A system and method for evaluating the autonomous driving takeover capability of vehicles

Abstract

This application provides a system and method for evaluating the autonomous driving takeover capability of vehicles. In the process of simulating and evaluating the driver's takeover capability in a vehicle, a driving simulation device simulates driving operation scenarios, the in-vehicle environment of the target vehicle, road conditions, weather conditions, and non-driving behaviors of the driver within the vehicle, constructing a first test scenario. A data processing device collects driving data and physiological information of the driver driving the target vehicle within the constructed first test scenario, and inputs this data into a pre-trained takeover capability evaluation model, outputting the driver's takeover capability evaluation information under the first test scenario. This approach, while ensuring a large amount of data is obtained through simulation scenarios, evaluates the driver's takeover capability from multiple dimensions using driving data and driver physiological state information, thus improving the accuracy of the driver takeover capability evaluation.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a system and method for evaluating the autonomous driving takeover capability of a vehicle. Background Technology

[0002] With the continuous breakthroughs in autonomous driving technology, Level 3 autonomous driving has been gradually applied to driving scenarios. In order to ensure driving safety, it is necessary to assess the driver's ability to take over driving and to perform corresponding operations to ensure driving safety when the driver does not have the ability to take over the vehicle.

[0003] In existing technologies, driver takeover capability is a product of multiple factors, including driver age, driving experience, gender, emotions, non-driving tasks, and the vehicle's environment. However, current assessments of driver takeover capability are limited in data and have a relatively singular approach, resulting in low accuracy in evaluating driver takeover capability. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a system and method for evaluating the autonomous driving takeover capability of a vehicle. By simulating test scenarios, the system can simulate corresponding test scenarios according to test requirements and collect vehicle driving data and driver physiological state information under the test scenarios. While ensuring that a large amount of data is obtained through simulation scenarios, the system evaluates the driver takeover capability from multiple dimensions through driving data and driver physiological state information, which helps to improve the accuracy of driver takeover capability evaluation.

[0005] In a first aspect, embodiments of this application provide a vehicle autonomous driving takeover capability evaluation system, which includes a driving simulation device and a data processing device. The driving simulation device is used to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. The data processing device is used to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0006] In one possible implementation, the driving simulation device includes a driving scenario simulation module, a driving operation simulation module, and a non-driving behavior simulation module; The driving scenario simulation module is used to simulate and construct the in-vehicle scenario, driving road scenario, and driving weather scenario of the target vehicle based on the scenario information to be tested. The driving operation simulation module is used to simulate the driving operation scenario based on the test scenario information; The driving behavior simulation module is used to simulate the driver's in-vehicle non-driving behavior based on the test scenario information and the driver's historical non-driving behavior in historical driving information.

[0007] In one possible implementation, the driving scenario simulation module is used to simulate and construct the in-vehicle scenario of the target vehicle through the following steps: Based on the cabin interior information, control mechanism information, and instrument display information contained in the test scenario information, the interior style, control mechanism, and instrument placement are determined, and the in-vehicle scene of the target vehicle is simulated based on the interior style, control mechanism, and instrument placement.

[0008] In one possible implementation, the driving operation simulation module includes a steering wheel simulation unit, a force feedback pedal unit, and a degree-of-freedom simulation unit; the driving operation simulation module is used to simulate the driving operation scenario through the following steps: Based on the information of the test scenario, the steering wheel simulation unit is controlled to simulate steering wheel steering information; Based on the test scenario information, the force feedback pedal unit is controlled to simulate pedal force feedback information; Based on the information of the test scenario, the degree of freedom simulation unit is controlled to simulate the vehicle attitude change information during the driving process of the target vehicle; The driving operation scenario is simulated based on the steering wheel steering information, the pedal force feedback information, and the vehicle posture change information.

[0009] In one possible implementation, the driver's in-vehicle non-driving behavior includes at least one of the following: driver's auditory task behavior and driver's visual task behavior.

[0010] In one possible implementation, the data processing device includes a driving data acquisition module, a driver physiological information acquisition module, and a driver takeover capability evaluation module. The driving data acquisition module is used to collect steering wheel steering information, pedal force feedback information, and vehicle gear information in the first test scenario; The driver physiological information collection module is used to collect the driver's physiological information during the process of taking over the target vehicle; wherein, the physiological information includes at least one of the following: driver's electroencephalogram (EEG) information, driver's electromyogram (EMG) information, driver's electrodermal conductance (EDC) information, and driver's facial information; The driver takeover ability evaluation module is used to receive steering wheel steering information, pedal force feedback information, and vehicle gear information collected by the driving data acquisition module, and driver physiological information collected by the driver physiological information acquisition module. The steering wheel steering information, pedal force feedback information, vehicle gear information, and driver physiological information are input into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0011] In one possible implementation, the data processing device is used to input the driving data and the physiological information into a pre-trained takeover capability evaluation model, so that the takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario. The data processing device is used to: The driving data and physiological information are input into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model determines the driver's takeover ability score based on the driving data and physiological information, and outputs the driver's takeover ability evaluation information based on the takeover ability score.

[0012] In one possible implementation, the driver's takeover capability evaluation information includes at least one of the following: having the ability to take over the vehicle, not having the ability to take over the vehicle, and being conditionally capable of taking over the vehicle.

[0013] In one possible implementation, the data processing device is further configured to: In the second test scenario simulated by the driving simulation device, driving data of the driver driving the target vehicle and the driver's physiological information are collected, and the driving data and the physiological information are input into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information in the second test scenario. Based on the takeover capability evaluation information and the driver takeover capability label corresponding to the second test scenario, the takeover capability evaluation model is adjusted.

[0014] Secondly, embodiments of this application also provide a method for evaluating the autonomous driving takeover capability of a vehicle, the method being used in the autonomous driving takeover capability evaluation system for a vehicle as described in any of the first aspects; the method for evaluating the autonomous driving takeover capability of a vehicle includes: The driving simulation device is controlled to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. The data processing device is controlled to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0015] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle autonomous driving takeover capability evaluation method as described in the second aspect.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the vehicle autonomous driving takeover capability evaluation method as described in the second aspect.

[0017] The vehicle autonomous driving takeover capability evaluation system and method provided in this application, during the simulation evaluation of the driver's takeover capability in the vehicle, a driving simulation device simulates driving operation scenarios, the in-vehicle scenario of the target vehicle, driving road scenarios, driving weather scenarios, and the driver's non-driving behaviors in the vehicle according to test requirements, constructing a first test scenario. A data processing device collects driving data of the driver driving the target vehicle and the driver's physiological information under the constructed first test scenario, and inputs the driving data and the driver's physiological information into a pre-trained takeover capability evaluation model. The takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario. In this way, by simulating the test scenario, corresponding test scenarios can be simulated according to test requirements, and driving data and driver physiological state information are collected under the test scenario. While ensuring that a large amount of data is obtained through simulation scenarios, the driver's takeover capability is evaluated from multiple dimensions through driving data and driver physiological state information, which helps to improve the accuracy of the driver takeover capability evaluation.

[0018] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is one of the structural schematic diagrams of the vehicle autonomous driving takeover capability evaluation system provided in the embodiments of this application; Figure 2 This is a schematic diagram of the driving simulation device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the driving operation simulation module provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application; Figure 5 This is a second schematic diagram of the structure of the vehicle autonomous driving takeover capability evaluation system provided in the embodiments of this application; Figure 6 A flowchart illustrating a method for evaluating the autonomous driving takeover capability of a vehicle, provided as an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0021] Icons: 100 - Autonomous driving takeover capability evaluation system; 110 - Driving simulation device; 111 - Driving scenario simulation module; 112 - Driving operation simulation module; 1121 - Steering wheel simulation unit; 1122 - Force feedback pedal unit; 1123 - Degree of freedom simulation unit; 113 - Non-driving behavior simulation module; 120 - Data processing device; 121 - Driving data acquisition module; 122 - Driver physiological information acquisition module; 123 - Driver takeover capability evaluation module; 700 - Electronic device; 710 - Processor; 720 - Memory; 730 - Bus. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0023] First, the applicable application scenarios of this application will be introduced. This application can be applied to the field of intelligent transportation technology.

[0024] With the continuous breakthroughs in autonomous driving technology, Level 3 autonomous driving has been gradually applied to driving scenarios. In order to ensure driving safety, it is necessary to assess the driver's ability to take over driving and to perform corresponding operations to ensure driving safety when the driver does not have the ability to take over the vehicle.

[0025] In existing technologies, driver takeover capability is a product of multiple factors, including driver age, driving experience, gender, emotions, non-driving tasks, and the vehicle's environment. However, current assessments of driver takeover capability are limited in data and have a relatively singular approach, resulting in low accuracy in evaluating driver takeover capability.

[0026] Based on this, embodiments of this application provide a vehicle autonomous driving takeover capability evaluation system to improve the accuracy of driver takeover capability evaluation.

[0027] Furthermore, the vehicle autonomous driving takeover capability evaluation system 100 disclosed in the embodiments of this application will be introduced.

[0028] Please see Figure 1 , Figure 1 This is one of the structural schematic diagrams of the vehicle autonomous driving takeover capability evaluation system 100 provided in the embodiments of this application, such as... Figure 1As shown, the autonomous driving takeover capability evaluation system 100 includes a driving simulation device 110 and a data processing device 120. Specifically, in the process of simulating and evaluating the driver's takeover capability in the vehicle, the driving simulation device 110 simulates driving operation scenarios, the in-vehicle scenario of the target vehicle, the driving road scenario, the driving weather scenario, and the driver's non-driving behavior in the vehicle according to the test requirements, and constructs a first test scenario. The data processing device 120 collects the driver's driving data of the target vehicle and the driver's physiological information under the constructed first test scenario, and inputs the driving data and the driver's physiological information into the pre-trained takeover capability evaluation model. The takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario.

[0029] Specifically, the driving simulation device 110 is used to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle.

[0030] In this embodiment of the application, the driving simulation device 110 simulates driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle according to the test scenario information in the test requirements, thereby constructing a first test scenario, so that the data processing device 120 can collect driving data and driver physiological information in the first test scenario, and then evaluate the driver's takeover ability.

[0031] Please see here. Figure 2 , Figure 2 This is a schematic diagram of the structure of the driving simulation device 110 provided in the embodiments of this application, as shown below. Figure 2 As shown, the driving simulation device 110 includes a driving scenario simulation module 111, a driving operation simulation module 112, and a non-driving behavior simulation module 113 to simulate driving scenarios, operating behaviors, and non-driving behaviors in the first test scenario.

[0032] Specifically, the driving scenario simulation module 111 is used to simulate and construct the in-vehicle scenario, driving road scenario, and driving weather scenario of the target vehicle based on the test scenario information; the driving operation simulation module 112 is used to simulate the driving operation scenario based on the test scenario information; and the non-driving behavior simulation module 113 is used to simulate the driver's in-vehicle non-driving behavior based on the test scenario information and the driver's historical non-driving behavior in historical driving information.

[0033] In one possible implementation, when simulating the first test scenario, the driving environment set in the test scenario can be simulated according to the test scenario information. This can include simulating the cabin inside the target vehicle, the road scenario in which the vehicle travels, and the weather scenario indicated in the test scenario information.

[0034] Specifically, the driving scenario simulation module 111 is used to simulate and construct the in-vehicle scenario of the target vehicle through the following steps: a1: Based on the cabin interior information, control mechanism information and instrument display information contained in the test scenario information, determine the interior style, control mechanism and instrument placement, and simulate and construct the in-vehicle scene of the target vehicle based on the interior style, control mechanism and instrument placement.

[0035] In one possible implementation, a reasonable and accurate interior style, control mechanism, and instrument display position can be determined on the target vehicle in the test scenario based on the cabin interior information, control mechanism information, and instrument display information in the test requirements. Then, the interior of the target vehicle is arranged according to the corresponding interior style, type and position of the control mechanism, and instrument display position to simulate and construct the in-vehicle scene of the target vehicle.

[0036] In one possible implementation, the driving road scenario can be simulated by the terminal device to simulate different road types and various traffic references.

[0037] Specifically, road types may include at least one of the following: urban roads, highways, rural roads, etc.; traffic references may include at least one of the following: pedestrians, other vehicles.

[0038] For example, if the test scenario involves two vehicles traveling in the same direction traveling together with the target vehicle on a highway, then the terminal device can select a highway as the road type and select two vehicles in the same direction lane to simulate the driving road scenario.

[0039] In one possible implementation, the driving weather information can be obtained by simulating different weather conditions. For example, the weather conditions may include at least one of the following: sunny, rainy, foggy, etc.

[0040] For example, in the above example, if the test scenario is that two vehicles traveling in the same direction are traveling together with the target vehicle on a highway in rainy weather, then the road type can be selected as highway on the terminal device, and two vehicles can be selected in the same direction lane to simulate rainy weather and simulate the driving road scenario.

[0041] In one possible implementation, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of the driving operation simulation module 112 provided in the embodiments of this application, as shown below. Figure 3 As shown, the driving operation simulation module 112 includes a steering wheel simulation unit 1121, a force feedback pedal unit 1122, and a degree of freedom simulation unit 1123. By simulating the speed and angle of steering wheel rotation, the force feedback of acceleration and / or braking pedal, and the degree of freedom angle, it simulates the driving operation scenario of the target vehicle.

[0042] Specifically, the driving operation simulation module is used to simulate the driving operation scenario through the following steps: b1: Based on the information of the scenario to be tested, control the steering wheel simulation unit to simulate steering wheel steering information.

[0043] b2: Based on the test scenario information, control the force feedback pedal unit to simulate pedal force feedback information.

[0044] b3: Based on the information of the test scenario, control the degree-of-freedom simulation unit to simulate the vehicle attitude change information during the driving process of the target vehicle.

[0045] b4: Based on the steering wheel information, the pedal force feedback information, and the vehicle posture change information, simulate the driving operation scenario.

[0046] In one possible implementation, the steering wheel simulation unit 1121 can simulate road feel such as steering resistance of the steering wheel during real driving. Based on the driving information indicated in the test scenario information, such as the current left turn, the steering wheel simulation unit 1121 can simulate road feel such as steering resistance when turning the steering wheel to the left, thereby simulating steering wheel rotation information.

[0047] In one possible implementation, the force feedback pedal unit 1122 can simulate the force feedback of the accelerator pedal and the brake pedal to simulate the pedal force feedback information of the driver during the process of driving the target vehicle, such as acceleration and braking.

[0048] In one possible implementation, the degree-of-freedom simulation unit 1123 can simulate the pitch, roll, and other attitude changes of the target vehicle during driving.

[0049] Specifically, the degree-of-freedom simulation unit can be a six-degree-of-freedom simulation platform, which simulates the pitch, roll, and other attitude changes of the target vehicle in different driving scenarios indicated in the test information, such as goods and downhill driving.

[0050] Here, driving operation scenarios are simulated based on the simulated steering wheel steering information, the pedal force feedback information, and the vehicle posture change information.

[0051] In one possible implementation, the driver's in-vehicle non-driving behavior includes at least one of the following: driver auditory task behavior and driver visual task behavior, that is, these behaviors can be performed during driving but do not directly affect the vehicle's driving process.

[0052] For example, a driver's auditory task behavior could be listening to in-vehicle navigation voice prompts, in-vehicle radio broadcasts, making or receiving phone calls, etc.; a driver's visual task behavior could be viewing information on the in-vehicle screen, etc.

[0053] Here, the driving simulation device 110 simulates driving scenarios, driving operations, and non-driving behaviors to obtain the first test scenario. The data processing device 120 can collect driving data and the driver's physiological information in the first test scenario to evaluate whether the driver has the ability to take over the vehicle during the autonomous driving process.

[0054] Specifically, the data processing device 120 is used to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0055] In one possible implementation, driving data may include steering wheel information, pedal force feedback information, and vehicle gear information of the driver in the first test scenario; driver physiological information may reflect the driver's emotional and psychological state during the driving process.

[0056] In one possible implementation, please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of the data processing apparatus 120 provided in the embodiments of this application, as shown below. Figure 4As shown, the data processing device 120 includes a driving data acquisition module 121, a driver physiological information acquisition module 122, and a driver takeover ability evaluation module 123. Specifically, the driving data acquisition module 121 is used to collect steering wheel information, pedal force feedback information, and vehicle gear information in the first test scenario; the driver physiological information acquisition module 122 is used to collect the driver's physiological information during the process of taking over the target vehicle; the driver takeover ability evaluation module 123 is used to receive the steering wheel information, pedal force feedback information, and vehicle gear information collected by the driving data acquisition module, and the driver physiological information collected by the driver physiological information acquisition module, and input the steering wheel information, pedal force feedback information, vehicle gear information, and driver physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information in the first test scenario.

[0057] In one possible implementation, steering wheel steering information can be measured using a steering wheel angle sensor installed in the target vehicle.

[0058] In one possible implementation, the pedal force feedback information is the pedal opening information, which can be obtained through a pedal position sensor installed in the target vehicle.

[0059] In one possible implementation, vehicle gear information can be obtained through a gear position sensor installed in the target vehicle, which is integrated into the transmission control unit (TCU) or mounted on the transmission housing.

[0060] Here, the physiological information includes at least one of the following: driver's electroencephalogram (EEG), driver's electromyography (EMG), driver's electrical activity of the skin (EDS), and driver's facial information, which are collected by a sensor patch set on the driver's body. The driver's EEG, EMG, and EDS can reflect the driver's physiological state, such as the level of tension; the driver's facial information can reflect the driver's expression and other conditions, showing the driver's state at the moment of takeover from multiple dimensions.

[0061] Furthermore, after acquiring steering wheel information, pedal force feedback information, vehicle gear information, and driving physiological information from the driving data, the driver takeover ability evaluation module 123 evaluates the driver's current takeover ability based on the steering wheel information, pedal force feedback information, vehicle gear information, driving physiological information, and the pre-trained takeover ability evaluation model.

[0062] Specifically, the data processing device is used to input the driving data and the physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario. The data processing device is used for: c1: Input the driving data and the physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model determines the driver's takeover ability score based on the driving data and the physiological information, and outputs the driver's takeover ability evaluation information based on the takeover ability score.

[0063] Here, the internal processing of the takeover capability evaluation model can be as follows: the driver's takeover capability score is determined by weighting the obtained driving data and driver physiological information according to the preset weight coefficients, and the driver's takeover capability evaluation information is output based on the determined takeover capability score.

[0064] Here, the driver's takeover capability assessment information includes at least one of the following: having the ability to take over the vehicle, not having the ability to take over the vehicle, or being able to take over the vehicle under certain conditions.

[0065] Specifically, different takeover capability score ranges can be set, with different takeover capability scores corresponding to different takeover capabilities. Based on the calculated takeover capability scores, the driver's takeover capability evaluation information can be output.

[0066] For example, the takeover capability score range corresponding to having vehicle takeover capability is (100, 85), the takeover capability score range corresponding to having vehicle takeover capability is (85, 60), and the takeover capability score range corresponding to not having vehicle takeover capability is (60, 0). In this case, the takeover capability score calculated based on the collected driving data and driver physiological information is 70, which falls within the score range of (85, 60). Therefore, the takeover capability evaluation information output by the takeover capability score is conditional vehicle takeover.

[0067] Here, conditional takeover of a vehicle refers to the ability of a driver to take over a target vehicle when certain conditions are met. For example, in the first test scenario, the driver is on the phone, and conditional takeover of a vehicle means that the driver can take over the vehicle after ending the call.

[0068] Furthermore, a mapping relationship between driving data and driver physiological information and takeover ability evaluation information can be established in different test scenarios, thereby accurately understanding the impact of different takeover abilities on driver performance in different driving scenarios.

[0069] In one possible implementation, the data processing device 120 can also evaluate the accuracy of the takeover capability evaluation model based on the takeover capability evaluation label corresponding to the test scenario. If the prediction accuracy of the takeover capability evaluation model is low, the takeover capability evaluation model can be adjusted.

[0070] Here, the data device is further configured to: collect driving data of the driver driving the target vehicle and the driver's physiological information in the second test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information in the second test scenario; and adjust the takeover ability evaluation model based on the takeover ability evaluation information and the driver's takeover ability label corresponding to the second test scenario.

[0071] Specifically, a second test scenario is constructed based on the known takeover capability labels, corresponding driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. Driving data and driver physiological information corresponding to the takeover capability labels are obtained. These data are then input into the takeover capability evaluation model to obtain the output takeover capability evaluation information. The model's accuracy is then checked against the corresponding takeover capability labels. If they match, the model's accuracy is considered high. If they do not match, the model's accuracy is questionable, and the model is tested again in different test scenarios to determine its accuracy rate. If the accuracy rate is lower than a preset threshold, the model parameters need adjustment until the accuracy rate exceeds the preset threshold.

[0072] For example, in a test scenario where a driver listens to music in the car during a rainy day, the corresponding takeover capability label is "not capable of taking over the vehicle." However, the takeover capability evaluation model, based on the obtained driving data and driver physiological information, outputs a takeover capability evaluation that indicates the driver is capable of taking over the vehicle. This is inconsistent with the corresponding takeover capability label, indicating that the accuracy of the takeover capability evaluation model is problematic. Multiple tests are needed to determine whether the takeover capability evaluation model needs to be adjusted in the future.

[0073] In another possible implementation, different evaluation methods can be set in the driver takeover ability evaluation module, and the driver's takeover ability can be evaluated based on driving data and driver physiological information through different evaluation methods.

[0074] Here, different test scenarios corresponding to known takeover capability labels can be constructed, and the evaluation accuracy of different evaluation methods can be tested. Then, the evaluation method with the highest accuracy can be selected for evaluation, so as to improve the accuracy of the vehicle's autonomous driving takeover capability evaluation system.

[0075] For example, Figure 5 This is a second structural schematic diagram of the vehicle autonomous driving takeover capability evaluation system 100 provided in this application embodiment, as shown below. Figure 5 As shown, the autonomous driving takeover capability evaluation system 100 includes a driving simulation device 110 and a data processing device 120. The driving simulation device 110 includes a driving scenario simulation module 111, a driving operation simulation module 112, and a non-driving behavior simulation module 113. The driving scenario simulation module 111 can perform a full-vehicle cabin simulation to simulate the cabin interior, control mechanisms, and instrument displays. The driving scenario simulation module 111 can also perform scenario simulations to simulate weather, roads, and objects. The driving operation simulation module 112 includes a steering wheel simulation unit 1121, a force feedback pedal unit 1122, and a degree-of-freedom simulation unit 1123. It simulates the steering wheel road feel during vehicle operation, and uses the force feedback pedal group and a six-degree-of-freedom simulation platform to simulate pedal usage and vehicle pitch changes during vehicle operation. The non-driving behavior simulation module 113 simulates the driver's non-driving behaviors during vehicle operation through visual and auditory task simulations. The data processing device 120 includes a driving data acquisition module 121, a driver physiological information acquisition module 122, and a driver takeover ability evaluation module 123. The driving data acquisition module 121 acquires steering wheel angle information, accelerator / brake pedal opening information, and gear information under a simulated test scenario. The driver physiological information acquisition module 122 acquires the driver's electroencephalogram (EEG), electromyogram (EMG), electrodermal transfer information, and facial information. The driver takeover ability evaluation module 123 evaluates the driver's takeover ability based on the acquired driving data and driver physiological information, and outputs takeover evaluation information indicating whether the driver has the ability to take over, is conditionally capable of taking over, or does not have the ability to take over, thus completing the evaluation of the driver's takeover ability.

[0076] The vehicle autonomous driving takeover capability evaluation system provided in this application, during the simulation evaluation of the driver's takeover capability in the vehicle, a driving simulation device simulates driving operation scenarios, the in-vehicle scenario of the target vehicle, driving road scenarios, driving weather scenarios, and the driver's non-driving behaviors in the vehicle according to test requirements, constructing a first test scenario. A data processing device collects driving data of the driver driving the target vehicle and the driver's physiological information under the constructed first test scenario, and inputs the driving data and the driver's physiological information into a pre-trained takeover capability evaluation model. The takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario. In this way, by simulating the test scenario, corresponding test scenarios can be simulated according to test requirements, and driving data and driver physiological state information are collected under the test scenario. While ensuring that a large amount of data is obtained through simulation scenarios, the driver's takeover capability is evaluated from multiple dimensions using driving data and driver physiological state information, which helps to improve the accuracy of the driver takeover capability evaluation.

[0077] Based on the same inventive concept, this application also provides a method for evaluating the autonomous driving takeover capability of a vehicle applied to an autonomous driving takeover capability evaluation system. Since the principle of the method in this application is similar to the above-mentioned autonomous driving takeover capability evaluation system for vehicles in this application, the implementation of the method can be referred to the implementation of the method, and the repeated parts will not be described again.

[0078] Please see Figure 6 , Figure 6 This is a flowchart illustrating a method for evaluating the autonomous driving takeover capability of a vehicle, as provided in an embodiment of this application. Figure 6 As shown, the autonomous driving takeover capability evaluation method includes: S601. Control the driving simulation device to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. S602. Control the data processing device to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into the pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0079] In one possible implementation, the driving simulation device includes a driving scenario simulation module, a driving operation simulation module, and a non-driving behavior simulation module; the controller of the driving simulation device constructs a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle, including: The driving scenario simulation module is controlled to simulate and construct the in-vehicle scenario, driving road scenario, and driving weather scenario of the target vehicle based on the test scenario information; The driving operation simulation module is controlled to simulate the driving operation scenario based on the test scenario information; The driving behavior simulation module controls the driver's in-vehicle non-driving behavior based on the test scenario information and the driver's historical non-driving behavior in historical driving information.

[0080] In one possible implementation, the interior scene of the target vehicle is simulated and constructed through the following steps: Based on the cabin interior information, control mechanism information, and instrument display information contained in the test scenario information, the interior style, control mechanism, and instrument placement are determined, and the in-vehicle scene of the target vehicle is simulated based on the interior style, control mechanism, and instrument placement.

[0081] In one possible implementation, the driving operation simulation module includes a steering wheel simulation unit, a force feedback pedal unit, and a degree-of-freedom simulation unit; the driving operation scenario is simulated through the following steps: Based on the information of the test scenario, the steering wheel simulation unit is controlled to simulate steering wheel steering information; Based on the test scenario information, the force feedback pedal unit is controlled to simulate pedal force feedback information; Based on the information of the test scenario, the degree of freedom simulation unit is controlled to simulate the vehicle attitude change information during the driving process of the target vehicle; The driving operation scenario is simulated based on the steering wheel steering information, the pedal force feedback information, and the vehicle posture change information.

[0082] In one possible implementation, the driver's in-vehicle non-driving behavior includes at least one of the following: driver's auditory task behavior and driver's visual task behavior.

[0083] In one possible implementation, the data processing device includes a driving data acquisition module, a driver physiological information acquisition module, and a driver takeover capability evaluation module. The controller of the data processing device collects driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and inputs the driving data and physiological information into a pre-trained takeover capability evaluation model, so that the takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario, including: The driving data acquisition module is controlled to collect steering wheel steering information, pedal force feedback information, and vehicle gear information under the first test scenario. The driver physiological information acquisition module is controlled to collect the driver's physiological information during the process of taking over the target vehicle; wherein, the physiological information includes at least one of the following: driver's electroencephalogram (EEG) information, driver's electromyogram (EMG) information, driver's electrodermal conductance (EDC) information, and driver's facial information; The driver takeover ability evaluation module receives steering wheel information, pedal force feedback information, and vehicle gear information collected by the driving data acquisition module, as well as driver physiological information collected by the driver physiological information acquisition module. It then inputs the steering wheel information, pedal force feedback information, vehicle gear information, and driver physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

[0084] In one possible implementation, inputting the driving data and the physiological information into a pre-trained takeover capability evaluation model, so that the takeover capability evaluation model outputs the driver's takeover capability evaluation information under the first test scenario, includes: The driving data and physiological information are input into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model determines the driver's takeover ability score based on the driving data and physiological information, and outputs the driver's takeover ability evaluation information based on the takeover ability score.

[0085] In one possible implementation, the driver's takeover capability evaluation information includes at least one of the following: having the ability to take over the vehicle, not having the ability to take over the vehicle, and being conditionally capable of taking over the vehicle.

[0086] In one possible implementation, the autonomous driving takeover capability evaluation method further includes: The data processing device is controlled to collect driving data of the driver driving the target vehicle and the driver's physiological information in the second test scenario simulated by the driving simulation device, and input the driving data and the physiological information into the pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information in the second test scenario. Based on the takeover capability evaluation information and the driver takeover capability label corresponding to the second test scenario, the takeover capability evaluation model is adjusted.

[0087] The autonomous driving takeover capability evaluation method for vehicles provided in this application involves a driving simulation device simulating driving operation scenarios, the in-vehicle environment of the target vehicle, road conditions, weather conditions, and non-driving behaviors of the driver within the vehicle to construct a first test scenario. A data processing device collects driving data and physiological information of the driver within the constructed first test scenario and inputs this data into a pre-trained takeover capability evaluation model. The model then outputs the driver's takeover capability evaluation information for the first test scenario. This approach allows for the simulation of test scenarios based on testing requirements, and the collection of vehicle driving data and driver physiological information within these scenarios. While ensuring a large amount of data is obtained through simulation, the method also provides a multi-dimensional evaluation of the driver's takeover capability using driving data and driver physiological information, thus improving the accuracy of the driver takeover capability evaluation. Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 700 includes a processor 710, a memory 720, and a bus 730.

[0088] The memory 720 stores machine-readable instructions executable by the processor 710. When the electronic device 700 is running, the processor 710 communicates with the memory 720 via the bus 730. When the machine-readable instructions are executed by the processor 710, they can perform the operations described above. Figure 5 The steps of the vehicle's autonomous driving takeover capability evaluation method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0089] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 5The steps of the vehicle's autonomous driving takeover capability evaluation method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0090] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0092] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0094] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0095] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An automatic driving takeover capability evaluation system of a vehicle, characterized by, The autonomous driving takeover capability evaluation system includes a driving simulation device and a data processing device. The driving simulation device is used to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. The data processing device is used to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

2. The autonomous driving takeover capability evaluation system according to claim 1, characterized in that, The driving simulation device includes a driving scenario simulation module, a driving operation simulation module, and a non-driving behavior simulation module; The driving scenario simulation module is used to simulate and construct the in-vehicle scenario, driving road scenario, and driving weather scenario of the target vehicle based on the scenario information to be tested. The driving operation simulation module is used to simulate the driving operation scenario based on the test scenario information; The driving behavior simulation module is used to simulate the driver's in-vehicle non-driving behavior based on the test scenario information and the driver's historical non-driving behavior in historical driving information.

3. The autonomous driving takeover capability evaluation system according to claim 2, characterized in that, The driving scenario simulation module is used to simulate and construct the in-vehicle scenario of the target vehicle through the following steps: Based on the cabin interior information, control mechanism information, and instrument display information contained in the test scenario information, the interior style, control mechanism, and instrument placement are determined, and the in-vehicle scene of the target vehicle is simulated based on the interior style, control mechanism, and instrument placement.

4. The autonomous driving takeover capability evaluation system according to claim 2, characterized in that, The driving operation simulation module includes a steering wheel simulation unit, a force feedback pedal unit, and a degree-of-freedom simulation unit; the driving operation simulation module is used to simulate the driving operation scenario through the following steps: Based on the information of the test scenario, the steering wheel simulation unit is controlled to simulate steering wheel steering information; Based on the test scenario information, the force feedback pedal unit is controlled to simulate pedal force feedback information; Based on the information of the test scenario, the degree of freedom simulation unit is controlled to simulate the vehicle attitude change information during the driving process of the target vehicle; The driving operation scenario is simulated based on the steering wheel steering information, the pedal force feedback information, and the vehicle posture change information.

5. The autonomous driving takeover capability evaluation system according to claim 2, characterized in that, The driver's in-vehicle non-driving behavior includes at least one of the following: driver's auditory task behavior and driver's visual task behavior.

6. The autonomous driving takeover capability evaluation system according to claim 1, characterized in that, The data processing device includes a driving data acquisition module, a driver physiological information acquisition module, and a driver takeover ability evaluation module. The driving data acquisition module is used to collect steering wheel steering information, pedal force feedback information, and vehicle gear information in the first test scenario; The driver physiological information collection module is used to collect the driver's physiological information during the process of taking over the target vehicle; wherein, the physiological information includes at least one of the following: driver's electroencephalogram (EEG) information, driver's electromyogram (EMG) information, driver's electrodermal conductance (EDC) information, and driver's facial information; The driver takeover ability evaluation module is used to receive steering wheel steering information, pedal force feedback information, and vehicle gear information collected by the driving data acquisition module, and driver physiological information collected by the driver physiological information acquisition module. The steering wheel steering information, pedal force feedback information, vehicle gear information, and driver physiological information are input into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

7. The autonomous driving takeover capability evaluation system according to claim 1, characterized in that, The data processing device is used to input the driving data and the physiological information into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario. The data processing device is used for: The driving data and physiological information are input into a pre-trained takeover ability evaluation model, so that the takeover ability evaluation model determines the driver's takeover ability score based on the driving data and physiological information, and outputs the driver's takeover ability evaluation information based on the takeover ability score.

8. The autonomous driving takeover capability evaluation system according to claim 1, characterized in that, The driver's takeover capability evaluation information includes at least one of the following: having the ability to take over the vehicle, not having the ability to take over the vehicle, or being able to take over the vehicle under certain conditions.

9. The autonomous driving takeover capability evaluation system according to claim 1, characterized in that, The data processing device is also used for: In the second test scenario simulated by the driving simulation device, driving data of the driver driving the target vehicle and the driver's physiological information are collected, and the driving data and the physiological information are input into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information in the second test scenario. Based on the takeover capability evaluation information and the driver takeover capability label corresponding to the second test scenario, the takeover capability evaluation model is adjusted.

10. A method for evaluating the autonomous driving takeover capability of a vehicle, characterized in that, The autonomous driving takeover capability evaluation method is applied to the autonomous driving takeover capability evaluation system of the vehicle as described in any one of claims 1-9; The method for evaluating autonomous driving takeover capability includes: The driving simulation device is controlled to construct a first test scenario by simulating driving operation scenarios, in-vehicle scenarios of the target vehicle, driving road scenarios, driving weather scenarios, and non-driving behaviors of the driver in the vehicle. The data processing device is controlled to collect driving data of the driver driving the target vehicle and the driver's physiological information under the first test scenario simulated by the driving simulation device, and input the driving data and the physiological information into a pre-trained takeover ability evaluation model so that the takeover ability evaluation model outputs the driver's takeover ability evaluation information under the first test scenario.

Images