulated using a first simulated behavior model for the target scenario with a relatively high degree of anthropomorphism of the simulated traffic participants' behavior in the target scenario. For target traffic participants with weak interactions with the ego vehicle in the target scenario, the behavior of target traffic participants with weak interactions with the ego vehicle in the target scenario is simulated using a second simulated behavior model for the target scenario with a relatively low degree of anthropomorphism of the simulated traffic participants' behavior in the target scenario.

[0051] Compared to simulating the behavior of traffic participants in the corresponding scenario using a simulated behavior model for the corresponding scenario with a high degree of anthropomorphism for each traffic participant in the corresponding scenario, the cost of constructing an anthropomorphic traffic flow for the corresponding scenario is low. At the same time, compared to simulating the behavior of traffic participants in the corresponding scenario using a simulated behavior model for the corresponding scenario with a low degree of anthropomorphism for each traffic participant in the corresponding scenario, the realism of the constructed anthropomorphic traffic flow for the corresponding scenario is high. Thus, both the cost of constructing the anthropomorphic traffic flow for the corresponding scenario and the realism of the constructed anthropomorphic traffic flow for the corresponding scenario are taken into account. This avoids the problem of high cost of constructing the anthropomorphic traffic flow for the corresponding scenario and low realism of the constructed anthropomorphic traffic flow for the corresponding scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of an example of simulating the behavior of traffic participants using a first simulation behavior model and a second simulation behavior model;

[0053] Figure 2 A schematic diagram of a flow chart of a data generation method provided in an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of an example of a preset position for calculating the position importance of a traffic participant;

[0055] Figure 4 A schematic flow chart of another data generation method provided by an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0058] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0059] refer to Figure 1 , which shows a schematic diagram of an example of simulating the behavior of traffic participants using the first simulation behavior model and the second simulation behavior model.

[0060] In this example, in order to construct an anthropomorphic traffic flow of a target scene, scene data of the target scene is acquired.

[0061] Figure 1 Two target traffic participants, namely traffic participant 1 and traffic participant 2, are shown among all target traffic participants around the vehicle. Both traffic participant 1 and traffic participant 2 are vehicles.

[0062] All target traffic participants around the ego vehicle are indicated by scene data of a target scene. As an example, the target scene is one of a dangerous cut-in scene, an intersection scene, a ramp scene, and an obstacle avoidance scene.

[0063] If the attention level of the traffic participant 1 is greater than the attention level threshold, the simulated behavior data 1 of the traffic participant 1 for the target scenario is generated using the first simulated behavior model for the target scenario.

[0064] If the attention level of the traffic participant 1 is not greater than the attention level threshold, the simulated behavior data 2 of the traffic participant 1 for the target scenario are generated using the second simulated behavior model for the target scenario.

[0065] The first simulated behavior model for the target scenario can be a model based on machine learning methods. The second simulated behavior model for the target scenario can be a classic driving behavior model such as the IDM model or the Gipps model. The first simulated behavior model for the target scenario consumes more resources than the second simulated behavior model for the target scenario.

[0066] The simulated behavior data 1 of the traffic participant 1 for the target scenario represents the simulated behavior 1 of the traffic participant 1 in the target scenario. The simulated behavior data 2 of the traffic participant 1 for the target scenario represents the simulated behavior 2 of the traffic participant 1 in the target scenario.

[0067] The anthropomorphism degree of the simulated behavior 1 of the traffic participant 1 for the target scenario is higher than the anthropomorphism degree of the simulated behavior 2 of the traffic participant 1 in the target scenario.

[0068] If the attention level of the traffic participant 2 is greater than the attention level threshold, the simulated behavior data 3 of the traffic participant 2 for the target scenario are generated using the first simulated behavior model for the target scenario.

[0069] If the attention level of the traffic participant 2 is not greater than the attention level threshold, the second simulated behavior model for the target scenario is used to generate simulated behavior data 4 of the traffic participant 2 for the target scenario.

[0070] The simulated behavior data 3 of the traffic participant 2 for the target scenario represent the simulated behavior 3 of the traffic participant 2 in the target scenario. The simulated behavior data 4 of the traffic participant 2 for the target scenario represent the simulated behavior 4 of the traffic participant 2 in the target scenario.

[0071] The anthropomorphism degree of the simulated behavior 3 of the traffic participant 2 in the target scenario is higher than the anthropomorphism degree of the simulated behavior 4 of the traffic participant 2 in the target scenario.

[0072] refer to Figure 2 , which shows a flow chart of a data generation method provided by an embodiment of the present invention. This method is executed during the construction of an anthropomorphic traffic flow for a target scenario. The anthropomorphic traffic flow for the target scenario is used to test the performance of algorithms running on the ego vehicle, such as autonomous driving algorithms running on the ego vehicle, in the target scenario.

[0073] In step S201, scene data of a target scene is acquired.

[0074] The target scene includes the vehicle and multiple traffic participants around the vehicle. The vehicle and multiple traffic participants around the vehicle in the target scene are indicated by scene data of the target scene.

[0075] The ego vehicle can be understood as a vehicle that runs the algorithm that needs to be tested for its performance in the target scenario.

[0076] For each of the multiple traffic participants around the vehicle, the traffic participant type of the traffic participant is one of multiple traffic participant types. As an example, the multiple traffic participant types include: people, vehicles, and other traffic participant types.

[0077] The type of the target scene is any one of multiple scene types.

[0078] In one possible implementation, the multiple scene types include, but are not limited to: dangerous entry scene type, intersection scene type, ramp scene type, obstacle avoidance scene type, etc.

[0079] It should be noted that the scene data of the target scene is collected by a vehicle used to collect the target scene data when the vehicle used to collect the target scene data is in the target scene.

[0080] In one possible implementation, the vehicle used to collect scene data is the vehicle itself or another vehicle.

[0081] The scene data of the target scene includes, but is not limited to: data of the vehicle for the target scene, and data of traffic participants around the vehicle for the target scene.

[0082] The data of the vehicle for the target scene includes but is not limited to: the position of the vehicle, the speed of the vehicle, etc.

[0083] The data of the traffic participants around the vehicle for the target scene include but are not limited to: the position of the traffic participants around the vehicle, the speed of the traffic participants around the vehicle, the traffic participant type of the traffic participants around the vehicle, etc.

[0084] It should be noted that the ego vehicle in the target scene, the position of the ego vehicle in the target scene, all traffic participants in the target scene, and the positions of all traffic participants in the target scene are indicated by the data of the target scene.

[0085] In a possible implementation, for a traffic participant in the target scene, if the distance between the position of the traffic participant and the position of the ego vehicle is less than a distance threshold, the traffic participant may be determined as a traffic participant around the ego vehicle.

[0086] In another possible implementation, if a traffic participant in the target scene is located within a predetermined area centered on the ego vehicle, the participant can be identified as one of the traffic participants surrounding the ego vehicle. For example, the predetermined shape is a square or rectangle with predetermined side lengths in all directions.

[0087] In step S202 , based on the scene data of the target scene, the attention level of each of the multiple traffic participants around the vehicle is determined, and the target traffic participant among the multiple traffic participants around the vehicle is determined.

[0088] In one possible implementation, to determine the attention level of each of the multiple traffic participants surrounding the ego vehicle, the ego vehicle's position and the positions of the multiple traffic participants surrounding the ego vehicle are obtained from scene data of the target scene. For each of the multiple traffic participants surrounding the ego vehicle, the positional importance of the traffic participant is determined based on the ego vehicle's position and the position of the traffic participant, and the positional importance of the traffic participant is used as the attention level of the traffic participant.

[0089] As an example, the distance between each of the multiple traffic participants surrounding the vehicle and the vehicle is determined. For each of the multiple traffic participants surrounding the vehicle, the distance between the traffic participant and the vehicle is determined within a preset distance interval among multiple preset distance intervals, and the importance of the preset distance interval is determined as the location importance of the traffic participant. The right endpoint value of the i-th preset distance interval is the left endpoint value of the (i+1)th preset distance interval, and the i-th distance interval is the distance interval other than the distance interval with the largest left endpoint value. The importance of each preset distance interval can be preset. The smaller the left endpoint value of the preset distance interval, the greater the importance of the preset distance interval. The larger the left endpoint value of the preset distance interval, the lower the importance of the preset distance interval.

[0090] As another example, for each of multiple preset locations, the location importance of the traffic participant closest to the vehicle at the preset location among multiple traffic participants surrounding the vehicle is the location importance of that location. The location importances of the other traffic participants, other than the traffic participant with the preset location importance, are the other location importances. The location importance of any one of the preset locations is greater than the location importances of the other locations.

[0091] As an example, the plurality of preset directions include: directly in front, left front, right front, left side, right side, directly behind, left rear, and right rear.

[0092] refer to Figure 3 , which shows a schematic diagram of an example of preset positions for calculating the position importance of traffic participants.

[0093] In this example, there are nine preset directions, represented by 1, 2, 3, 4, 5, 6, 7, and 8. 1, 4, and 7 represent: front, left, and right, respectively. 3, 6, 5, 2, and 8 represent: left front, right front left rear, rear, and right rear, respectively.

[0094] As an example, for each of the preset directions (directly in front, left, and right), the position importance of the traffic participant closest to the vehicle at that location among the multiple traffic participants surrounding the vehicle is 1. For each of the preset directions (left front, right front left rear, directly rear, and right rear), the position importance of the traffic participant closest to the vehicle at that location among the multiple traffic participants surrounding the vehicle is 0.5. The position importance of the traffic participants other than those with preset direction importance among the multiple traffic participants surrounding the vehicle is 0.1.

[0095] In another possible implementation, to determine the attention level of each of the multiple traffic participants surrounding the vehicle, the traffic participant type of each of the multiple traffic participants surrounding the vehicle can be obtained from the scene data of the target scene. For each of the multiple traffic participants surrounding the vehicle, the type importance of the traffic participant type is determined, and the type importance of the traffic participant type is used as the attention level of the traffic participant. The type importance of each of the multiple traffic participant types can be preset. As an example, the type importance of people and cyclists is 1, the type importance of small vehicles is 0.8, and the type importance of large vehicles is 0.5.

[0096] In one possible implementation, to identify target traffic participants among multiple traffic participants surrounding the vehicle, the traffic participants surrounding the vehicle can be ranked from highest to lowest in terms of their attention. After ranking, each traffic participant surrounding the vehicle is assigned a position, with the higher the attention level, the closer the position is to the front of the vehicle. After ranking, the first predetermined number of traffic participants among the multiple traffic participants can be identified as target traffic participants.

[0097] In another possible implementation, each of the multiple traffic participants around the vehicle may be determined as a target traffic participant.

[0098] In another possible implementation, to determine a target traffic participant among multiple traffic participants surrounding the vehicle, a traffic participant that meets a preset condition can be determined as the target traffic participant. The preset condition is that the traffic participant's traffic participant type is used to determine whether the traffic participant is the target traffic participant. The traffic participant type used to determine whether the traffic participant is the target traffic participant is preset.

[0099] In step S203, for each target traffic participant among the multiple traffic participants around the vehicle, when the attention level of the target traffic participant is greater than the attention level threshold, the first simulated behavior model for the target scene is used to generate first simulated behavior data of the target traffic participant for the target scene; when the attention level of the target traffic participant is not greater than the attention level threshold, the second simulated behavior model for the target scene is used to generate second simulated behavior data of the target traffic participant for the target scene.

[0100] As an example, the attention threshold is 0.8.

[0101] For a target traffic participant around the vehicle, the anthropomorphic degree of the simulated behavior represented by the first simulated behavior data of the target traffic participant for the target scene is higher than the anthropomorphic degree of the simulated behavior represented by the second simulated behavior data of the target traffic participant for the target scene.

[0102] It should be noted that the degree of anthropomorphism of the simulated behavior represented by the simulated behavior data generated by the simulated behavior model is directly proportional to the amount of resources consumed by the simulated behavior model. The higher the degree of anthropomorphism of the simulated behavior represented by the simulated behavior data generated by the simulated behavior model, the more resources the simulated behavior model consumes. The lower the degree of anthropomorphism of the simulated behavior represented by the simulated behavior data generated by the simulated behavior model, the fewer resources the simulated behavior model consumes.

[0103] For a target traffic participant around the vehicle, the simulated behavior represented by the first simulated behavior data of the target traffic participant for the target scene specifically refers to: the simulated behavior of the target traffic participant in the target scene represented by the first simulated behavior data of the target traffic participant for the target scene.

[0104] For a target traffic participant around the vehicle, the simulated behavior represented by the second simulated behavior data of the target traffic participant for the target scene specifically refers to: the simulated behavior of the target traffic participant in the target scene represented by the second simulated behavior data of the target traffic participant for the target scene.

[0105] It should be noted that the degree of anthropomorphism of the target traffic participant's simulated behavior in the target scenario can be understood as the degree to which the target traffic participant's simulated behavior in the target scenario approximates one of the following behaviors: a behavior performed by the traffic participant in the target scenario, or a behavior performed by the traffic participant that corresponds to an operation performed by the person operating the traffic participant on the traffic participant. The behavior that corresponds to an operation performed by the person operating the traffic participant on the traffic participant is caused by the operation performed by the person operating the traffic participant on the traffic participant in the target scenario.

[0106] As an example, the degree of anthropomorphism of the simulated behavior of a person in a target scene in the target scene can be understood as the degree to which the simulated behavior of the person in the target scene approximates the behavior of the person in the target scene. The degree of anthropomorphism of the simulated behavior of a vehicle in the target scene in the target scene can be understood as the degree to which the simulated behavior of the vehicle in the target scene approximates the behavior of the vehicle corresponding to the driving operation of the vehicle by the person in the target scene.

[0107] In one possible implementation, the first simulated behavior model for the target scenario is a model based on a machine learning method, for example, a model based on transfer learning, deep learning, or adversarial learning. The second simulated behavior model for the target scenario is a classic driving behavior model. The first simulated behavior model for the target scenario consumes more resources than the second simulated behavior model for the target scenario.

[0108] As an example, the first simulated behavior model for the target scenario is a behavior model for simulating traffic participants based on reinforcement learning. The traffic participants around the vehicle are treated as a single agent. The single agent learns and makes decisions in the environment, and the interaction between the single agent and the environment follows a Markov decision process.

[0109] The interaction between a single agent and the environment is represented by a multi-tuple<S,A,R,f,γ> where S and A represent the agent's state and action space, respectively, and f represents the agent's state transition function, which determines the probability distribution of transitioning from state s to s' given an action a. R is the reward function, which defines the instantaneous reward the environment receives when the agent transitions from state s to state s' through action a. From the start time t to the end of the interaction at time T, the total reward of the environment can be expressed as:

[0110]

[0111] Where γ∈[0,1] is the discount factor, which is used to balance the impact of the agent's instantaneous return and long-term return on the total return. The agent's learning strategy can be expressed as a state-to-action mapping π:S→A. The goal of solving the MDP is to find the optimal strategy π with the maximum expected return value. * , the expected return is generally formalized using the optimal state action value function (Q function)

[0112]

[0113] Optimal strategy π * The optimal behavior of the agent, such as optimal driving behavior.

[0114] As an example, the second simulation behavior model for the target scenario is a cosine lane-changing model, an intelligent driving model (IDM), and a John Gipps (Gipps) model.

[0115] One of the classic driving behavior models such as the Gipps model. The cosine lane-changing model can be expressed as:

[0116]

[0117] Among them, a y represents the lateral acceleration of the vehicle, the distance between the center lines of the two lanes is d, the longitudinal displacement generated by the lane changing process is L, and x represents the longitudinal position of the vehicle.

[0118] refer to Figure 4 , which shows a flow chart of another data generation method provided by an embodiment of the present invention.

[0119] In step S401 , the tag information of a plurality of scene data is clustered to determine a plurality of scenes and the scene to which each scene data belongs.

[0120] By clustering the label information of multiple scene data, multiple clustering results can be obtained.

[0121] Each clustering result includes at least one scene data and corresponds to a different scene.

[0122] For a clustering result, each scene data belonging to the clustering result belongs to the scene corresponding to the clustering result.

[0123] For a piece of scene data, the label information of the scene data may include: a general class label of the scene data, a traffic participant information label of the scene data, and a traffic class label of the scene data.

[0124] General class labels for scene data include: the time of scene data collection, the location of scene data collection, the road type of the road in the scene where the vehicle was used to collect the scene data, the road characteristics of the road in the scene where the vehicle was used to collect the scene data, the weather in the environment where the vehicle was used to collect the scene data, and the lighting in the environment where the vehicle was used to collect the scene data. Traffic participant labels for scene data include: the type of traffic participant in the scene where the vehicle was used to collect the scene data, the motion state of the traffic participant in the scene where the vehicle was used to collect the scene data, the behavioral intention of the traffic participant in the scene where the vehicle was used to collect the scene data, and the initial direction of the traffic participant in the scene where the vehicle was used to collect the scene data. Traffic class labels for scene data include: the degree of traffic congestion at the time of scene data collection, the status of the traffic lights in the scene where the vehicle was used to collect the scene data, and the signs and markings in the scene where the vehicle was used to collect the scene data.

[0125] Table 1 is an example of general class labels for scene data, Table 2 is an example of traffic participant information labels for scene data, and Table 3 is an example of a traffic class label table for scene data.

[0126] Table 1

[0127]

[0128]

[0129] Table 2

[0130]

[0131] Table 3

[0132]

[0133]

[0134] In a possible implementation, a nonlinear clustering algorithm may be used to cluster the label information of multiple scene data to determine multiple scenes and the scene to which each scene data belongs.

[0135] As an example, considering that there are many parameters and the parameters have nonlinear and non-explicit coupling relationships, a Gaussian mixture model with good fitting ability is used to cluster the label information of multiple scene data. The Gaussian mixture model can be expressed as:

[0136]

[0137] Among them, f(x GMM ; Θ) represents the Gaussian mixture model, Θ=[K,ω k ,θ k ], K represents the number of Gaussian kernels in the Gaussian mixture model, that is, how many classes the label information of the scene data can be divided into; ω k Represents the weight of the kth Gaussian component in the total model, and the sum of all weights is 1, that is, θ k =[μ k ,∑ k ], represents the mean matrix and variance matrix corresponding to the kth component. The input of the Gaussian mixture model is the label information of multiple scene data.

[0138] In step S402 , based on the scene data of the target scene, the attention level of each of the multiple traffic participants around the vehicle is determined, and the target traffic participant among the multiple traffic participants around the vehicle is determined.

[0139] Step S402 refers to step S201.

[0140] In step S403, for each of the multiple traffic participants around the own vehicle, the position importance of the traffic participant's position and the type importance of the traffic participant's traffic participant type are determined based on the scene data of the target scene, and the importance parameter of the traffic participant is determined based on the position importance of the traffic participant's position and the type importance of the traffic participant's traffic participant type, and the attention level of the traffic participant is determined based on the importance parameter of the traffic participant.

[0141] For a traffic participant around the vehicle, the method of determining the position importance of the position of the traffic participant and the type importance of the traffic participant type of the traffic participant is as described in step S202 .

[0142] In one possible implementation, for a traffic participant around the vehicle, determining the importance parameter of the traffic participant based on the position importance of the traffic participant's position and the type importance of the traffic participant type of the traffic participant includes: taking the product of the position importance of the traffic participant's position and the type importance of the traffic participant type of the traffic participant as the importance parameter of the traffic participant.

[0143] In a possible implementation, for a traffic participant among multiple traffic participants around the vehicle, the importance parameter of the traffic participant may be used to determine the attention level of the traffic participant.

[0144] In this embodiment of the present invention, when determining a traffic participant's importance parameter, the influence of the location importance of the traffic participant's position and the type importance of the traffic participant's type on the traffic participant's importance can be simultaneously considered. This improves the accuracy of the traffic participant's importance parameter and the accuracy of the traffic participant's attention.

[0145] In a possible implementation, step S403 includes: step S4031.

[0146] In step S4031, for a traffic participant among multiple traffic participants around the vehicle, the right-of-way parameter of the traffic participant is determined based on whether the traffic participant is in the target lane of the vehicle; and the attention level of the traffic participant is determined based on the importance parameter of the traffic participant and the right-of-way parameter of the traffic participant.

[0147] The right-of-way parameter of the traffic participant when the traffic participant is in the target lane where the vehicle is located is greater than the right-of-way parameter of the traffic participant when the traffic participant is not in the target lane where the vehicle is located.

[0148] In one possible implementation, for a traffic participant around the ego vehicle, if the traffic participant is in the target lane of the ego vehicle, the traffic participant's right-of-way parameter is 1. If the traffic participant is not in the target lane of the ego vehicle, the traffic participant's right-of-way parameter is 0.

[0149] The target lane where the ego vehicle is located and whether the traffic participant is in the target lane where the ego vehicle is located are indicated by the scene data of the target scene.

[0150] In a possible implementation, in step S4031, for one traffic participant among multiple traffic participants around the vehicle, the sum of the importance parameter of the traffic participant and the right-of-way parameter of the traffic participant is determined as the attention level of the traffic participant.

[0151] In an embodiment of the present invention, when determining the attention of traffic participants, the importance parameters of traffic participants that are highly correlated with the strength of the interaction between traffic participants and the vehicle itself and the right-of-way parameters of traffic participants that are highly correlated with the strength of the interaction between traffic participants and the vehicle itself can be considered simultaneously, thereby more comprehensively evaluating the strength of the interaction between traffic participants and the vehicle itself and improving the accuracy of the attention of traffic participants.

[0152] In one possible implementation, step S4031 includes: step S4031a - step S4031b.

[0153] In step S4031a, for a traffic participant around the own vehicle, when the traffic participant is a vehicle, the risk parameter of the traffic participant is determined based on the associated parameter information used to determine the risk parameter of the traffic participant. The associated parameter information used to determine the risk parameter of the traffic participant includes: the relative distance between the own vehicle and the traffic participant, the speed of the own vehicle, and the speed of the traffic participant.

[0154] In step S4031b, the attention level of the traffic participant is determined based on the importance parameter of the traffic participant, the right-of-way parameter of the traffic participant, and the risk parameter of the traffic participant.

[0155] In one possible implementation, in step S4031a, for a traffic participant around the ego vehicle, spring damping model parameters for the traffic participant can be obtained, and the spring damping model parameters for the traffic participant include: a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant; based on the spring damping model parameters for the traffic participant and associated parameter information for determining the risk parameter of the traffic participant, the longitudinal risk value of the traffic participant relative to the ego vehicle and the lateral risk value of the traffic participant relative to the ego vehicle are calculated; based on the longitudinal risk value of the traffic participant relative to the ego vehicle and the lateral risk value of the traffic participant relative to the ego vehicle, the risk parameter of the traffic participant is determined.

[0156] For a traffic participant around the vehicle, in order to obtain the spring-damping model parameters for the traffic participant, the physical model of the virtual spring and damping can be used to simulate the force between vehicles to obtain the spring-damping model for the traffic participant. The spring-damping model for the traffic participant has a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant.

[0157] For a traffic participant around the ego vehicle, determining the risk parameter of the traffic participant based on the spring-damping model parameters for the traffic participant and the associated parameter information for determining the risk parameter of the traffic participant includes: calculating the longitudinal risk value of the traffic participant relative to the ego vehicle and the lateral risk value of the traffic participant relative to the ego vehicle based on the spring-damping model parameters for the traffic participant and the associated parameter information for determining the risk parameter of the traffic participant; and determining the risk parameter of the traffic participant based on the longitudinal risk value of the traffic participant relative to the ego vehicle and the lateral risk value of the traffic participant relative to the ego vehicle.

[0158] The longitudinal risk field function used to calculate the longitudinal risk value of the traffic participant relative to the vehicle can be expressed as:

[0159]

[0160] U x represents the longitudinal risk value of the traffic participant relative to the vehicle, k lon represents the virtual longitudinal spring stiffness, x represents the relative distance between the ego vehicle and the traffic participant, x0 represents the expected relative distance between the ego vehicle and the traffic participant, c lon represents the virtual longitudinal damping coefficient, v p represents the speed of traffic participants, v x Indicates the speed of the vehicle.

[0161] The lateral risk field function used to calculate the lateral risk value of the traffic participant relative to the vehicle can be expressed as:

[0162]

[0163] U y represents the lateral risk value of the traffic participant relative to the vehicle, c lat represents the virtual lateral damping coefficient, v y represents the lateral speed of the vehicle, y represents the lateral offset of the vehicle from the center line of the current lane, and k lat Represents the virtual lateral spring stiffness.

[0164] The risk parameter of the traffic participant can be expressed as:

[0165]

[0166] Among them, U represents the risk parameter of the traffic participant, U x,max Indicates the maximum longitudinal risk value set, U y,max Indicates the set maximum lateral risk.

[0167] The risk parameters of traffic participants around the ego vehicle reflect the potential danger their behavior poses to the ego vehicle. This factor is considered when determining the attention level of traffic participants around the ego vehicle, allowing for a more comprehensive assessment of the strength of their interaction with the ego vehicle. This improves the accuracy of the attention level of traffic participants around the ego vehicle.

[0168] In an embodiment of the present invention, when determining the attention of traffic participants, the importance parameters of traffic participants that are highly correlated with the strength of the interaction between traffic participants and the vehicle, the right of way parameters of traffic participants that are highly correlated with the strength of the interaction between traffic participants and the vehicle, and the risk parameters of traffic participants that are highly correlated with the strength of the interaction between traffic participants and the vehicle can be considered simultaneously. In this way, the strength of the interaction between traffic participants and the vehicle can be more comprehensively evaluated, and the accuracy of the attention of traffic participants can be improved.

[0169] In one possible implementation, in step S4031b, for one traffic participant among multiple traffic participants around the vehicle, the sum of the importance parameter of the traffic participant, the right-of-way parameter of the traffic participant, and the risk parameter of the traffic participant is determined as the attention level of the traffic participant.

[0170] In another possible implementation, in step S4031b, for a traffic participant around the vehicle, the weighted sum of the traffic participant's importance parameter, the traffic participant's road right parameter, and the traffic participant's risk parameter is determined as the traffic participant's attention level.

[0171] The weighted sum of the importance parameter of the traffic participant, the road right parameter of the traffic participant, and the risk parameter of the traffic participant is determined as the attention degree of the traffic participant, which can be expressed as:

[0172] D=ω1I+ω2U+ω3R

[0173] Where D represents the attention level of the traffic participant, I represents the importance parameter of the traffic participant, U represents the risk parameter of the traffic participant, R represents the right-of-way parameter of the traffic participant, and ω1, ω2, and ω3 represent the weights of the importance parameter, risk parameter, and right-of-way parameter of the traffic participant, respectively. ω1+ω2+ω3=1.

[0174] It should be noted that the importance parameter of each traffic participant has the same weight, the right-of-way parameter of each traffic participant has the same weight, and the risk parameter of each traffic participant has the same weight.

[0175] In embodiments of the present invention, the weights of a traffic participant's importance parameter, a traffic participant's right-of-way parameter, and a traffic participant's risk parameter can be flexibly set based on the characteristics of the traffic participant's attention in a given scenario or testing requirements. The degree of attention of a traffic participant determined using the weights of the traffic participant's importance parameter, the weights of the traffic participant's right-of-way parameter, and the weights of the traffic participant's risk parameter conforms to the characteristics of the traffic participant's attention in a given scenario or testing requirements, thereby improving the flexibility and accuracy of determining the degree of attention of traffic participants.

[0176] For example, when ω1 is greater than 0.5, the focus is on traffic participants with higher importance; when ω2 is greater than 0.5, the focus is on traffic participants with higher risk; and when ω3 is greater than 0.5, the focus is on traffic participants with greater right of way. In vehicle-following scenarios, to evaluate features like automatic emergency braking and therefore focus more on risk, ω2 can be set to 1. In test scenarios involving cutting in and lane changing, it is necessary to balance the risk, importance, and right of way of traffic participants. ω1 can be set to ω2 = ω3 = 1 / 3.

[0177] In step S404, for each target traffic participant among the multiple traffic participants around the vehicle, when the target traffic participant's attention is greater than the attention threshold, the first simulated behavior model for the target scene is used to generate first simulated behavior data of the target traffic participant for the target scene; when the target traffic participant's attention is not greater than the attention threshold, the second simulated behavior model for the target scene is used to generate second simulated behavior data of the target traffic participant for the target scene.

[0178] Step S404 is similar to step S203, and the process of step S404 refers to the process of step S203.

[0179] A data generating device is also provided in the embodiment of the present invention, and the data generating device is used to implement the above-mentioned method embodiment and preferred implementation mode, which have been described and will not be repeated here. As used below, the term "unit" can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and conceived. The device in the embodiment of the present invention is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0180] The data generating device comprises:

[0181] an acquisition unit, configured to acquire scene data of a target scene, wherein the target scene includes a vehicle and a plurality of traffic participants around the vehicle;

[0182] a determining unit, configured to determine the attention level of each of the plurality of traffic participants and determine a target traffic participant among the plurality of traffic participants based on the scene data;

[0183] A generation unit is used to, for each target traffic participant, when the target traffic participant's attention is greater than an attention threshold, generate first simulated behavior data of the target traffic participant for the target scene by using a first simulated behavior model for the target scene; when the target traffic participant's attention is not greater than the attention threshold, generate second simulated behavior data of the target traffic participant for the target scene by using a second simulated behavior model for the target scene, wherein the degree of anthropomorphism of the simulated behavior in the target scene represented by the first simulated behavior data is higher than the degree of anthropomorphism of the simulated behavior in the target scene represented by the second simulated behavior data.

[0184] Furthermore, the determination unit is further used to determine, for each traffic participant, the position importance of the traffic participant's position and the type importance of the traffic participant's type based on the scene data, and to determine the importance parameter of the traffic participant based on the position importance and the type importance, and to determine the attention level of the traffic participant based on the importance parameter of the traffic participant.

[0185] Furthermore, the determination unit is further used to determine the right-of-way parameter of the traffic participant based on whether the traffic participant is in the target lane of the own vehicle, wherein the target lane of the own vehicle is indicated by the scene data; and determine the attention level of the traffic participant based on the importance parameter and right-of-way parameter of the traffic participant.

[0186] Furthermore, the determination unit is further used to determine the risk parameters of the traffic participant when the traffic participant is a vehicle based on associated parameter information used to determine the risk parameters of the traffic participant, the associated parameter information including: the relative distance between the vehicle and the traffic participant, the speed of the vehicle, and the speed of the traffic participant, wherein the associated parameter information is indicated by the scene data; and determine the attention level of the traffic participant based on the importance parameter of the traffic participant, the right of way parameter of the traffic participant and the risk parameter of the traffic participant.

[0187] Furthermore, the determination unit is further used to obtain spring damping model parameters for the traffic participant, and the spring damping model parameters include: a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant; based on the spring damping model parameters for the traffic participant and the associated parameter information for determining the risk parameters of the traffic participant, the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle are calculated; based on the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle, the risk parameters of the traffic participant are determined.

[0188] Furthermore, the determination unit is further configured to determine the attention level of the traffic participant by taking a weighted sum of the importance parameter of the traffic participant, the road right parameter of the traffic participant, and the risk parameter of the traffic participant.

[0189] Furthermore, the determination unit is further configured to sort the attention levels of the multiple traffic participants from large to small according to the attention levels of the traffic participants; and determine the first preset number of traffic participants among the multiple traffic participants as target traffic participants.

[0190] Furthermore, the target scene is any one of the multiple scenes; the data generating device further includes:

[0191] The clustering unit is configured to cluster the label information of the plurality of scene data before acquiring the scene data of the target scene, so as to determine the plurality of scenes and the scene to which each of the plurality of scene data belongs.

[0192] refer to Figure 5 , Figure 51 is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. The computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in or on the memory for displaying graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple storage devices. Similarly, multiple vehicles can be connected, with each device providing some of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof. The memory 20 stores instructions executable by at least one processor 10, causing the at least one processor 10 to perform the methods described in the above embodiments. The memory 20 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function; the data storage area may store data generated based on vehicle usage. Furthermore, the memory 20 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some optional embodiments, the memory 20 may optionally include memory remote from the processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The memory 20 may include volatile memory, such as random access memory; non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; or a combination of these types of memory. The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected via a bus or other means. The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc.The output device 40 may include a display device, an auxiliary lighting device (e.g., LED), and a tactile feedback device (e.g., a vibration motor). The display device includes, but is not limited to, a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0193] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0194] A portion of the embodiments of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes but is not limited to a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0195] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or modification made by those skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A data generation method, characterized in that: The method comprises: Acquire scene data of a target scene, wherein the target scene includes a self-vehicle and a plurality of traffic participants around the self-vehicle; determining, based on the scene data, a degree of attention of each of the plurality of traffic participants, and determining a target traffic participant among the plurality of traffic participants; For each target traffic participant, when the target traffic participant's attention is greater than the attention threshold, a first simulated behavior model for the target scene is used to generate first simulated behavior data of the target traffic participant for the target scene; when the target traffic participant's attention is not greater than the attention threshold, a second simulated behavior model for the target scene is used to generate second simulated behavior data of the target traffic participant for the target scene, wherein the degree of anthropomorphism of the simulated behavior in the target scene represented by the first simulated behavior data is higher than the degree of anthropomorphism of the simulated behavior in the target scene represented by the second simulated behavior data.

2. The method according to claim 1, wherein: Determining the attention level of each of the plurality of traffic participants according to the scene data includes: For each traffic participant, the position importance of the traffic participant's position and the type importance of the traffic participant's type are determined based on the scene data, and the importance parameter of the traffic participant is determined based on the position importance and the type importance, and the attention level of the traffic participant is determined based on the importance parameter of the traffic participant.

3. The method according to claim 2, wherein: Determining the attention level of the traffic participant according to the importance parameter of the traffic participant includes: determining a right-of-way parameter of the traffic participant according to whether the traffic participant is in a target lane of the ego vehicle, wherein the target lane of the ego vehicle is indicated by the scenario data; The attention level of the traffic participant is determined according to the importance parameter and the road right parameter of the traffic participant.

4. The method according to claim 3, wherein: Determining the attention level of the traffic participant according to the importance parameter and the right-of-way parameter of the traffic participant includes: When the traffic participant is a vehicle, determining the risk parameter of the traffic participant according to associated parameter information used to determine the risk parameter of the traffic participant, the associated parameter information including: a relative distance between the vehicle and the traffic participant, a speed of the vehicle, and a speed of the traffic participant, wherein the associated parameter information is indicated by the scenario data; The attention level of the traffic participant is determined according to the importance parameter of the traffic participant, the road right parameter of the traffic participant and the risk parameter of the traffic participant.

5. The method according to claim 4, characterized in that: Determining the risk parameter of the traffic participant according to the associated parameter information for determining the risk parameter of the traffic participant includes: Acquiring spring damping model parameters for the traffic participant, the spring damping model parameters including: a virtual longitudinal spring stiffness and a virtual longitudinal damping coefficient for the traffic participant, and a virtual lateral spring stiffness and a virtual lateral damping coefficient for the traffic participant; Calculating a longitudinal risk value of the traffic participant relative to the own vehicle and a lateral risk value of the traffic participant relative to the own vehicle based on the spring-damping model parameters for the traffic participant and the associated parameter information for determining the risk parameter of the traffic participant; The risk parameter of the traffic participant is determined according to the longitudinal risk value of the traffic participant relative to the own vehicle and the lateral risk value of the traffic participant relative to the own vehicle.

6. The method according to claim 4, characterized in that: Determining the attention level of the traffic participant according to the importance parameter of the traffic participant, the road right parameter of the traffic participant, and the risk parameter of the traffic participant includes: The weighted sum of the importance parameter of the traffic participant, the road right parameter of the traffic participant and the risk parameter of the traffic participant is determined as the attention degree of the traffic participant.

7. The method according to claim 1, wherein: Determining a target traffic participant among the multiple traffic participants includes: sorting the attention levels of the multiple traffic participants according to the attention levels of the traffic participants from greatest to least; The first preset number of traffic participants among the multiple traffic participants are respectively determined as target traffic participants.

8. The method according to claim 1, wherein: The target scene is any one of multiple scenes; Before acquiring the scene data of the target scene, the method further includes: The label information of the plurality of scene data is clustered to determine the plurality of scenes and the scene to which each scene data in the plurality of scene data belongs.

9. A data generating device, characterized in that: The device comprises: an acquisition unit, configured to acquire scene data of a target scene, wherein the target scene includes a vehicle and a plurality of traffic participants around the vehicle; a determining unit, configured to determine the attention level of each of the plurality of traffic participants and determine a target traffic participant among the plurality of traffic participants based on the scene data; A generation unit is used to, for each target traffic participant, when the target traffic participant's attention is greater than an attention threshold, generate first simulated behavior data of the target traffic participant for the target scene by using a first simulated behavior model for the target scene; when the target traffic participant's attention is not greater than the attention threshold, generate second simulated behavior data of the target traffic participant for the target scene by using a second simulated behavior model for the target scene, wherein the degree of anthropomorphism of the simulated behavior in the target scene represented by the first simulated behavior data is higher than the degree of anthropomorphism of the simulated behavior in the target scene represented by the second simulated behavior data.

10. A computer device installed on a vehicle, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 8.

Images