Vehicle collision risk early warning method and device in simulation scene and storage medium

Abstract

The invention discloses a vehicle collision risk early warning method and device in a simulation scene and a storage medium. The method comprises the steps of obtaining current driving information of a first virtual vehicle in a current simulation scene; an obstacle exists in the current simulation scene; determining current sensing data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information; obtaining current fusion sensing data; performing fusion processing on the current perception data and the current fusion perception data to obtain current test data; determining a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data; and if the current collision risk prediction result represents that the collision risk exists between the first virtual vehicle and the second virtual vehicle, generating collision risk early warning information. According to the invention, the timeliness and reliability of vehicle collision risk early warning are improved, and the safety in the vehicle driving process is improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device and storage medium for warning the collision risk of a vehicle in a simulation scenario. Background Art

[0002] The actual testing of autonomous driving vehicles on the road has the dilemma of long test cycle, high test cost and low efficiency. In this process, autonomous driving simulation testing came into being. The autonomous driving system is divided into three subsystems: environmental perception, decision planning and control execution. The three subsystems are composed of sensor models, decision models, control object models and corresponding software and hardware. The existing simulation tests are mainly focused on the decision planning and control execution algorithm testing after obtaining simulation data.

[0003] In the current mainstream V2X HIL test scenario, the forward collision warning (FCW) function communicates interactively through the vehicle-mounted OBU. After the host vehicle (HV) obtains the basic position, speed, lane and other information of the remote vehicle (RV), it calculates the front and rear distance and collision time. If the collision time is less than the FCW function threshold, FCW will issue a warning to remind the driver of the risk of collision. This function is suitable for assisted driving under human driving.

[0004] Secondly, the current ADAS HIL test mainly provides ideal environmental data to the HV through simulation software, focusing on whether the HV can be correctly controlled under different environmental conditions and perform operations such as braking; in addition, in the ADAS test, the FCW function is ideal perception data obtained from the simulation software. Therefore, in the scene with obstructions, it is quite different from the actual perception effect and the test accuracy is low. In the real world, the perception effect of the sensor will be greatly reduced when encountering an obstruction scene. However, since ADASHIL is ideal perception data directly obtained from the simulation software, the perception effect will still be very good. This is quite different from the results of the actual field test. The simulation test should be as close to reality as possible. Summary of the invention

[0005] The present application provides a method, device and storage medium for warning the collision risk of a vehicle in a simulation scenario, which can improve the timeliness and reliability of the vehicle collision risk warning and enhance the safety of the vehicle during driving.

[0006] On the one hand, the present application provides a method for early warning of vehicle collision risk in a simulation scenario, the method comprising:

[0007] Obtaining current driving information of the first virtual vehicle in a current simulation scene; there are obstacles in the current simulation scene;

[0008] Determining current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information;

[0009] Acquire current fused perception data; the current fused perception data is determined based on current simulation perception data collected by the state sensor on the first virtual vehicle, current vehicle state data of the second virtual vehicle, current virtual geographic information, and current environment data;

[0010] fusing the current sensing data and the current fused sensing data to obtain current test data;

[0011] Determining a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data;

[0012] If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated.

[0013] In an exemplary embodiment, the obtaining of current fused perception data includes:

[0014] Acquire driving state data of the first virtual vehicle in the current driving state collected by the state sensor on the first virtual vehicle as the current simulation perception data;

[0015] Acquiring the current vehicle state data of the second virtual vehicle;

[0016] Acquire the current virtual geographic information of the first virtual vehicle in the current simulation scene collected by a virtual global navigation satellite system;

[0017] Acquire the current environment data of an area at a preset distance from the first virtual vehicle collected by a roadside unit;

[0018] The current fused perception data is determined according to the current simulated perception data, the current vehicle state data, the current virtual geographic information and the current environment data.

[0019] In an exemplary embodiment, the obtaining the current vehicle state data of the second virtual vehicle includes:

[0020] If there is a second on-board unit on the second virtual vehicle, acquiring the current vehicle state data of the second virtual vehicle collected by the second on-board unit;

[0021] If the second on-board unit does not exist on the second virtual vehicle, the current vehicle status data of the second virtual vehicle collected by the roadside unit is obtained.

[0022] In an exemplary embodiment, determining a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data includes:

[0023] Determine, according to the current test data, a current distance between the first virtual vehicle and the second virtual vehicle, first current driving data of the first virtual vehicle, and second current driving data of the second virtual vehicle;

[0024] determining a current estimated collision time between the first virtual vehicle and the second virtual vehicle according to the current distance, the first current driving data, and the second current driving data;

[0025] If the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and the current collision risk prediction result is obtained.

[0026] In an exemplary embodiment, if the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and before obtaining the current collision risk prediction result, the method further includes:

[0027] Acquire a virtual vehicle model threshold relationship library; the virtual vehicle model threshold relationship library includes a mapping relationship between a preset vehicle model and a preset collision time threshold;

[0028] Obtaining a target virtual vehicle model corresponding to the first virtual vehicle;

[0029] The preset collision time threshold value matching the target virtual vehicle model is searched in the virtual vehicle model threshold relationship library to obtain the current preset collision time threshold value.

[0030] In an exemplary embodiment, if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, generating collision risk warning information includes:

[0031] If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, generating the collision risk warning information and the speed control command;

[0032] Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid risks;

[0033] The collision risk warning information is sent to a target terminal so that the target terminal displays the collision risk warning information.

[0034] In an exemplary embodiment, sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid the risk includes:

[0035] Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed;

[0036] Acquire real-time perception data of the first virtual vehicle in a real-time driving state, and use the data as the current perception data;

[0037] Acquire real-time fused perception data and use it as the current fused perception data again;

[0038] If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, repeating the step of fusing the current perception data and the current fused perception data to obtain current test data until the step of generating collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle;

[0039] If the current collision risk prediction result indicates that there is no collision risk between the first virtual vehicle and the second virtual vehicle, the first virtual vehicle is controlled to stop adjusting the vehicle speed.

[0040] On the other hand, a collision risk warning device for a vehicle in a simulation scenario is provided, the device comprising:

[0041] A current driving information module, used to obtain current driving information of the first virtual vehicle in a current simulation scene; there are obstacles in the current simulation scene;

[0042] A current perception data module, used to determine current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information;

[0043] A current fused perception data module, used to obtain current fused perception data; the current fused perception data is determined based on current simulation perception data collected by the state sensor on the first virtual vehicle, current vehicle state data of the second virtual vehicle, current virtual geographic information and current environment data;

[0044] A current test data module, used for fusing the current perception data and the current fused perception data to obtain current test data;

[0045] A current collision risk prediction result module, used to determine a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data;

[0046] The collision risk warning information module is used to generate collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle.

[0047] On the other hand, an electronic device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded by the processor and executes the vehicle collision risk warning method in the simulation scenario as described above.

[0048] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the vehicle collision risk warning method in the simulation scenario as described above.

[0049] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the vehicle collision risk warning method in the simulation scenario as described above.

[0050] The present application provides a method, device and storage medium for warning the collision risk of vehicles in a simulation scenario, which have the following technical effects: the present application obtains the current driving information of a first virtual vehicle in a current simulation scenario; there are obstacles in the current simulation scene; according to the current simulation scene and the current driving information, the current perception data of the first virtual vehicle in the current driving state is determined; the current fused perception data is obtained; the current fused perception data is determined based on the current simulation perception data collected by the state sensor on the first virtual vehicle, the current vehicle state data of the second virtual vehicle, the current virtual geographic information and the current environmental data; the current perception data and the current fused perception data are fused to obtain current test data; according to the current test data, the current collision risk prediction result corresponding to the first virtual vehicle is determined; if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated. The present application obtains the current perception data collected by the first virtual vehicle itself, and the current fused perception data composed of the current simulated perception data collected by the state sensor of the first virtual vehicle, the current vehicle state data of the second virtual vehicle, the current virtual geographic information and the current environmental data, and fuses the two to determine the current test data, thereby realizing the collaborative testing of single-vehicle intelligence and V2X, and performing collision risk assessment based on the data obtained by the fusion of the two, and issuing an early warning when a collision risk occurs, thereby improving the timeliness and reliability of vehicle collision risk warnings, avoiding safety hazards of vehicles during driving, and improving the safety of the vehicle driving process. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions and advantages of the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0053] Figure 2 It is a schematic diagram of a vehicle in a simulation scene in which an obstacle exists in the current simulation scene provided by an embodiment of this specification;

[0054] Figure 3 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0055] Figure 4It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0056] Figure 5 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0057] Figure 6 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0058] Figure 7 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0059] Figure 8 It is a flow chart of a method for early warning of vehicle collision risk in a simulation scenario provided by an embodiment of this specification;

[0060] Fig. 9 It is a structural block diagram of vehicle data interaction in a simulation scenario provided by an embodiment of this specification;

[0061] Fig.10 It is a structural schematic diagram of a vehicle collision risk warning device in a simulation scenario provided in an embodiment of this specification.

[0062] Fig.11 It is a structural diagram of a server of a vehicle collision risk warning method in a simulation scenario provided in an embodiment of this specification. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0064] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0065] The following describes a vehicle collision risk warning method in a simulation scenario of the present application. Figure 1 It is a flowchart of a method for warning vehicle collision risk in a simulation scenario provided by an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 1 As shown, the method can be applied to a control unit in a vehicle in a simulation scenario, and the method includes:

[0066] S101: Acquire current driving information of a first virtual vehicle in a current simulation scene; there are obstacles in the current simulation scene.

[0067] In the embodiments of this specification, the current simulation scene is any scene in the simulation scene library constructed by the simulation scene software. The simulation scene library contains scenes with obstacles and scenes without obstacles. The simulation scene software can simulate different scenes of vehicles in the real world, thereby helping the simulation test to better simulate the effect of single-vehicle intelligent driving in the real world. Among them, the scene with obstacles includes but is not limited to the scene where the first virtual vehicle passes through a bridge hole, or the scene where there is an obstruction at the intersection that makes the first virtual vehicle's line of sight unclear. For example, Figure 2 As shown, Figure 2 If car A is the first virtual vehicle, then car B is the second virtual vehicle, and there is an intersection occlusion between car A and car B. At this time, there is an obstacle in the current simulation scene; if car A is the second virtual vehicle, then car B is the first virtual vehicle, and there is an intersection occlusion between car B and car A. At this time, there is an obstacle in the current simulation scene.

[0068] S103: Determine current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information.

[0069] In the embodiment of the present specification, when a scene with obstacles is played in the simulation software, the first virtual vehicle will generate simulation data, and the current perception data of the first virtual vehicle in the current driving state with obstacles is obtained by combining the current simulation scene and the driving information of the first virtual vehicle in this scene, wherein the current perception data includes but is not limited to the speed, acceleration, and longitude and latitude of the first virtual vehicle. By obtaining the current perception data of the first virtual vehicle from the simulation software, the true value perception data of the vehicle body collected by the first virtual vehicle itself is determined, which provides an accurate benchmark for subsequent data comparison and calibration, and improves the accuracy and reliability of the measurement results of the perception data of the vehicle in the simulation test.

[0070] S105: Obtain current fused perception data; the current fused perception data is determined based on current simulation perception data collected by the state sensor on the first virtual vehicle, current vehicle state data of the second virtual vehicle, current virtual geographic information and current environmental data.

[0071] In the embodiments of the present specification, by acquiring current fused perception data that combines current simulation perception data, current vehicle status data, current virtual geographic information and current environmental data, subsequent data fusion is facilitated, wherein the current vehicle status data, current virtual geographic information and current environmental data are all acquired from the second on-board unit OBU and the roadside unit RSU of the second virtual vehicle through V2X communication. It can be seen that acquiring information collected by combining single-vehicle intelligence and V2X communication can help the first virtual vehicle acquire perception data in some specific scenarios, such as when there are obstructions, curves, bridges and other scenarios ahead, thereby realizing the information supplement of some perception blind spots of the first virtual vehicle under single-vehicle intelligence, thereby helping the intelligent driving algorithm platform to make decisions and control vehicles more effectively, improving the functional effect of collision risk warning, and improving the accuracy and reliability of vehicle collision risk prediction results in simulation tests.

[0072] In the embodiment of this specification, the current fusion perception data is obtained, such as Figure 3 As shown, Figure 3 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, including:

[0073] S301: Acquire driving state data of the first virtual vehicle in the current driving state collected by the state sensor on the first virtual vehicle as the current simulation perception data.

[0074] In the embodiments of the present specification, by installing a sensor physical model on the first virtual vehicle in the simulation software, it is possible to simulate the effect of vehicle data collected after the first virtual vehicle is equipped with sensors in the real world; the current simulated perception data of the first virtual vehicle collected by the state sensor on the first virtual vehicle is obtained, thereby improving the authenticity of the driving data of the first virtual vehicle, so that the simulation test can more accurately simulate the driving conditions of the vehicle in the real world, especially the performance in complex environments.

[0075] S302: Acquire the current vehicle status data of the second virtual vehicle.

[0076] In the embodiments of this specification, the current vehicle state data of the second virtual vehicle refers to the driving state data of the second virtual vehicle, including but not limited to the driving speed, acceleration, yaw angle and position information of the second virtual vehicle. By obtaining the current vehicle state data of the second virtual vehicle, it is indirectly determined whether the first virtual vehicle has a collision risk, thereby improving the accuracy and reliability of the vehicle collision risk prediction results in the simulation scenario.

[0077] In this embodiment of the specification, the obtaining of the current vehicle state data of the second virtual vehicle includes:

[0078] If there is a second on-board unit on the second virtual vehicle, acquiring the current vehicle state data of the second virtual vehicle collected by the second on-board unit;

[0079] In an embodiment of the present specification, if there is a second on-board unit on the second virtual vehicle, the second on-board unit of the second virtual vehicle can be communicatively connected with the first on-board unit of the first virtual vehicle, wherein the communication method can be PC5, and the first virtual vehicle obtains the current vehicle status data of the second virtual vehicle transmitted by the second on-board unit of the second virtual vehicle through the first on-board unit.

[0080] If the second on-board unit does not exist on the second virtual vehicle, the current vehicle state data of the second virtual vehicle collected by the roadside unit is obtained.

[0081] In the embodiment of this specification, if the second onboard unit does not exist on the second virtual vehicle, the second virtual vehicle can be a bicycle, a battery vehicle or other vehicle. At this time, the roadside unit can collect the current vehicle status data of the second virtual vehicle, and the roadside unit is connected to the first onboard unit of the first virtual vehicle in communication, wherein the communication method can be PC5, and the first virtual vehicle obtains the current vehicle status data of the second virtual vehicle transmitted by the roadside unit through the first onboard unit. By obtaining the current vehicle status data of the second virtual vehicle, subsequent data fusion is facilitated, thereby improving the comprehensiveness and authenticity of the data collected for predicting the vehicle collision risk results in the simulation scenario, and improving the accuracy and reliability of the vehicle collision risk prediction results in the simulation scenario.

[0082] S303: Acquire the current virtual geographic information of the first virtual vehicle in the current simulation scene collected by the virtual global navigation satellite system.

[0083] In the embodiments of the present specification, the virtual global navigation satellite system is a GNSS positioning system, which is a technology that uses signals transmitted from one or more groups of satellites in Earth orbit to determine the precise position of objects on the Earth. By using GNSS positioning system data to determine the current virtual geographic information of the first virtual vehicle, it is convenient to test and verify various functions of the vehicle, thereby improving the safety and functionality of the vehicle.

[0084] S304: Acquire the current environment data of an area at a preset distance from the first virtual vehicle collected by a roadside unit.

[0085] In an embodiment of the present specification, the roadside unit is communicatively connected with the first on-board unit of the first virtual vehicle, wherein the communication method may be PC5, the preset distance may be a, and the first virtual vehicle obtains the current environmental data collected by the roadside unit in the area with a distance value of a from the first virtual vehicle through the first on-board unit, wherein the current environmental data includes but is not limited to roadside perception information, traffic light information, and map information.

[0086] S305: Determine the current fused perception data according to the current simulation perception data, the current vehicle status data, the current virtual geographic information and the current environment data.

[0087] In the embodiments of the present specification, the current fused perception data is obtained by fusing the current simulation perception data, the current vehicle status data, and the current environment data described in the current virtual geographic information, so as to facilitate the subsequent data fusion with the current perception data of the first virtual vehicle. By fusing the data collected by the single vehicle intelligence and the data collected through V2X communication, the output perception data of the first virtual vehicle, the surrounding environment of the first virtual vehicle, and the second virtual vehicle are comprehensively obtained, taking into account the situations where there are obstacles and the absence of obstacles in the simulation scene, thereby improving the accuracy and reliability of the collision risk prediction results of the vehicles in the simulation scene.

[0088] S107: Fusing the current perception data and the current fused perception data to obtain current test data.

[0089] In the embodiment of the present specification, due to the performance difference between the real sensor and the state sensor on the first virtual vehicle, there is an error between the current perception data and the current simulated perception data, and when there are obstacles in the current simulation scene, the current vehicle state data, current virtual geographic information and current environmental data of the second virtual vehicle are obtained at the same time, and these data are fused, thereby improving the authenticity and comprehensiveness of the data for predicting the collision risk results of the first virtual vehicle and improving the driving safety of the vehicle in the simulation scene.

[0090] S109: Determine a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data.

[0091] In the embodiment of the present specification, the current collision risk prediction result corresponding to the first virtual vehicle is determined by comprehensive detection and current test data obtained through data fusion, thereby improving the accuracy and reliability of the current collision risk prediction result and improving the safety of vehicle driving in the simulation scenario.

[0092] In the embodiment of this specification, the current collision risk prediction result corresponding to the first virtual vehicle is determined according to the current test data, such as Figure 4 As shown, Figure 4 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, including:

[0093] S401: Determine, according to the current test data, a current distance between the first virtual vehicle and the second virtual vehicle, first current driving data of the first virtual vehicle, and second current driving data of the second virtual vehicle.

[0094] In the embodiments of the present specification, the current test data includes but is not limited to the driving speed, acceleration and position information of the first virtual vehicle, the driving speed, acceleration and position information of the second virtual vehicle, so as to obtain the current distance between the first virtual vehicle and the second virtual vehicle according to the position information of the first virtual vehicle and the position information of the second virtual vehicle, obtain the first current driving data of the first virtual vehicle according to the driving speed and acceleration of the first virtual vehicle, and obtain the second current driving data of the second virtual vehicle according to the driving speed and acceleration of the second virtual vehicle. By determining the driving data of the first virtual vehicle and the second virtual vehicle, it is convenient to determine whether there is a collision risk between the vehicles in the simulation scenario.

[0095] S402: Determine a current estimated collision time between the first virtual vehicle and the second virtual vehicle according to the current distance, the first current driving data, and the second current driving data.

[0096] In the embodiment of the present specification, the current expected collision time is determined based on the current distance, the first current driving data and the second current driving data, so as to determine whether the first virtual vehicle has a collision risk, thereby improving the accuracy and reliability of the vehicle collision risk prediction results in the simulation scenario.

[0097] In the embodiment of the present specification, if the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and before obtaining the current collision risk prediction result, as follows Figure 5 As shown, Figure 5 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, wherein the method further comprises:

[0098] S501: Acquire a virtual vehicle model threshold relationship library; the virtual vehicle model threshold relationship library includes a mapping relationship between a preset vehicle model and a preset collision time threshold.

[0099] In the embodiments of the present specification, the virtual vehicle model threshold relationship library may include, but is not limited to, a table or a linear formula. The preset vehicle models may include, but are not limited to, sedan b, sedan c, and truck d. If the virtual vehicle model threshold relationship library is a table, the preset collision time threshold B corresponding to sedan b, the preset collision time threshold C corresponding to sedan c, and the preset collision time threshold D corresponding to truck d can be directly queried in the virtual vehicle model threshold relationship library; if the virtual vehicle model threshold relationship library is a linear formula, the preset vehicle model can be substituted into the formula to obtain the preset collision time threshold corresponding to the preset vehicle model, the preset vehicle model b can be substituted into the formula to obtain the preset collision time threshold B corresponding to the preset sedan model b, the preset vehicle model c can be substituted into the formula to obtain the preset collision time threshold C corresponding to the preset sedan model c, and the preset vehicle model d can be substituted into the formula to obtain the preset collision time threshold D corresponding to the preset truck model d. By setting the virtual vehicle model threshold relationship library to determine the preset collision time thresholds corresponding to vehicles of different models, vehicles of different models are fully considered, and the accuracy and reliability of the prediction of vehicle collision risk results in simulation scenarios are improved.

[0100] S502: Obtain a target virtual vehicle model corresponding to the first virtual vehicle.

[0101] In the embodiment of this specification, exemplarily, the first virtual vehicle is a sedan, and the target virtual vehicle type corresponding to the first virtual vehicle is b.

[0102] S503: Searching the virtual vehicle model threshold relationship library for a preset collision time threshold that matches the target virtual vehicle model to obtain the current preset collision time threshold.

[0103] In the embodiment of this specification, if the virtual vehicle model threshold relationship library is a table, the current preset collision time threshold B corresponding to car b can be queried in the virtual vehicle model threshold relationship library, which is 3s; if the virtual vehicle model threshold relationship library is a linear formula, the preset vehicle model b is substituted into the formula to obtain the current preset collision time threshold B corresponding to the preset car model b, which is 3s. By setting the current preset collision time threshold corresponding to the first virtual vehicle, the collision risk warning time required by different vehicle models can be accurately located, the applicability of the vehicle system is improved, the decision logic of the intelligent driving system is optimized, and the driving safety performance of the vehicle in the simulation scenario is guaranteed, and the timeliness and reliability of the vehicle collision risk warning in the simulation scenario are improved.

[0104] S403: If the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and the current collision risk prediction result is obtained.

[0105] In the embodiment of this specification, the current preset collision time threshold is 3s. If the current estimated collision time is less than 3s, it can be determined that there is a collision risk between the first virtual vehicle and the second virtual vehicle at this time, so a safety strategy formulated for the collision risk is adopted to control the first virtual vehicle to adjust the speed to avoid a collision between the first virtual vehicle and the second virtual vehicle; if the current estimated collision time is greater than or equal to 3s, it can be determined that there is no collision risk between the first virtual vehicle and the second virtual vehicle at this time, and the current round of collision risk judgment ends at this time, and the first virtual vehicle drives normally. By formulating different strategies for different collision risk prediction results, the safety of vehicle driving in simulation scenarios is improved.

[0106] S111: If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated.

[0107] In an embodiment of the present specification, when there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated, so that the user can timely understand the vehicle condition of the first virtual vehicle and respond in combination with the vehicle speed adjustment strategy to avoid the collision risk, thereby improving the user's risk perception ability and improving the driving safety of the vehicle in the simulation scenario.

[0108] In the embodiment of this specification, if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated, such as Figure 6 As shown, Figure 6 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, including:

[0109] S601: If the current collision risk prediction result indicates that there is the collision risk between the first virtual vehicle and the second virtual vehicle, generate the collision risk warning information and the speed control command.

[0110] In an embodiment of the present specification, when there is a collision risk, collision risk warning information and a speed control command are generated, wherein the collision risk warning information includes but is not limited to sound warning information and text warning information, and the speed control command includes but is not limited to the recommended driving speed and braking speed of the first virtual vehicle.

[0111] S602: Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid risks.

[0112] In the embodiment of this specification, a speed control command is sent to the wire-controlled chassis of the first virtual vehicle, so as to control the first virtual vehicle to brake and decelerate, thereby increasing the distance between the first virtual vehicle and the second virtual vehicle, avoiding the risk of collision between the two, and improving the driving safety of the vehicle in the simulation scenario. It can be seen that this application introduces ADAS testing on the basis of V2X and HIL testing, which can not only check whether the vehicle is correctly warned, but also test whether the first virtual vehicle can control the speed when the distance between the first virtual vehicle and the second virtual vehicle is too close, thereby deepening the depth of V2X testing.

[0113] In the embodiment of this specification, the speed control command is sent to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid risks, such as Figure 7 As shown, Figure 7 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, including:

[0114] S701: Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed.

[0115] In the embodiments of the present specification, for example, if the first virtual vehicle is a sedan, the target virtual vehicle type corresponding to the first virtual vehicle is b, the current preset collision time threshold B is set, and the corresponding target vehicle speed α is set for the target virtual vehicle type b, and the first virtual vehicle is controlled to adjust the vehicle speed to α; if the first virtual vehicle is a truck, the target virtual vehicle type corresponding to the first virtual vehicle is d, the current preset collision time threshold D is set, and the corresponding target vehicle speed β is set for the target virtual vehicle type d, and the first virtual vehicle is controlled to adjust the vehicle speed to β; by sending a speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to brake and decelerate, the first virtual vehicle is avoided from sending a collision, and risk warning and avoidance are performed within a reasonable time, which not only maintains the normal driving speed of the vehicle in the simulation scenario but also ensures the driving safety of the vehicle in the simulation scenario.

[0116] S702: Acquire real-time perception data of the first virtual vehicle in a real-time driving state, and use it as the current perception data again.

[0117] In the embodiment of the present specification, by acquiring real-time perception data of the first virtual vehicle in a real-time driving state in the process of braking and decelerating the first virtual vehicle to avoid collision risk, the real-time situation of the first virtual vehicle can be determined, thereby facilitating controlling the first virtual vehicle to adjust its speed.

[0118] S703: Acquire real-time fused perception data, and use it as the current fused perception data again.

[0119] In the embodiments of the present specification, by acquiring real-time fused perception data, the first virtual vehicle can acquire all-round status data of the first virtual vehicle and the surrounding environment and vehicle of the first virtual vehicle regardless of whether the first virtual vehicle is in a simulation scenario with good road conditions or with obstacles, so that the fused data is more real and reliable, thereby improving the authenticity and reliability of the vehicle collision risk prediction results in the simulation scenario, and greatly improving the driving safety of the vehicle in the simulation scenario.

[0120] S704: If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, repeat the step of fusing the current perception data and the current fused perception data to obtain current test data until the step of generating collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle.

[0121] In the embodiment of the present specification, by repeatedly obtaining the current collision risk prediction result while the first virtual vehicle adjusts the speed to avoid risk, the collision risk prediction result of the first virtual vehicle is continuously obtained, and the speed is adjusted in time, the timeliness of the vehicle collision risk warning in the simulation scenario and the driving safety of the vehicle in the simulation scenario are improved.

[0122] S705: If the current collision risk prediction result indicates that there is no collision risk between the first virtual vehicle and the second virtual vehicle, control the first virtual vehicle to stop adjusting the speed.

[0123] In the embodiment of the present specification, when there is no collision risk between the first virtual vehicle and the second virtual vehicle, the first virtual vehicle stops adjusting the speed and resumes normal driving state. By combining the ADAS HIL test, different speed control strategies are formulated for different collision risk prediction results, so that the vehicle can control the wire-controlled chassis to adjust the vehicle speed. In this way, not only the vehicle warning function can be tested during the simulation, but also the vehicle decision-making and control functions can be tested, which not only maintains the vehicle's normal driving speed in the simulation scenario but also improves the vehicle's driving safety in the simulation scenario.

[0124] S603: Send the collision risk warning information to the target terminal, so that the target terminal displays the collision risk warning information.

[0125] In an embodiment of the present specification, the target terminal may be the main control platform HMI of the first virtual vehicle, and the collision risk warning information may include but is not limited to the current expected collision time, voice prompt information that the vehicle is at risk of collision, and the driving status information of the first virtual vehicle at this time. By sending the collision risk warning information to the target terminal, the target terminal can issue a voice prompt to the user that the first virtual vehicle is at risk of collision at this time, and display the current expected collision time on the screen, and update the driving status of the first virtual vehicle, so that the user can understand the vehicle's driving conditions in a timely manner and respond in combination with the speed control command, so that the first virtual vehicle can avoid the collision risk in time, thereby improving the driving safety of the vehicle in the simulation scenario.

[0126] In an exemplary embodiment, Figure 8 As shown, Figure 8 The following is a flowchart of a method for early warning of vehicle collision risk in a simulation scenario, including:

[0127] S801: The simulation scenario software is started to generate simulation data.

[0128] In the embodiment of the present specification, when the simulation scene software is started, different scenes are played according to user needs, and the main vehicle generates simulation data, wherein the simulation scenes include scenes with good road conditions and scenes with obstacles, and the simulation data includes but is not limited to the speed, acceleration, and longitude and latitude of the main vehicle.

[0129] S802: Acquire relevant perception data of the host and remote vehicles from the simulation scenario software.

[0130] In the embodiment of the present specification, the perception data obtained from the simulation scenario software includes the perception data of the host vehicle, the perception data of the remote vehicle, the data collected by the roadside unit, and the data collected by the GNSS positioning system.

[0131] S803: Input relevant perception data of the host vehicle and the remote vehicle into the intelligent driving computing platform of the host vehicle for data fusion.

[0132] In the embodiment of the present specification, the relevant perception data of the host and remote vehicles are input into the intelligent driving computing platform of the host vehicle for data fusion, so that the intelligent driving computing unit can calculate the possibility of collision based on V2X communication data, thereby comprehensively predicting the collision risk of the host vehicle.

[0133] S804: Acquire surrounding perception data of the main vehicle through the sensor physical model.

[0134] In the embodiment of the present specification, a sensor physical model is installed on the main vehicle in the simulation scene software, and the data around the main vehicle is obtained through the sensor physical model, and the simulated actual perception data is obtained.

[0135] S805: Input the surrounding perception data of the main vehicle into the intelligent driving computing platform of the main vehicle for perception data fusion.

[0136] In the embodiments of the present specification, the main vehicle's perception data obtained by the main vehicle's on-board unit OBU, the perception data of the remote vehicle, the data collected by the roadside unit, the data collected by the GNSS positioning system, and the simulated actual perception data obtained by the main vehicle's sensor physical model are fused through the main vehicle's intelligent driving computing unit, so that the data used to predict the collision risk of the main vehicle is more comprehensive and accurate.

[0137] S806: Determine whether the current host remote vehicle has a forward collision. If the host remote vehicle has not a forward collision, go to S809.

[0138] In the embodiment of this specification, by judging the distance between the main and remote vehicles and the estimated collision time, it is judged whether the main and remote vehicles will collide, thereby improving the accuracy and reliability of the collision risk prediction results. In addition, when judging whether the main and remote vehicles send a forward collision, data selection can be performed according to the simulation scene. When the simulation scene is in a scene with good road conditions, the main vehicle is not blocked by obstacles, and the perception data of the main vehicle is also convincing. The user can choose between the collision risk prediction results obtained based on the perception data of the main vehicle and the collision risk prediction results obtained based on the fusion data to control the vehicle; when the simulation scene is in a scene with obstacles or objects blocking the main vehicle, the main vehicle has unclear vision and there is a blind spot. At this time, the collision risk prediction results obtained based on the fusion data are selected, which is more reliable and accurate, and improves the driving safety of the vehicle in the simulation scene.

[0139] S807: The main vehicle control algorithm controls the current driving state of the main vehicle.

[0140] In the embodiments of this specification, the speed of the host vehicle is controlled by a control algorithm to avoid collision between the host vehicle and the remote vehicle, and different control algorithms are set for different vehicle models, which not only maintains the safety of the host vehicle during driving but also improves the driving efficiency of the vehicle.

[0141] S808: Continue to determine whether the host vehicle and the remote vehicle have a forward collision.

[0142] In the embodiment of the present specification, by continuously detecting whether the main remote vehicle has a forward collision while controlling the main vehicle's driving speed to avoid a forward collision sent by the main remote vehicle, the main vehicle can adjust its driving state in time, thereby maintaining the safety of the main vehicle during driving and improving the driving efficiency of the vehicle.

[0143] S809: This warning judgment is completed.

[0144] This embodiment improves the authenticity of the perception data by obtaining the true value perception data and simulated actual perception data of the main vehicle from the simulation software, so that the simulation test can more accurately simulate the driving conditions of the vehicle in the real world, especially the performance in complex environments, and obtains additional perception information from the remote vehicle on-board unit OBU and the roadside unit RSU through V2X communication, so that when the main vehicle is in a scene with obstacles, the main vehicle's intelligent driving algorithm platform can obtain more comprehensive information in the perception blind spot, so as to make more effective decisions, and by combining C-V2X with single-vehicle intelligence, the performance of a single-vehicle intelligent vehicle in a V2X communication environment can be tested in the vehicle-road-cloud demonstration area, thereby improving the accuracy and reliability of the vehicle collision risk prediction results.

[0145] In an exemplary embodiment, Fig. 9 As shown, Fig. 9 This is a structural block diagram of vehicle data interaction in a simulation scenario. The code and corresponding name of each component in the system are as follows:

[0146] 901: The on-board unit OBU of the first virtual vehicle is used to receive vehicle data of the second virtual vehicle and data collected by the roadside unit.

[0147] 902: An intelligent driving computing unit of the first virtual vehicle is used to fuse the collected data.

[0148] 903: A physical model of a sensor on the first virtual vehicle is used to collect current simulation perception data of the first virtual vehicle.

[0149] 904: A human-machine interaction page HMI of the first virtual vehicle is used to display collision risk warning information of the first virtual vehicle.

[0150] 905: A control-by-wire chassis of the first virtual vehicle, used to control the first virtual vehicle to adjust the vehicle speed.

[0151] 906: A GNSS positioning system is used to collect current virtual geographic information of the first virtual vehicle.

[0152] 907: When the second virtual vehicle has an on-board unit OBU, the second virtual vehicle has an on-board unit OBU, which is used to collect current vehicle status data of the second virtual vehicle and send the collected data to the on-board unit OBU of the first virtual vehicle.

[0153] 908: Roadside unit RSU, used for collecting current environment data and transmitting it to the on-board unit OBU of the first virtual vehicle.

[0154] 909: Current environment data collected by the roadside unit, representing environment data of the area near the first virtual vehicle.

[0155] This specification also provides a vehicle collision risk warning device in a simulation scenario, such as Fig.10 As shown, the device comprises:

[0156] The current driving information module 1001 is used to obtain the current driving information of the first virtual vehicle in the current simulation scene; there are obstacles in the current simulation scene;

[0157] A current perception data module 1002, configured to determine current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information;

[0158] The current fused perception data module 1003 is used to obtain current fused perception data; the current fused perception data is determined based on the current simulation perception data collected by the state sensor on the first virtual vehicle, the current vehicle state data of the second virtual vehicle, the current virtual geographic information and the current environment data;

[0159] The current test data module 1004 is used to perform fusion processing on the current sensing data and the current fused sensing data to obtain current test data;

[0160] A current collision risk prediction result module 1005 is used to determine a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data;

[0161] The collision risk warning information module 1006 is configured to generate collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle.

[0162] In some embodiments, the current fused perception data module further includes:

[0163] The current simulation perception data submodule is used to obtain the driving state data of the first virtual vehicle in the current driving state collected by the state sensor on the first virtual vehicle as the current simulation perception data.

[0164] The current vehicle status data submodule is used to obtain the current vehicle status data of the second virtual vehicle.

[0165] The current virtual geographic information submodule is used to obtain the current virtual geographic information of the first virtual vehicle in the current simulation scene collected by the virtual global navigation satellite system.

[0166] The current environment data submodule is used to obtain the current environment data of the area at a preset distance from the first virtual vehicle collected by the roadside unit.

[0167] The current fused perception data submodule is used to determine the current fused perception data according to the current simulation perception data, the current vehicle status data, the current virtual geographic information and the current environment data.

[0168] In some embodiments, the current vehicle status data submodule further includes:

[0169] The first current vehicle state data unit is used to obtain the current vehicle state data of the second virtual vehicle collected by the second onboard unit if there is a second onboard unit on the second virtual vehicle.

[0170] The second current vehicle status data unit is used to obtain the current vehicle status data of the second virtual vehicle collected by the roadside unit if the second on-board unit does not exist on the second virtual vehicle.

[0171] In some embodiments, the current collision risk prediction result module further includes:

[0172] The first determination submodule is used to determine the current distance between the first virtual vehicle and the second virtual vehicle, the first current driving data of the first virtual vehicle, and the second current driving data of the second virtual vehicle according to the current test data.

[0173] The current estimated collision time submodule is used to determine the current estimated collision time between the first virtual vehicle and the second virtual vehicle according to the current distance, the first current driving data and the second current driving data.

[0174] The current collision risk prediction result submodule is used to determine that there is the collision risk between the first virtual vehicle and the second virtual vehicle if the current expected collision time is less than or equal to the current preset collision time threshold, and obtain the current collision risk prediction result.

[0175] In some embodiments, the apparatus further comprises:

[0176] The virtual vehicle type threshold relationship library module is used to obtain a virtual vehicle type threshold relationship library; the virtual vehicle type threshold relationship library includes a mapping relationship between a preset vehicle type and a preset collision time threshold.

[0177] The target virtual vehicle model module is used to obtain the target virtual vehicle model corresponding to the first virtual vehicle.

[0178] The current preset collision time threshold module is used to query the preset collision time threshold that matches the target virtual vehicle model in the virtual vehicle model threshold relationship library to obtain the current preset collision time threshold.

[0179] In some embodiments, the collision risk warning information module further includes:

[0180] The second determining submodule is configured to generate the collision risk warning information and the speed control command if the current collision risk prediction result indicates that there is the collision risk between the first virtual vehicle and the second virtual vehicle.

[0181] The speed regulation submodule is used to send the speed regulation control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid risks.

[0182] The display submodule is used to send the collision risk warning information to the target terminal so that the target terminal displays the collision risk warning information.

[0183] In some embodiments, the speed regulation submodule further includes:

[0184] A speed control unit is used to send the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed.

[0185] The real-time perception data unit is used to obtain the real-time perception data of the first virtual vehicle in the real-time driving state and use it as the current perception data again.

[0186] The real-time fused perception data unit is used to obtain the real-time fused perception data and reuse it as the current fused perception data.

[0187] A repeating unit is used to repeat the steps of fusing the current perception data and the current fused perception data to obtain current test data if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, and generating collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle.

[0188] The speed control stopping unit is configured to control the first virtual vehicle to stop adjusting the speed if the current collision risk prediction result indicates that there is no collision risk between the first virtual vehicle and the second virtual vehicle.

[0189] The device and method embodiments in the described device embodiments are based on the same inventive concept.

[0190] An embodiment of the present specification provides a vehicle electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement a vehicle collision risk warning method in a simulation scenario as provided in the above method embodiment.

[0191] An embodiment of the present application also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to a vehicle collision risk warning method in a simulation scenario in a method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the vehicle collision risk warning method in a simulation scenario provided in the above method embodiment.

[0192] The embodiment of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the vehicle collision risk warning method in the simulation scenario provided by the above method embodiment.

[0193] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0194] The vehicle collision risk warning method embodiment in the simulation scenario provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Fig.11 1 is a hardware structure block diagram of a server of a vehicle collision risk warning method in a simulation scenario provided by an embodiment of this specification. Fig.11As shown, the server 1100 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1110 (the central processing unit 1110 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1130 for storing data, and one or more storage media 1120 (such as one or more mass storage devices) for storing application programs 1123 or data 1122. Among them, the memory 1130 and the storage medium 1120 can be short-term storage or permanent storage. The program stored in the storage medium 1120 may include one or more modules, and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 1110 may be configured to communicate with the storage medium 1120 and execute a series of instruction operations in the storage medium 1120 on the server 1100. The server 1100 may also include one or more power supplies 1160, one or more wired or wireless network interfaces 1150, one or more input and output interfaces 1140, and / or one or more operating systems 1121, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0195] The input / output interface 1140 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 1100. In one example, the input / output interface 1140 includes a network adapter (NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 1140 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0196] It can be understood by those skilled in the art that Fig.11 The structure shown is only for illustration and does not limit the structure of the above electronic device. Fig.11 More or fewer components as shown, or with Fig.11 Different configurations are shown.

[0197] It can be seen from the embodiments of the collision risk warning method, device and storage medium for vehicles in a simulation scenario provided by the above-mentioned present application that the present application obtains current driving information of a first virtual vehicle in a current simulation scenario; there are obstacles in the current simulation scene; according to the current simulation scene and the current driving information, current perception data of the first virtual vehicle in the current driving state is determined; current fused perception data is obtained; the current fused perception data is determined based on the current simulation perception data collected by the state sensor on the first virtual vehicle, the current vehicle state data of the second virtual vehicle, current virtual geographic information and current environmental data; the current perception data and the current fused perception data are fused to obtain current test data; according to the current test data, a current collision risk prediction result corresponding to the first virtual vehicle is determined; if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated. The present application improves the authenticity of the first virtual vehicle data by acquiring the current perception data of the first virtual vehicle collected by the single-vehicle intelligence based on the first virtual vehicle and the current simulated perception data collected by the state sensor on the first virtual vehicle. By acquiring the current vehicle state data, current virtual geographic information and current environmental data of the second virtual vehicle collected based on V2 communication, when there are obstacles in the simulation scene, the perception ability of the sensor physical model is reduced. Additional perception information is obtained from the OBU and RSU of the second virtual vehicle through V2X communication, namely C-V2X, to help the intelligent driving algorithm platform of the first virtual vehicle obtain more comprehensive information in the perception blind spot, so as to make more effective decisions. The intelligent driving algorithm platform of the first virtual vehicle integrates C-V2X with the data collected by the single-vehicle intelligence, so that the performance of the single-vehicle intelligent vehicle in the V2X communication environment can be tested in the vehicle-road-cloud demonstration area, so as to test not only the ability of the single-vehicle intelligence itself, but also its performance when communicating with the outside world, thereby improving the reliability and safety of verifying the single-vehicle intelligent vehicle in a real environment. At the same time, by communicating with ADAS The combination of HIL tests can not only test the vehicle warning function in simulation scenarios, but also test the vehicle's decision-making and control functions in simulation scenarios, thereby helping C-V2X technology to make greater progress in the field of assisted driving. It not only improves the comprehensiveness and authenticity of the vehicle data collected in simulation scenarios, but also improves the timeliness and reliability of vehicle collision risk warnings in simulation scenarios, and improves the safety of vehicle driving in simulation scenarios.

[0198] It should be noted that the above sequence of the embodiments of this specification is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0200] A person skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0201] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A vehicle collision risk warning method in a simulation scenario, characterized in that: The method comprises: Obtaining current driving information of the first virtual vehicle in a current simulation scene; there are obstacles in the current simulation scene; Determining current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information; Acquire current fused perception data; the current fused perception data is determined based on current simulation perception data collected by the state sensor on the first virtual vehicle, current vehicle state data of the second virtual vehicle, current virtual geographic information, and current environment data; fusing the current sensing data and the current fused sensing data to obtain current test data; Determining a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data; If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, collision risk warning information is generated.

2. The method according to claim 1, characterized in that The obtaining of current fused perception data includes: Acquire driving state data of the first virtual vehicle in the current driving state collected by the state sensor on the first virtual vehicle as the current simulation perception data; Acquiring the current vehicle state data of the second virtual vehicle; Acquire the current virtual geographic information of the first virtual vehicle in the current simulation scene collected by a virtual global navigation satellite system; Acquire the current environment data of an area at a preset distance from the first virtual vehicle collected by a roadside unit; The current fused perception data is determined according to the current simulated perception data, the current vehicle state data, the current virtual geographic information and the current environment data.

3. The method according to claim 2, characterized in that The obtaining of the current vehicle state data of the second virtual vehicle comprises: If there is a second on-board unit on the second virtual vehicle, acquiring the current vehicle state data of the second virtual vehicle collected by the second on-board unit; If the second on-board unit does not exist on the second virtual vehicle, the current vehicle status data of the second virtual vehicle collected by the roadside unit is obtained.

4. The method according to claim 1, characterized in that: The step of determining, according to the current test data, a current collision risk prediction result corresponding to the first virtual vehicle includes: Determine, according to the current test data, a current distance between the first virtual vehicle and the second virtual vehicle, first current driving data of the first virtual vehicle, and second current driving data of the second virtual vehicle; determining a current estimated collision time between the first virtual vehicle and the second virtual vehicle according to the current distance, the first current driving data, and the second current driving data; If the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and the current collision risk prediction result is obtained.

5. The method according to claim 4, characterized in that If the current estimated collision time is less than or equal to the current preset collision time threshold, it is determined that there is the collision risk between the first virtual vehicle and the second virtual vehicle, and before obtaining the current collision risk prediction result, the method further includes: Acquire a virtual vehicle model threshold relationship library; the virtual vehicle model threshold relationship library includes a mapping relationship between a preset vehicle model and a preset collision time threshold; Obtaining a target virtual vehicle model corresponding to the first virtual vehicle; The preset collision time threshold value matching the target virtual vehicle model is searched in the virtual vehicle model threshold relationship library to obtain the current preset collision time threshold value.

6. The method according to claim 4, characterized in that If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, generating collision risk warning information includes: If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, generating the collision risk warning information and the speed control command; Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid risks; The collision risk warning information is sent to a target terminal so that the target terminal displays the collision risk warning information.

7. The method according to claim 6, characterized in that The sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed to avoid the risk includes: Sending the speed control command to the wire-controlled chassis of the first virtual vehicle to control the first virtual vehicle to adjust the speed; Acquire real-time perception data of the first virtual vehicle in a real-time driving state, and use the data as the current perception data; Acquire real-time fused perception data and use it as the current fused perception data again; If the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle, repeating the step of fusing the current perception data and the current fused perception data to obtain current test data until the step of generating collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle; If the current collision risk prediction result indicates that there is no collision risk between the first virtual vehicle and the second virtual vehicle, the first virtual vehicle is controlled to stop adjusting the vehicle speed.

8. A vehicle collision risk warning device in a simulation scenario, characterized in that: The device comprises: A current driving information module, used to obtain current driving information of the first virtual vehicle in a current simulation scene; there are obstacles in the current simulation scene; A current perception data module, used to determine current perception data of the first virtual vehicle in a current driving state according to the current simulation scene and the current driving information; A current fused perception data module, used to obtain current fused perception data; the current fused perception data is determined based on current simulation perception data collected by the state sensor on the first virtual vehicle, current vehicle state data of the second virtual vehicle, current virtual geographic information and current environment data; A current test data module, used for fusing the current perception data and the current fused perception data to obtain current test data; A current collision risk prediction result module, used to determine a current collision risk prediction result corresponding to the first virtual vehicle according to the current test data; The collision risk warning information module is used to generate collision risk warning information if the current collision risk prediction result indicates that there is a collision risk between the first virtual vehicle and the second virtual vehicle.

9. An electronic device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded by the processor and executed by the vehicle collision risk warning method in a simulation scenario as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the vehicle collision risk warning method in a simulation scenario as described in any one of claims 1-7.

Images