Method and device for evaluating takeover ability of automatic driving, electronic equipment and medium

Abstract

The present disclosure relates to the technical field of computers, in particular to the technical field of automatic driving, and more particularly to a method and device for evaluating the takeover ability of a safety officer of an automatic driving vehicle, an electronic device and a medium. The specific implementation scheme is as follows: collecting evaluation data for evaluating the takeover ability during the driving process of the automatic driving vehicle; calculating a dangerous area covered by the automatic driving vehicle during the takeover process based on the evaluation data; and generating a takeover ability evaluation result based on the dangerous area. The evaluation data collected by the vehicle during the driving process is used to calculate the dangerous area in the longitudinal direction of the automatic driving vehicle, and the takeover ability of the safety officer is quantified based on the size of the dangerous area, thereby realizing quantitative evaluation of the takeover ability of the safety officer.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to the field of autonomous driving technology, and more specifically to methods, apparatus, electronic devices, and media for assessing the takeover capabilities of personnel in autonomous vehicles. Background Technology

[0002] The purpose of autonomous driving road testing is to verify the rationality, safety, and stability of autonomous driving systems in terms of functionality, performance, safety, and stability. It verifies the maturity of data generation, transmission, and interaction technologies between vehicles and roads, provides verification results for virtual testing, and can also establish dynamic adaptive testing of vehicles through test scenarios. This is a crucial step for whether autonomous vehicles can be truly put into commercial production and will undoubtedly play a positive role in promoting it.

[0003] During the initial road testing phase of autonomous driving, to prevent road safety accidents caused by imperfect system strategies and engineering issues, safety drivers are initially assigned to provide a safety backup. They take over the autonomous vehicle upon identifying a collision risk. Currently, the assessment of the safety driver's takeover ability relies primarily on subjective human judgment, making it impossible to quantify this capability. Furthermore, as autonomous vehicles improve their capabilities and test data accumulates, the safety driver's responsibilities gradually decrease, and their position within the vehicle shifts from the driver's seat, front passenger, rear seat, and eventually to outside the vehicle. This leads to a decline in the safety driver's takeover ability, and there is currently no effective means to measure the impact of these changes in takeover ability on safety. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and medium for assessing the takeover capability of autonomous driving.

[0005] According to a first aspect of this disclosure, a method for assessing the takeover capability of autonomous driving is provided, comprising:

[0006] Collect assessment data during the operation of autonomous vehicles to evaluate their takeover capabilities;

[0007] Calculate the hazardous areas covered by the autonomous vehicle during the takeover process based on the assessment data;

[0008] The assessment results of takeover capability are generated based on the aforementioned hazardous areas.

[0009] According to a second aspect of this disclosure, an autonomous driving takeover capability assessment device is provided, comprising:

[0010] The data acquisition module is configured to collect assessment data during the operation of the autonomous vehicle to evaluate its takeover capability.

[0011] The calculation module is configured to calculate the hazardous areas covered by the autonomous vehicle during the takeover process based on the evaluation data;

[0012] The assessment module is configured to generate takeover capability assessment results based on the hazardous area.

[0013] According to a third aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described in any one of the above technical solutions.

[0014] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method according to any one of the above-described technical solutions.

[0015] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any one of the above-described technical solutions.

[0016] According to a sixth aspect of this disclosure, an autonomous vehicle is provided, including electronic devices as described in the above technical solutions.

[0017] This disclosure provides a method, device, electronic device, and medium for assessing the takeover capability of autonomous driving. By collecting assessment data during vehicle operation, it calculates the longitudinal danger zone of the autonomous vehicle and quantifies the takeover capability of the autonomous vehicle's personnel based on the size of the danger zone. This enables a quantitative assessment of the takeover capability of the personnel, thereby more accurately determining the impact of the personnel's takeover capability on the safety of the autonomous vehicle. On the other hand, it also facilitates the arrangement of matching personnel based on their takeover capability during road testing, reducing the incidence of safety accidents during road testing.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0019] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0020] Figure 1 This is a schematic diagram of the steps of the autonomous driving takeover capability assessment method in the embodiments of this disclosure;

[0021] Figure 2 This is a schematic diagram of the first danger zone in front of the autonomous vehicle in an embodiment of this disclosure;

[0022] Figure 3 This is a schematic diagram of the second danger zone in front of the autonomous vehicle in an embodiment of this disclosure;

[0023] Figure 4 This is a schematic block diagram of the autonomous driving takeover capability assessment device in an embodiment of this disclosure;

[0024] Figure 5 This is a schematic block diagram of an example electronic device in an embodiment of this disclosure. Detailed Implementation

[0025] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0026] Existing technologies in road testing of autonomous vehicles can only identify the takeover methods employed by the operator, subjectively evaluating their takeover ability. This remains at the level of the common perception that more takeover methods are safer than fewer, and cannot provide a data-driven assessment. To address the technical problem of insufficient objectivity in takeover ability evaluation due to the reliance on manual assessment of the operator's capabilities in existing technologies, this disclosure provides a method for evaluating the takeover ability of autonomous vehicles, such as... Figure 1As shown, the process includes: Step S101, collecting assessment data during the autonomous vehicle's operation to evaluate its takeover capability. This assessment data may include various data collected during the autonomous vehicle's operation, such as vehicle speed, acceleration, rate of change of acceleration, and time. Step S102, calculating the hazardous area covered by the autonomous vehicle during the takeover process based on the assessment data. The takeover process refers to the period from the moment the takeover personnel take over the autonomous vehicle to the end of the takeover. Based on the assessment data, the hazardous areas where the autonomous vehicle may collide forward or rear-end, can be calculated. The takeover personnel can be a safety officer during road testing or a driver during normal driving. In this embodiment, it is used to assess the safety officer's takeover capability. During the takeover process, the smaller the hazardous area covered (i.e., the smaller the area swept by the autonomous vehicle from the moment of takeover to the end of the takeover), the stronger the takeover capability of the personnel. Step S103, generating a takeover capability assessment result based on the hazardous area. The area of ​​the hazardous area can be converted into a corresponding score or level as the assessment result, thus visually demonstrating the takeover capability of the personnel.

[0027] The takeover capability assessment method in this embodiment is mainly used to evaluate the safety driver's takeover capability during road testing. In certain scenarios, it can also be used to evaluate the driver's takeover capability. Road testing scenarios for autonomous vehicles include, but are not limited to, parking and starting at the side of the road, crossing pedestrian crossings, turning right at a traffic light-controlled intersection, turning left at a traffic light-controlled intersection, going straight at a traffic light-controlled intersection, turning left at an intersection without traffic lights, passing bus stops, stopping and yielding at intersections, passing roundabouts, driving on highways, passing through tunnels, and passing through elevated roads, etc. During road testing, autonomous vehicles complete the above test items to verify their ability to recognize traffic signals, their ability to drive safely and courteously, their ability to navigate complex traffic environments, and their ability to cooperate with other road users.

[0028] During road testing, to avoid safety accidents caused by the immaturity of autonomous driving system technology, it is necessary to have qualified personnel with appropriate takeover capabilities. For example, autonomous driving is currently divided into several levels, L0-L5: L0 is purely manual driving; L1 is driving automation; L2 is assisted driving; L3 is automated assisted driving; L4 is autonomous driving; and L5 is driverless driving. Different levels of autonomous driving have different requirements for the takeover capabilities of the driver or safety operator. The higher the level, the higher the degree of automation, and the lower the requirement for the takeover capability of the personnel. For lower-level autonomous vehicles, the requirements for the takeover capability of the personnel are higher. Therefore, quantitatively assessing the capabilities of takeover personnel is essential to avoid the subjectivity of human evaluation, reduce the occurrence of safety accidents, provide quantitative basis for evaluating different types of takeover personnel, more clearly demonstrate takeover capabilities, and provide a basis for assessing takeover capabilities and safety risks at different stages of autonomous driving road testing.

[0029] As an optional implementation, the evaluation data includes at least one of the following: the speed of the autonomous vehicle; the deceleration of the autonomous vehicle; the width of the autonomous vehicle; and the rate of change of acceleration of the autonomous vehicle. Based on the above evaluation data, the danger zone swept by the autonomous vehicle from the moment of takeover to the end of takeover is calculated, thereby generating an evaluation result based on the area of ​​the danger zone.

[0030] As an optional implementation, step S102, which calculates the hazardous area covered by the autonomous vehicle during the takeover process based on the evaluation data, includes: determining the takeover operation range based on the position of the takeover personnel on the autonomous vehicle; and calculating the corresponding hazardous area based on the takeover operation range. Takeover personnel generally have three methods to control the vehicle from inside: brake, accelerator, and steering wheel. In actual testing, the appropriate method will be selected to take over the vehicle according to different risk scenarios, allowing the vehicle to escape the dangerous state. Braking and accelerator are longitudinal controls, while steering wheel is a lateral control. This embodiment only involves the two longitudinal control takeover methods: brake takeover and accelerator takeover. To identify and quantify the two takeover methods, it is necessary to study and clarify the typical scenarios, safety definition methods, and safety range expression methods for each takeover method. Through research on a large amount of takeover data from takeover personnel, the typical scenarios and characteristics of the two takeover methods are shown in Table 1.

[0031]

[0032] Table 1. Characteristics of Brake and Throttle Control Lines

[0033] Furthermore, the location of the person taking over the vehicle also determines the scope of their takeover operation: when the person taking over is in the driver's seat, both the accelerator and the brake can be used as takeover tools. As shown in Table 1, the braking takeover capability determines the area of ​​the danger zone in front of the vehicle, i.e. Figure 2 The shaded area represents the first danger zone S1. The throttle control capability determines the size of the danger zone behind the vehicle. Figure 3 The shaded area indicates the second danger zone, S2. Therefore, both S1 and S2 should be considered when assessing takeover capability. When the takeover operator is in the passenger seat and cannot use the accelerator, but can only use the linked auxiliary brake, the avoidable danger zone is only S1, excluding S2. When the takeover operator is in another vehicle outside the car and uses remote brake takeover, the avoidable danger zone is also S1. However, due to communication distance limitations and efficiency losses from indirect braking, the value of S1 will increase, and the risk will increase. That is, when the takeover operator is in a position other than the driver's seat, their takeover operation range does not include accelerator takeover. The takeover operation range of the takeover operator varies depending on their position, therefore the assessment indicators used are also different. Therefore, it is necessary to first determine the current position of the takeover operator, then calculate the corresponding assessment indicators, and thus change the assessment method based on the change in the takeover operator's position, thereby improving the accuracy of the assessment results.

[0034] As an optional implementation method, such as Figure 2 As shown, the calculation of the corresponding danger zone based on the takeover operation range includes: in response to the takeover operation range being brake takeover, calculating the first danger zone in front of the autonomous vehicle; and obtaining the area of ​​the first danger zone by multiplying the first travel distance of the autonomous vehicle from the moment the brake takeover is triggered to the moment the speed is reduced to zero by the width of the autonomous vehicle.

[0035] Braking takeover primarily mitigates the longitudinal forward collision risk of autonomous vehicles. The forward danger zone is defined as the area swept by the vehicle when it decelerates from its initial speed (i.e., the speed at which the brakes are applied) to zero after the takeover operator. The danger zone that braking takeover can avoid is as follows: Figure 1 As shown. Figure 1 In the diagram, C represents the autonomous vehicle, and the shaded area represents the danger zone S1 where the operator can take over braking and avoid obstacles. For example, assuming the vehicle's deceleration is constant, the danger zone S1 can be represented as:

[0036]

[0037] Where S1 represents the first danger zone; V represents the speed at the moment the takeover personnel take over braking (i.e., the moment braking takeover is triggered); a represents the maximum emergency braking deceleration (i.e., the maximum deceleration after the takeover personnel initiate braking); L1 represents the first travel distance (i.e., the distance the vehicle travels from the moment braking takeover is triggered until the speed decreases to 0); and B represents the width of the autonomous vehicle. The area of ​​the danger zone S1 in front of the vehicle can be calculated using the above formula. Therefore, the smaller the area of ​​the danger zone during braking takeover, the more effective the takeover measures are. It can be seen from the formula that the greater the braking force applied by the takeover personnel, the greater the deceleration 'a', and the smaller the danger zone S1. The slower the vehicle speed at the time of takeover, the smaller the danger zone S1. The calculation method in this embodiment allows for a quantitative assessment of the takeover personnel's ability to take over, resulting in a more objective evaluation.

[0038] As an optional implementation, calculating the danger zone based on the takeover operation range includes: in response to the takeover operation range being throttle takeover, calculating a second danger zone behind the autonomous vehicle; and obtaining the area of ​​the second danger zone S2 by multiplying the second travel distance L2 from the moment the autonomous vehicle suddenly brakes until its deceleration becomes zero by the width B of the autonomous vehicle. As shown in Table 1, the throttle takeover method is mainly to avoid the risk of rear-end collisions. When the takeover personnel find that the autonomous vehicle suddenly brakes due to a malfunction or program abnormality, even when there are no obstacles or other braking factors in front, the vehicle's deceleration is negative, which can easily cause rear-end collisions. In this case, the takeover personnel should take over the throttle in time. After the takeover personnel press the throttle, the deceleration gradually changes from negative to positive until the vehicle's deceleration changes from negative to zero, at which point the takeover ends.

[0039] Throttle control primarily addresses the risk of rear-end collisions caused by sudden or excessive braking in autonomous vehicles. The second danger zone is defined as the area swept across during sudden braking as the vehicle's deceleration changes from negative to zero; that is, the transition from deceleration to acceleration. At this point, the risk of sudden braking by the autonomous driving system can be considered to have disappeared. The danger zone that can be avoided by the operator taking over the throttle is as follows: Figure 3 As shown. Figure 3 In the image, C represents the autonomous vehicle, and the shaded area represents the second danger zone S2 that can be avoided by the operator taking over the accelerator. Assuming the deceleration process is a uniformly accelerated deceleration motion, the second danger zone S2 can be represented as:

[0040]

[0041] Where d(t) represents the calculus over time; L0 represents the initial distance during emergency braking; v0 represents the initial velocity during emergency braking; a0 represents the initial maximum deceleration during emergency braking; j represents the deceleration (i.e., the rate of change of acceleration) gained when the operator presses the accelerator. In this embodiment, j is assumed to be a constant value, and we can obtain:

[0042]

[0043]

[0044]

[0045] Where L2 represents the distance traveled by the autonomous vehicle from the moment it suddenly brakes until its deceleration becomes zero, ΔL = L(t) - L0; B represents the width of the autonomous vehicle. It is evident that the smaller the danger zone of throttle intervention, the more effective the intervention method. From the above formula, it can be seen that the greater the force with which the operator presses the accelerator, the greater the resulting deceleration j, and the smaller the second danger zone S2. Similarly, the smaller the vehicle's deceleration a0 during intervention, the smaller the second danger zone S2. Through the above technical solution, the rearward collision danger zone of the vehicle can be further calculated based on the evaluation data collected during driving. The area of ​​the danger zone can be used to quantify the intervention capability of the operator, improving the objectivity of the intervention assessment.

[0046] As an optional implementation, calculating the corresponding danger zone based on the takeover operation range includes: responding to the takeover operation range including brake takeover and throttle takeover, calculating a first danger zone S1 forward of the autonomous vehicle and a second danger zone S2 backward of the autonomous vehicle; obtaining the area of ​​the first danger zone S1 by multiplying the first travel distance of the autonomous vehicle from the moment the brake takeover is triggered to when the speed decreases to zero by the width of the autonomous vehicle; obtaining the area of ​​the second danger zone S2 by multiplying the second travel distance L2 from the moment the autonomous vehicle brakes suddenly to when the deceleration becomes zero by the width B of the autonomous vehicle. In this embodiment, if the takeover operator is in the driver's seat, both their brake takeover capability and their throttle takeover capability must be evaluated.

[0047] This disclosure proposes a quantitative evaluation method for takeover techniques employed by personnel. By defining avoidable danger zones during takeover, a mathematical model of the takeover process is constructed, a method for representing these danger zones is provided, and the impact of different parameters is analyzed. This method can quantitatively measure the differences in different takeover techniques employed by personnel, as well as the differences in reaction and driving abilities among personnel. This method can provide a basis for safety assessments at different stages of autonomous driving road testing.

[0048] This disclosure provides an autonomous driving takeover capability assessment device 400, such as... Figure 4As shown, the system includes: a data acquisition module 401, configured to acquire assessment data for evaluating the takeover capability of the autonomous vehicle during its operation. The assessment data may include various data collected during the autonomous vehicle's operation, such as vehicle speed, acceleration, rate of change of acceleration, and time; a calculation module 402, configured to calculate the hazardous areas covered by the autonomous vehicle during the takeover process based on the assessment data. The takeover process refers to the period from the moment the takeover personnel take over the autonomous vehicle to the end of the takeover. Based on the assessment data, the system can calculate the hazardous areas where the autonomous vehicle may collide forward or rear-end. The takeover personnel can be a safety officer during road testing or a driver during normal driving; in this embodiment, it is used to assess the safety officer's takeover capability. During the takeover process, the smaller the hazardous area covered—that is, the smaller the area swept by the autonomous vehicle from the moment of takeover to the end of takeover—the stronger the takeover capability of the personnel. An assessment module 403, configured to generate a takeover capability assessment result based on the hazardous areas, can convert the area of ​​the hazardous areas into corresponding scores or levels as the assessment result, thus intuitively demonstrating the takeover capability of the personnel.

[0049] The takeover capability assessment device in this embodiment is mainly used to assess the takeover capability of the personnel taking over during road tests. In certain scenarios, it can also assess the takeover capability of the driver. Road test scenarios for autonomous vehicles include, but are not limited to, parking and starting at the side of the road, crossing pedestrian crossings, turning right at a traffic light-controlled intersection, turning left at a traffic light-controlled intersection, going straight at a traffic light-controlled intersection, turning left at an intersection without traffic lights, passing bus stops, stopping and yielding at intersections, passing roundabouts, driving on highways, passing through tunnels, and passing through elevated roads, etc. During road tests, autonomous vehicles complete the above test items to verify their ability to recognize traffic signals, their ability to drive safely and courteously, their ability to navigate complex traffic environments, and their ability to cooperate with other road users.

[0050] During road testing, to avoid safety accidents caused by the immaturity of autonomous driving system technology, it is necessary to have qualified personnel with appropriate takeover capabilities. For example, autonomous driving is currently divided into several levels, L0-L5: L0 is purely manual driving; L1 is driving automation; L2 is assisted driving; L3 is automated assisted driving; L4 is autonomous driving; and L5 is driverless driving. Different levels of autonomous driving have different requirements for the takeover capabilities of the driver or safety operator. The higher the level, the higher the degree of automation, and the lower the requirement for the takeover capability of the personnel. For lower-level autonomous vehicles, the requirements for the takeover capability of the personnel are higher. Therefore, quantitatively assessing the capabilities of takeover personnel is essential to avoid the subjectivity of human evaluation, reduce the occurrence of safety accidents, provide quantitative basis for evaluating different types of takeover personnel, more clearly demonstrate takeover capabilities, and provide a basis for assessing takeover capabilities and safety risks at different stages of autonomous driving road testing.

[0051] As an optional implementation, the evaluation data includes at least one of the following: the speed of the autonomous vehicle; the deceleration of the autonomous vehicle; the width of the autonomous vehicle; and the rate of change of acceleration of the autonomous vehicle. Based on the above evaluation data, the danger zone swept by the autonomous vehicle from the moment of takeover to the end of takeover is calculated, thereby generating an evaluation result based on the area of ​​the danger zone.

[0052] As an optional implementation, the calculation module 402 calculates the hazardous area covered by the autonomous vehicle during the takeover process based on the evaluation data, including: determining the takeover operation range based on the position of the takeover personnel on the autonomous vehicle; and calculating the corresponding hazardous area based on the takeover operation range. Takeover personnel generally have three methods to control the vehicle from inside: brake, accelerator, and steering wheel. In actual testing, the appropriate method will be selected to take over the vehicle according to different risk scenarios, so that the vehicle can escape the dangerous state. Braking and accelerator are longitudinal controls, while steering wheel is a lateral control. This embodiment only involves the two longitudinal control takeover methods, namely brake takeover and accelerator takeover. To identify and quantify the two takeover methods, it is necessary to study and clarify the typical scenarios, safety definition methods, and safety range expression methods for each takeover method. Through the study of a large amount of takeover data from takeover personnel, the typical scenarios and characteristics of the two takeover methods are shown in Table 1.

[0053] Furthermore, the location of the person taking over the vehicle also determines the scope of their takeover operation: when the person taking over is in the driver's seat, both the accelerator and the brake can be used as takeover tools. As shown in Table 1, the braking takeover capability determines the area of ​​the danger zone in front of the vehicle, i.e. Figure 2 The shaded area represents the first danger zone S1. The throttle control capability determines the size of the danger zone behind the vehicle. Figure 3The shaded area indicates the second danger zone, S2. Therefore, both S1 and S2 should be considered when assessing takeover capability. When the takeover operator is in the passenger seat and cannot use the accelerator, but can only use the linked auxiliary brake, the avoidable danger zone is only S1, excluding S2. When the takeover operator is in another vehicle outside the car and uses remote braking to take over, the avoidable danger zone is also S1, but due to communication distance limitations and efficiency losses from indirect braking, the value of S1 will increase, and the risk will increase. The takeover operator's operational range varies depending on their position, therefore the assessment indicators used will also differ. It is necessary to first determine the current position of the takeover operator, then calculate the corresponding assessment indicators, and thus adjust the assessment method based on changes in the operator's position to improve the accuracy of the assessment results.

[0054] As an optional implementation method, such as Figure 2 As shown, the calculation module 402 calculates the corresponding danger zone based on the takeover operation range, including: in response to the takeover operation range being brake takeover, calculating the first danger zone in front of the autonomous vehicle; and obtaining the area of ​​the first danger zone by multiplying the first travel distance of the autonomous vehicle from the moment the brake takeover is triggered to the moment the speed is reduced to zero by the width of the autonomous vehicle.

[0055] Braking takeover primarily mitigates the longitudinal forward collision risk of autonomous vehicles. The forward danger zone is defined as the area swept by the vehicle when it decelerates from its initial speed (i.e., the speed at which the brakes are applied) to zero after the takeover operator. The danger zone that braking takeover can avoid is as follows: Figure 1 As shown. Figure 1 In the diagram, C represents the autonomous vehicle, and the shaded area represents the danger zone S1 where the operator can take over braking and avoid obstacles. For example, assuming the vehicle's deceleration is constant, the danger zone S1 can be represented as:

[0056]

[0057] Where S1 represents the first danger zone; V represents the speed at the moment of brake takeover triggering; a represents the maximum emergency braking deceleration (i.e., the maximum deceleration after the takeover personnel initiate brake takeover); L1 represents the first travel distance (i.e., the distance the vehicle travels from the moment the takeover personnel initiate brake takeover until the speed decreases to 0); and B represents the width of the autonomous vehicle. The area of ​​the danger zone S1 in front of the vehicle can be calculated using the above formula. Therefore, the smaller the area of ​​the danger zone during brake takeover, the more effective the takeover measures are. It can be seen from the formula that the greater the braking force applied by the takeover personnel, the greater the deceleration 'a', and the smaller the danger zone S1. The slower the vehicle speed at the time of takeover, the smaller the danger zone S1. The calculation method in this embodiment allows for a quantitative assessment of the takeover personnel's ability to take over, resulting in a more objective evaluation.

[0058] As an optional implementation, the calculation module 402 calculates the danger zone based on the takeover operation range, including: in response to the takeover operation range being throttle takeover, calculating the second danger zone behind the autonomous vehicle; and obtaining the area of ​​the second danger zone S2 by multiplying the second travel distance L2 from the moment the autonomous vehicle suddenly brakes until the deceleration becomes zero by the width B of the autonomous vehicle. As shown in Table 1, the throttle takeover method is mainly to avoid the risk of rear-end collisions. When the takeover personnel find that the autonomous vehicle suddenly brakes due to a malfunction or program abnormality, even when there are no obstacles or other braking factors in front, the vehicle's deceleration is negative, which can easily cause rear-end collisions. In this case, the takeover personnel should take over the throttle in time. After the takeover personnel press the throttle, the deceleration gradually changes from negative to positive until the vehicle's deceleration changes from negative to 0, at which point the takeover ends.

[0059] Throttle control primarily addresses the risk of rear-end collisions caused by sudden or excessive braking in autonomous vehicles. The second danger zone is defined as the area swept across during sudden braking as the vehicle's deceleration changes from negative to zero; that is, the transition from deceleration to acceleration. At this point, the risk of sudden braking by the autonomous driving system can be considered to have disappeared. The danger zone that can be avoided by the operator taking over the throttle is as follows: Figure 3 As shown. Figure 3 In the image, C represents the autonomous vehicle, and the shaded area represents the second danger zone S2 that can be avoided by the operator taking over the accelerator. Assuming the deceleration process is a uniformly accelerated deceleration motion, the second danger zone S2 can be represented as:

[0060]

[0061] Where d(t) represents the calculus over time; L0 represents the initial distance during emergency braking; v0 represents the initial velocity during emergency braking; a0 represents the initial maximum deceleration during emergency braking; j represents the deceleration (i.e., the rate of change of acceleration) gained when the operator presses the accelerator. In this embodiment, j is assumed to be a constant value, and we can obtain:

[0062]

[0063]

[0064]

[0065] Where L2 represents the distance traveled by the autonomous vehicle from the moment it suddenly brakes until its deceleration becomes zero, ΔL = L(t) - L0; B represents the width of the autonomous vehicle. It is evident that the smaller the danger zone of throttle intervention, the more effective the intervention method. From the above formula, it can be seen that the greater the force with which the operator presses the accelerator, the greater the resulting deceleration j, and the smaller the second danger zone S2. Similarly, the smaller the vehicle's deceleration a0 during intervention, the smaller the second danger zone S2. Through the above technical solution, the rearward collision danger zone of the vehicle can be further calculated based on the evaluation data collected during driving. The area of ​​the danger zone can be used to quantify the intervention capability of the operator, improving the objectivity of the intervention assessment.

[0066] As an optional implementation, the calculation module 402 calculates the corresponding danger zone based on the takeover operation range, including: in response to the takeover operation range including brake takeover and throttle takeover, calculating a first danger zone S1 forward of the autonomous vehicle and a second danger zone S2 backward of the autonomous vehicle; obtaining the area of ​​the first danger zone S1 by multiplying the first travel distance of the autonomous vehicle from the moment the brake takeover is triggered to when the speed decreases to zero by the width of the autonomous vehicle; obtaining the area of ​​the second danger zone S2 by multiplying the second travel distance L2 from the moment the autonomous vehicle brakes suddenly to when the deceleration becomes zero by the width B of the autonomous vehicle. In this embodiment, if the takeover operator is in the driver's seat, both their brake takeover capability and their throttle takeover capability need to be evaluated.

[0067] This disclosure proposes a quantitative evaluation device for takeover techniques employed by personnel. By defining avoidable danger zones during takeover, a mathematical model of the takeover process is constructed, a method for representing these danger zones is provided, and the influence of different parameters is analyzed. This allows for the quantitative measurement of differences in different takeover techniques employed by personnel, as well as differences in reaction capabilities and driving abilities among personnel taking over different roles. This device can provide a basis for safety assessments at different stages of autonomous driving road testing.

[0068] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0069] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0070] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0071] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0072] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0073] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the takeover capability assessment method. For example, in some embodiments, the takeover capability assessment method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the takeover capability assessment method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the takeover capability assessment method by any other suitable means (e.g., by means of firmware).

[0074] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0076] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0078] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0079] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0080] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0081] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for assessing the takeover capability of autonomous driving, comprising: Collect assessment data during the operation of autonomous vehicles to evaluate the takeover capabilities of personnel. Calculate the hazardous areas covered by the autonomous vehicle during the takeover process based on the assessment data; Based on the assessment results of the takeover capability of the aforementioned hazardous area; Specifically, calculating the hazardous area covered by the autonomous vehicle during the takeover process based on the assessment data includes: The scope of the takeover operation is determined based on the position of the takeover personnel on the autonomous vehicle. In response to the control operation range including brake control and throttle control, a first danger zone in front of the autonomous vehicle and a second danger zone behind the autonomous vehicle are calculated; The area of ​​the first danger zone is obtained by multiplying the first travel distance of the autonomous vehicle from the moment the brake take-off is triggered to the moment the speed is reduced to zero by the width of the autonomous vehicle; The area of ​​the second danger zone is obtained by multiplying the second travel distance from the moment the autonomous vehicle brakes suddenly until its deceleration becomes zero by the width of the autonomous vehicle.

2. The method according to claim 1, wherein, The evaluation data includes at least one of the following: the speed of the autonomous vehicle; the deceleration of the autonomous vehicle; the width of the autonomous vehicle; and the rate of change of acceleration of the autonomous vehicle.

3. The method according to claim 1, wherein, Determining the scope of the takeover operation based on the position of the takeover personnel on the autonomous vehicle includes: In response to the person taking over being in the driver's position of the autonomous vehicle, the scope of the takeover operation includes brake takeover and accelerator takeover; In response to the takeover personnel being located outside the driver's position, the takeover operation range is brake takeover.

4. The method according to claim 3, wherein, The method further includes: In response to the takeover operation range being the brake takeover, the first danger zone in front of the autonomous vehicle is calculated; The area of ​​the first danger zone is obtained by multiplying the first distance traveled by the autonomous vehicle from the moment the brake take-off is triggered until the speed decreases to zero by the width of the autonomous vehicle.

5. The method according to claim 1 or 4, before obtaining the area of ​​the first danger zone by multiplying the first travel distance of the autonomous vehicle from the moment the brake take-off is triggered to the moment the speed decreases to zero by the width of the autonomous vehicle, the method further includes: The first travel distance is obtained by dividing the square of the speed at the moment the brake take-off is triggered by twice the maximum emergency braking deceleration.

6. The method according to claim 1, wherein, Before calculating the area of ​​the second danger zone by multiplying the second travel distance from the moment the autonomous vehicle brakes suddenly to the moment its deceleration becomes zero by the width of the autonomous vehicle, the method further includes: The second travel distance is obtained by dividing the cube of the maximum emergency braking deceleration by the square of the rate of change of acceleration after triggering throttle control, and then multiplying by two-thirds.

7. An autonomous driving takeover capability assessment device, comprising: The data acquisition module is configured to collect assessment data during the operation of the autonomous vehicle to evaluate the takeover capabilities of the personnel in charge. The calculation module is configured to calculate the hazardous area covered by the autonomous vehicle during the takeover process based on the evaluation data. Specifically, the calculation module is used to determine the takeover operation range based on the position of the takeover personnel on the autonomous vehicle. In response to the control operation range including brake control and throttle control, a first danger zone in front of the autonomous vehicle and a second danger zone behind the autonomous vehicle are calculated; The area of ​​the first danger zone is obtained by multiplying the first travel distance of the autonomous vehicle from the moment the brake take-off is triggered to the moment the speed decreases to zero by the width of the autonomous vehicle; the area of ​​the second danger zone is obtained by multiplying the second travel distance of the autonomous vehicle from the moment the brake take-off is triggered to the moment the speed decreases to zero by the width of the autonomous vehicle. The assessment module is configured to generate takeover capability assessment results based on the hazardous area.

8. The apparatus according to claim 7, wherein, The evaluation data includes at least one of the following: the speed of the autonomous vehicle; the deceleration of the autonomous vehicle; the width of the autonomous vehicle; and the rate of change of acceleration of the autonomous vehicle.

9. The apparatus according to claim 7, wherein, The calculation module determines the takeover operation range based on the position of the takeover personnel on the autonomous vehicle, including: In response to the person taking over being in the driver's position of the autonomous vehicle, the scope of the takeover operation includes brake takeover and accelerator takeover; In response to the takeover personnel being located outside the driver's position, the takeover operation range is brake takeover.

10. The apparatus according to claim 9, wherein, The computing module is also used for: In response to the takeover operation range being the brake takeover, the first danger zone in front of the autonomous vehicle is calculated; The area of ​​the first danger zone is obtained by multiplying the first distance traveled by the autonomous vehicle from the moment the brake take-off is triggered until the speed decreases to zero by the width of the autonomous vehicle.

11. The apparatus of claim 7 or 10, further comprising, before the calculation module obtains the area of ​​the first danger zone by multiplying the first travel distance of the autonomous vehicle from the moment the brake take-off is triggered to the moment the speed is reduced to zero by the width of the autonomous vehicle: The first travel distance is obtained by dividing the square of the speed at the moment the brake take-off is triggered by twice the maximum emergency braking deceleration.

12. The apparatus according to claim 7, wherein, Before the calculation module calculates the area of ​​the second danger zone by multiplying the second travel distance from the moment the autonomous vehicle brakes suddenly to the moment its deceleration becomes zero by the width of the autonomous vehicle, it further includes: The second travel distance is obtained by dividing the cube of the maximum emergency braking deceleration by the square of the rate of change of acceleration after triggering throttle control, and then multiplying by two-thirds.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

16. An autonomous vehicle, including the electronic equipment as claimed in claim 13.

Images