Driving takeover control method

Abstract

The invention discloses a driving takeover control method. The method comprises the following steps: generating a driving takeover request instruction based on driving scene information; in response to the driving takeover request instruction, acquiring input torque information of a driver to a steering wheel; performing risk analysis based on the driving scene information to obtain scene risk information; correcting the input torque information based on the driving scene information and the scene risk information to obtain corrected torque information; and the vehicle is controlled to be switched to a driver take-over mode according to the corrected assistance torque. A torque limiting strategy is set based on different driving scene information, so that the assistance torque of the automatic driving controller attenuates the input torque according to different driving scenes, steering abrupt feeling and steering wheel violent hitting are avoided, the control force of a driver to a vehicle is improved, and the driving safety is improved. The problem that the control information of the vehicle intelligent driving system is not matched with the input information of the driver in the takeover process of the driver is solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a control method for driving takeover. Background Art

[0002] In the field of autonomous driving, more and more vehicles have the function of autonomous driving or assisted driving. In the process of the driver taking over the autonomous vehicle, in the scenario of human-vehicle co-driving, there is a conflict between the system and the driver, resulting in uneven vehicle control and a poor actual driving experience.

[0003] In the prior art, after the intelligent driving system sends a request to take over signal to the driver, the driver responds to the request to take over signal and applies lateral control torque, and the intelligent driving system performs coefficient correction on the lateral control torque. Since no judgment is made on the scenario during the takeover process, there is a problem of mismatch between the control information of the vehicle's intelligent driving system and the driver's input information. Summary of the invention

[0004] In order to solve the problems of the prior art, the present application provides a control method for driving takeover, which sets a torque limitation strategy based on different driving scenario information, so that the assist torque of the automatic driving controller attenuates the input torque according to different driving scenarios, avoids abrupt steering and sudden steering wheel movements, improves the driver's control over the vehicle, and solves the problem of mismatch between the control information of the vehicle intelligent driving system and the driver's input information during the driver takeover process.

[0005] According to one aspect of the present application, a driving takeover control method is provided, the method comprising:

[0006] generating a driving takeover request instruction based on the driving scenario information;

[0007] In response to the driving takeover request instruction, obtaining input torque information of the driver to the steering wheel;

[0008] Performing risk analysis based on the driving scenario information to obtain scenario risk information;

[0009] Correcting the input torque information based on the driving scene information and the scene risk information to obtain corrected torque information;

[0010] The vehicle is controlled to switch to a driver takeover mode according to the corrected assist torque.

[0011] In a possible implementation, the generating a driving takeover request instruction based on the driving scenario information includes:

[0012] Acquire the driving scene information, and determine whether the vehicle meets a preset trigger takeover condition according to the driving scene information:

[0013] When the driving scene information satisfies the preset trigger takeover condition, generating an activation takeover instruction, and determining that the activation takeover instruction is the driving takeover request instruction;

[0014] The method further comprises:

[0015] When the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

[0016] In a possible implementation, the method further includes:

[0017] Constructing a first preset scenario of the vehicle entering a boundary of an autonomous driving operation design domain;

[0018] Constructing a second preset scenario where a merging occurs on the road where the vehicle is located;

[0019] Constructing a third preset scenario where a pedestrian appears on the road where the vehicle is located;

[0020] Constructing a fourth preset scenario in which a temporary construction area appears on the road where the vehicle is located;

[0021] Constructing a fifth preset scenario that is beyond the sensor's processing range;

[0022] Constructing a sixth preset scenario in which a single point failure occurs in the system of the vehicle;

[0023] A preset scene set is constructed according to the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene.

[0024] In a possible implementation, judging whether the vehicle meets a preset trigger takeover condition according to the driving scene information includes:

[0025] Querying the preset scene set based on the driving scene information to obtain a query result;

[0026] When the query result indicates that the driving scene information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

[0027] In a possible implementation, the method further includes:

[0028] Determine the risk level corresponding to the risk scenario according to the risk scenario;

[0029] If the risk scenario is a highway scenario, determining the risk level of the rural road scenario as the first risk level;

[0030] If the risk scenario is a rural road scenario, determining the risk level of the rural road scenario to be a second risk level;

[0031] If the risk scenario is a city street scenario, determining the risk level of the city street scenario to be the third risk level;

[0032] If the risk scenario is a complex intersection scenario, determining the risk level of the complex intersection scenario to be a fourth risk level;

[0033] If the risk scenario is a severe weather scenario, determining the risk level of the severe weather scenario to be the fifth risk level;

[0034] Determining a risk factor corresponding to the risk scenario based on the risk level corresponding to the risk scenario;

[0035] The first risk level is lower than the second risk level, the second risk level is lower than the third risk level, the third risk level is lower than the fourth risk level, and the fourth risk level is lower than the fifth risk level.

[0036] In a possible implementation, determining the risk coefficient corresponding to the risk scenario based on the risk level corresponding to the risk scenario includes:

[0037] If the risk level is the first risk level, determining the risk coefficient corresponding to the risk scenario as the first risk coefficient;

[0038] If the risk level is the second risk level, determining the risk coefficient corresponding to the risk scenario as the second risk coefficient;

[0039] If the risk level is the third risk level, determining the risk coefficient corresponding to the risk scenario as the third risk coefficient;

[0040] If the risk level is the fourth risk level, determining the risk coefficient corresponding to the risk scenario as the fourth risk coefficient;

[0041] If the risk level is the fifth risk level, determining the risk coefficient corresponding to the risk scenario as the fifth risk coefficient;

[0042] The method further comprises:

[0043] According to the relationship between the risk scenario and the risk coefficient corresponding to the risk scenario, an association relationship library between the risk scenario and the risk coefficient is constructed.

[0044] In a possible implementation, the driving scenario information further includes risk scenario information, and the risk scenario information is at least one of the urban street scenario, the rural road scenario, the highway scenario, the complex intersection scenario, and the severe weather scenario.

[0045] The performing risk analysis on the driving scene information to obtain the scene risk information includes:

[0046] Based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information;

[0047] Determine the risk coefficient corresponding to the risk scenario information as the scenario risk information.

[0048] In a possible implementation, the correcting the input torque information based on the driving scenario information and the scenario risk information to obtain the corrected torque information includes:

[0049] Acquiring initial assist torque information corresponding to the driving scene information;

[0050] Determining an assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information;

[0051] Calculating the product of the assist torque attenuation coefficient and the initial assist torque information to obtain the attenuated assist torque;

[0052] The input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

[0053] In a possible implementation, determining the assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information includes:

[0054] The product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient.

[0055] In a possible implementation, the correcting the input torque information based on the attenuated assist torque to obtain the corrected torque information includes:

[0056] The input torque information is subtracted from the attenuation assist torque to obtain the correction torque information.

[0057] In another aspect, a control device for driving takeover is provided, the device comprising:

[0058] An instruction generation module, used to generate a driving takeover request instruction based on driving scenario information;

[0059] An input torque information acquisition module, used for acquiring the driver's input torque information on the steering wheel in response to the driving takeover request instruction;

[0060] A risk analysis module, used to perform risk analysis based on the driving scenario information to obtain scenario risk information;

[0061] A correction processing module, used for performing correction processing on the input torque information based on the driving scene information and the scene risk information to obtain corrected torque information;

[0062] A control module is used to control the vehicle to switch to a driver takeover mode according to the corrected assist torque.

[0063] In a possible implementation, the instruction generation module is used to:

[0064] Acquire the driving scene information, and determine whether the vehicle meets a preset trigger takeover condition according to the driving scene information:

[0065] When the driving scene information satisfies the preset trigger takeover condition, generating an activation takeover instruction, and determining that the activation takeover instruction is the driving takeover request instruction;

[0066] The instruction generation module is further used for:

[0067] When the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

[0068] In a possible implementation manner, the device further includes a preset scene set module, and the preset scene set module is used to:

[0069] Constructing a first preset scenario of the vehicle entering a boundary of an autonomous driving operation design domain;

[0070] Constructing a second preset scenario where a merging occurs on the road where the vehicle is located;

[0071] Constructing a third preset scenario where a pedestrian appears on the road where the vehicle is located;

[0072] Constructing a fourth preset scenario in which a temporary construction area appears on the road where the vehicle is located;

[0073] Constructing a fifth preset scenario that is beyond the sensor's processing range;

[0074] Constructing a sixth preset scenario in which a single point failure occurs in the system of the vehicle;

[0075] A preset scene set is constructed according to the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene.

[0076] In a possible implementation, the device further includes a takeover triggering judgment module, and the takeover triggering judgment module is used to:

[0077] Querying the preset scene set based on the driving scene information to obtain a query result;

[0078] When the query result indicates that the driving scene information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

[0079] In a possible implementation manner, the device further includes a risk coefficient determination module, and the risk coefficient determination module is used to:

[0080] Determine the risk level corresponding to the risk scenario according to the risk scenario;

[0081] If the risk scenario is a highway scenario, determining the risk level of the rural road scenario as the first risk level;

[0082] If the risk scenario is a rural road scenario, determining the risk level of the rural road scenario to be a second risk level;

[0083] If the risk scenario is a city street scenario, determining the risk level of the city street scenario to be the third risk level;

[0084] If the risk scenario is a complex intersection scenario, determining the risk level of the complex intersection scenario to be a fourth risk level;

[0085] If the risk scenario is a severe weather scenario, determining the risk level of the severe weather scenario to be the fifth risk level;

[0086] Determining a risk factor corresponding to the risk scenario based on the risk level corresponding to the risk scenario;

[0087] The first risk level is lower than the second risk level, the second risk level is lower than the third risk level, the third risk level is lower than the fourth risk level, and the fourth risk level is lower than the fifth risk level.

[0088] In a possible implementation, the risk factor determination module is further used to:

[0089] If the risk level is the first risk level, determining the risk coefficient corresponding to the risk scenario as the first risk coefficient;

[0090] If the risk level is the second risk level, determining the risk coefficient corresponding to the risk scenario as the second risk coefficient;

[0091] If the risk level is the third risk level, determining the risk coefficient corresponding to the risk scenario as the third risk coefficient;

[0092] If the risk level is the fourth risk level, determining the risk coefficient corresponding to the risk scenario as the fourth risk coefficient;

[0093] If the risk level is the fifth risk level, determining the risk coefficient corresponding to the risk scenario as the fifth risk coefficient;

[0094] The device further includes an association relationship library construction module, wherein the association relationship library construction module is used to:

[0095] According to the relationship between the risk scenario and the risk coefficient corresponding to the risk scenario, an association relationship library between the risk scenario and the risk coefficient is constructed.

[0096] In a possible implementation, the driving scenario information further includes risk scenario information, and the risk scenario information is at least one of the urban street scenario, the rural road scenario, the highway scenario, the complex intersection scenario, and the severe weather scenario.

[0097] The risk analysis module is used to:

[0098] Based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information;

[0099] Determine the risk coefficient corresponding to the risk scenario information as the scenario risk information.

[0100] In a possible implementation, the correction processing module is used to:

[0101] Acquiring initial assist torque information corresponding to the driving scene information;

[0102] Determining an assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information;

[0103] Calculating the product of the assist torque attenuation coefficient and the initial assist torque information to obtain the attenuated assist torque;

[0104] The input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

[0105] In a possible implementation, the correction processing module is further used to:

[0106] The product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient.

[0107] In a possible implementation, the correction processing module is further used to:

[0108] The input torque information is subtracted from the attenuation assist torque to obtain the correction torque information.

[0109] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the control method for driving takeover in any of the above aspects.

[0110] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement a driving takeover control method as described in any of the above aspects.

[0111] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the control method for driving takeover of any of the above aspects.

[0112] The embodiment of the present application generates a driving takeover request instruction based on driving scenario information; obtains the driver's input torque information to the steering wheel in response to the driving takeover request instruction; performs risk analysis based on the driving scenario information to obtain scenario risk information; performs correction processing on the input torque information based on the driving scenario information and the scenario risk information to obtain corrected torque information; and controls the vehicle to switch to the driver takeover mode according to the corrected power-assisted torque. A torque limiting strategy is set based on different driving scenario information, so that the power-assisted torque of the automatic driving controller attenuates the input torque according to different driving scenarios, avoids abrupt steering and violent steering, improves the driver's control over the vehicle, and solves the problem of mismatch between the control information of the vehicle intelligent driving system and the driver's input information during the driver takeover process. BRIEF DESCRIPTION OF THE DRAWINGS

[0113] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0114] Figure 1 It is a flowchart of a control method for driving takeover provided in an embodiment of the present application;

[0115] Figure 2 It is a flowchart of a method for generating a driving takeover request instruction provided in an embodiment of the present application;

[0116] Figure 3 It is a flowchart of a method for determining scenario risk information provided by an embodiment of the present application;

[0117] Figure 4 It is a flowchart of a method for determining scenario risk information provided by an embodiment of the present application;

[0118] Figure 5 is a flowchart of another driving takeover control method provided in an embodiment of the present application;

[0119] Figure 6 It is a structural block diagram of a driving takeover control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0120] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0121] The autonomous driving controller of a car with autonomous driving function, as the brain of autonomous driving, realizes the fusion processing of environmental perception information and makes decisions on the vehicle's driving behavior to safely drive to the destination. L3 level autonomous driving vehicle TJP (Traffic Jam Pilot System) can automatically follow the vehicle in the current lane at low speeds without the need for driver intervention. L3 level autonomous driving is an autonomous driving mode that can execute some functional decisions under restricted conditions.

[0122] When L3 autonomous driving requests the driver to take over the vehicle, the autonomous driving system still maintains stable control of the vehicle for a certain period of time. If the autonomous driving system cannot match the driver's input during the takeover process, it is easy to cause safety hazards, such as the driver suddenly turning the steering wheel during the takeover process. This solution can effectively solve the problem of abrupt vehicle steering when the driver takes over the vehicle and performs lateral overtaking control.

[0123] The present application provides a control method for driving takeover, which sets a torque limitation strategy based on different driving scenario information, so that the assist torque of the automatic driving controller of the vehicle's automatic driving system can attenuate the input torque according to different driving scenarios, thereby avoiding abrupt steering and sudden steering. Figure 1 The driving takeover control method includes steps S101 to S109.

[0124] In step S101 , a driving takeover request instruction is generated based on driving scenario information.

[0125] In a possible implementation, the generating a driving takeover request instruction based on the driving scenario information includes:

[0126] Acquire the driving scene information, and determine whether the vehicle meets a preset trigger takeover condition according to the driving scene information:

[0127] When the driving scene information satisfies the preset trigger takeover condition, generating an activation takeover instruction, and determining that the activation takeover instruction is the driving takeover request instruction;

[0128] The method further comprises:

[0129] When the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

[0130] In one possible implementation, Figure 2 As shown, the method for generating the driving takeover request instruction includes steps S201 to S205.

[0131] In step S201, the driving scene information is obtained, and it is determined whether the vehicle meets a preset trigger takeover condition based on the driving scene information.

[0132] In a possible implementation, the driver's state is detected by a DMS (Driver Monitor System) to determine whether the driver is in a fatigue state, and the detection result is used as the driving scene information.

[0133] In one possible implementation, the autonomous driving system includes DMS, whose core functions include driver identification, fatigue driving monitoring, and dangerous behavior detection, aiming to improve driving safety, especially in the context of the increasing popularity of autonomous driving technology, to prevent accidents caused by drivers' over-reliance on automatic systems.

[0134] In this implementation, the driving scene information is obtained, and whether the driver is ready to take over the vehicle is determined based on the driving scene information. When the driver is ready to drive, an activation takeover instruction is generated, which improves the effectiveness of the takeover request and further improves the safety of vehicle control.

[0135] In step S203, when the driving scene information satisfies the preset trigger takeover condition, an activation takeover instruction is generated, and the activation takeover instruction is determined to be the driving takeover request instruction.

[0136] In a possible implementation, judging whether the vehicle meets a preset trigger takeover condition according to the driving scene information includes:

[0137] Querying the preset scene set based on the driving scene information to obtain a query result;

[0138] When the query result indicates that the driving scene information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

[0139] In a possible implementation, the method further includes:

[0140] Constructing a first preset scenario of the vehicle entering a boundary of an autonomous driving operation design domain;

[0141] Constructing a second preset scenario where a merging occurs on the road where the vehicle is located;

[0142] Constructing a third preset scenario where a pedestrian appears on the road where the vehicle is located;

[0143] Constructing a fourth preset scenario in which a temporary construction area appears on the road where the vehicle is located;

[0144] Constructing a fifth preset scenario that is beyond the sensor's processing range;

[0145] Constructing a sixth preset scenario in which a single point failure occurs in the system of the vehicle;

[0146] A preset scene set is constructed according to the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene.

[0147] In a possible implementation, the driving scene information also includes vehicle environment information, where the vehicle environment information is a perception result obtained by a perception system of the vehicle perceiving an environment in which the vehicle is located.

[0148] In one possible implementation, the perception system includes perception sensors, which include cameras, radars, and inertial sensors. The perception system is used to collect and process information about the vehicle's environment, and use computer vision algorithms to monitor targets, including lane lines, traffic lights, traffic signs, pedestrians, vehicle obstacles, etc., to achieve environmental perception tasks.

[0149] In a possible implementation, when the driving scene information indicates that the current driver is not in a fatigued state, vehicle environment information of the driving scene information is acquired, and the preset scene set is queried based on the vehicle environment information to obtain a query result.

[0150] In a possible implementation, when the query result indicates that the vehicle environment information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

[0151] In a possible implementation, the first preset scenario represents the vehicle entering the boundary of the autonomous driving operation design domain; the second preset scenario represents the merging of the road where the vehicle is located; the third preset scenario represents the appearance of pedestrians on the road where the vehicle is located; the fourth preset scenario represents the appearance of a temporary construction area on the road where the vehicle is located; the fifth preset scenario represents exceeding the processing range of the vehicle sensor; and the sixth preset scenario represents the occurrence of a single point failure in the vehicle's system.

[0152] In a possible implementation, the preset scenario set is constructed based on a plurality of preset scenarios, and a query is performed based on the vehicle environment information to determine whether the driving scenario information satisfies the preset trigger takeover condition.

[0153] In one possible implementation, when the driving scene information indicates that the current driver is in a non-fatigued state and the vehicle environment information of the driving scene information matches at least one of the preset scenes in the preset scene set, it is determined that the driving scene information meets the preset trigger takeover conditions, and the activation takeover instruction is generated.

[0154] In this implementation, after determining that the driver is ready to take over, the takeover conditions are determined based on the vehicle's driving scenario information, and the scenario during the takeover process is further determined to facilitate control corrections based on different scenarios, thereby improving the accuracy of vehicle control.

[0155] In step S205, when the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

[0156] In one possible implementation, when the driving scene information indicates that the current driver is in a fatigued state, it is determined that the vehicle does not meet the preset trigger takeover conditions, the takeover prevention instruction is generated, and the driver is reminded through the prompt module of the automatic driving system.

[0157] In step S103, in response to the driving takeover request instruction, the driver's input torque information on the steering wheel is obtained.

[0158] In a possible implementation, the driver inputs a hand torque to the steering wheel, and obtains steering information of the steering wheel under the hand torque as the input torque information.

[0159] In a possible implementation, the input torque information is obtained when the driving scene information indicates that the current driver is in a non-fatigue state and the vehicle environment information of the driving scene information matches at least one of the preset scenes in the preset scene set.

[0160] In step S105, risk analysis is performed based on the driving scene information to obtain scene risk information.

[0161] In a possible implementation, the method further includes:

[0162] Determine the risk level corresponding to the risk scenario according to the risk scenario;

[0163] If the risk scenario is a highway scenario, determining the risk level of the rural road scenario as the first risk level;

[0164] If the risk scenario is a rural road scenario, determining the risk level of the rural road scenario to be a second risk level;

[0165] If the risk scenario is a city street scenario, determining the risk level of the city street scenario to be the third risk level;

[0166] If the risk scenario is a complex intersection scenario, determining the risk level of the complex intersection scenario to be a fourth risk level;

[0167] If the risk scenario is a severe weather scenario, determining the risk level of the severe weather scenario to be the fifth risk level;

[0168] Determining a risk factor corresponding to the risk scenario based on the risk level corresponding to the risk scenario;

[0169] The first risk level is lower than the second risk level, the second risk level is lower than the third risk level, the third risk level is lower than the fourth risk level, and the fourth risk level is lower than the fifth risk level.

[0170] In a possible implementation, determining the risk coefficient corresponding to the risk scenario based on the risk level corresponding to the risk scenario includes:

[0171] If the risk level is the first risk level, determining the risk coefficient corresponding to the risk scenario as the first risk coefficient;

[0172] If the risk level is the second risk level, determining the risk coefficient corresponding to the risk scenario as the second risk coefficient;

[0173] If the risk level is the third risk level, determining the risk coefficient corresponding to the risk scenario as the third risk coefficient;

[0174] If the risk level is the fourth risk level, determining the risk coefficient corresponding to the risk scenario as the fourth risk coefficient;

[0175] If the risk level is the fifth risk level, determining the risk coefficient corresponding to the risk scenario as the fifth risk coefficient;

[0176] The method further comprises:

[0177] According to the relationship between the risk scenario and the risk coefficient corresponding to the risk scenario, an association relationship library between the risk scenario and the risk coefficient is constructed.

[0178] In a possible implementation, multiple risk scenarios are preset, and the risk level corresponding to each risk scenario is determined. Specifically, the risk scenario represents the driving environment of the vehicle, and the risk level is used to predict the complexity of the driving environment.

[0179] In a possible implementation, the risk scenarios include highway scenarios, rural road scenarios, city street scenarios, complex intersection scenarios, and severe weather scenarios.

[0180] In a possible implementation, when a vehicle is traveling on a highway, the risk level of the highway is determined to be the first risk level, and the risk coefficient corresponding to the first risk level is preset as the first risk coefficient. Specifically, the value range of the first risk coefficient may be [0.2, 0.4], and the value of the first risk coefficient gradually increases as the vehicle speed increases and the traffic volume increases in the highway scenario. Traffic volume refers to the number of vehicles passing through a certain road point within a certain period of time.

[0181] In a possible implementation, in a highway scenario, when the vehicle speed is less than a first preset speed and the traffic volume is less than the first preset traffic volume, the value of the first risk coefficient is 0.2; in a highway scenario, when the vehicle speed is greater than a second preset speed and the traffic volume is greater than the second preset traffic volume, the value of the first risk coefficient is 0.4; the first preset speed is less than the second preset speed, and the first preset traffic volume is less than the second preset traffic volume.

[0182] In a possible implementation, when a vehicle is driving on a rural road, the risk level of the rural road scene is determined to be the second risk level, and the risk coefficient corresponding to the second risk level is preset as the second risk coefficient. Specifically, the value range of the second risk coefficient can be [0.3, 0.5], and the value of the second risk coefficient gradually increases as the traffic flow increases and the road conditions deteriorate in the rural road scene; the traffic flow represents the traffic flow formed by the continuous driving of cars on the road in the current scene, that is, the number of vehicles passing through a specified location or section of the road (or a lane on the road) in a unit time; the road condition refers to the technical conditions of the existing roadbed, pavement, structures and ancillary facilities, and also refers to the damage of the pavement and ancillary facilities.

[0183] In a possible implementation, in a rural road scenario, when the traffic flow is less than the first preset traffic flow and the road condition is less than the first preset road condition, the value of the second risk coefficient is 0.3; in a rural road scenario, when the traffic flow is greater than the second preset traffic flow and the road condition is greater than the second preset road condition, the value of the second risk coefficient is 0.5; the first preset traffic flow is less than the second preset traffic flow, and the first preset road condition is less than the second preset road condition.

[0184] In a possible implementation, when a vehicle is driving on a city street, the risk level of the city street scene is determined to be the third risk level, and the risk coefficient corresponding to the third risk level is preset as the third risk coefficient. Specifically, the value range of the third risk coefficient may be [0.5, 0.7], and the value of the third risk coefficient increases as the complexity of pedestrians, vehicles, and traffic signals in the city street scene increases; the complexity of pedestrians, vehicles, and traffic signals characterizes the number of pedestrians, vehicles, and traffic signals existing within a preset range in the current scene.

[0185] In a possible implementation, in an urban street scenario, when the complexity is less than a first preset complexity, the value of the third risk coefficient is 0.5; in an urban street scenario, when the complexity is greater than a second preset complexity, the value of the third risk coefficient is 0.7; the first preset complexity is less than the second preset complexity.

[0186] In a possible implementation, when a vehicle is traveling in a complex intersection scenario, the risk level of the complex intersection scenario is determined to be the fourth risk level, and the risk coefficient corresponding to the fourth risk level is preset as the fourth risk coefficient. Specifically, the value range of the fourth risk coefficient may be [0.7, 0.9], and the value of the fourth risk coefficient gradually increases as the number of traffic participants in the complex intersection scenario increases and the road conditions become more complex.

[0187] In one possible implementation, in a complex intersection scenario, when the number of traffic participants is less than the first preset number of participants, the value of the fourth risk coefficient is 0.7; in a complex intersection scenario, when the number of traffic participants is greater than the second preset number of participants, the value of the fourth risk coefficient is 0.9; the first preset number of participants is less than the second preset number of participants.

[0188] In a possible implementation, when a vehicle is driving in a bad weather scene, the risk level of the bad weather scene is determined to be the fifth risk level, and the risk coefficient corresponding to the fifth risk level is preset as the fifth risk coefficient. Specifically, the value range of the fifth risk coefficient may be [0.8, 1], and the value of the fifth risk coefficient gradually increases with the increase of driving difficulty in the bad weather scene; the driving difficulty is characterized by the slippery degree of the road and visibility.

[0189] In one possible implementation, in severe weather scenarios, when the driving difficulty is less than a first preset difficulty, the value of the fifth risk coefficient is 0.8; in severe weather scenarios, when the driving difficulty is greater than a second preset difficulty, the value of the fifth risk coefficient is 1; the first preset difficulty is less than the second preset difficulty.

[0190] In a possible implementation, a correlation relationship library of the risk scenarios and the risk coefficients corresponding to the risk scenarios is constructed according to the relationship between the risk scenarios and the risk coefficients corresponding to the risk scenarios. The corresponding risk coefficients can be obtained by querying according to the risk scenarios.

[0191] In this implementation, the risk factors of different scenarios are analyzed according to different scenarios to ensure the safety of the vehicle, and the impact of the scenarios on vehicle control is determined according to different scenarios, which facilitates the determination of control strategies based on the scenarios, improves the driver's control ability over the vehicle, and enables the driver to better control the vehicle when facing complex or high-risk scenarios.

[0192] In a possible implementation, the driving scenario information further includes risk scenario information, and the risk scenario information is at least one of the urban street scenario, the rural road scenario, the highway scenario, the complex intersection scenario, and the severe weather scenario.

[0193] The performing risk analysis on the driving scene information to obtain the scene risk information includes:

[0194] Based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information;

[0195] Determine the risk coefficient corresponding to the risk scenario information as the scenario risk information.

[0196] In one possible implementation, Figure 3 As shown, the method for determining the scene risk information includes steps S301 to S303.

[0197] In step S301, based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information;

[0198] In step S303, a risk coefficient corresponding to the risk scenario information is determined as the scenario risk information.

[0199] In a possible implementation, based on matching the risk scenario information with a plurality of risk scenarios, a risk coefficient corresponding to a risk scenario matching the risk scenario information is determined as the scenario risk information.

[0200] In this implementation, a preset association relationship library is queried based on the risk scenario information to obtain a risk coefficient corresponding to the risk scenario information, and the risk coefficient corresponding to the risk scenario information is determined to be the scenario risk information. This can quickly locate the current scenario impact information, improve decision-making efficiency, and further improve vehicle control efficiency.

[0201] In step S107, the input torque information is corrected based on the driving scene information and the scene risk information to obtain corrected torque information.

[0202] In a possible implementation, the correcting the input torque information based on the driving scenario information and the scenario risk information to obtain the corrected torque information includes:

[0203] Acquiring initial assist torque information corresponding to the driving scene information;

[0204] Determining an assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information;

[0205] Calculating the product of the assist torque attenuation coefficient and the initial assist torque information to obtain the attenuated assist torque;

[0206] The input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

[0207] In a possible implementation, determining the assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information includes:

[0208] The product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient.

[0209] In a possible implementation, the correcting the input torque information based on the attenuated assist torque to obtain the corrected torque information includes:

[0210] The input torque information is subtracted from the attenuation assist torque to obtain the correction torque information.

[0211] In one possible implementation, Figure 4 As shown, the method for determining the scene risk information includes steps S401 to S407.

[0212] In step S401, initial assist torque information corresponding to the driving scene information is obtained;

[0213] In step S403, based on the initial assist torque information and the scenario risk information, an assist torque attenuation coefficient is determined;

[0214] In step S405, the product of the assist torque attenuation coefficient and the initial assist torque information is calculated to obtain the attenuated assist torque;

[0215] In step S407, the input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

[0216] In a possible implementation manner, torque input information of a driver to a steering wheel is obtained as the input torque information.

[0217] In a possible implementation, the assist torque attenuation coefficient is determined based on the initial assist torque information k and the scenario risk information factor.

[0218] In a possible implementation, when the driving scene information is the first preset scene, that is, the vehicle is about to enter the boundary of the ODD (Operational Design Domain), the initial assist torque information k=1.2Nm / s, and the assist torque attenuation coefficient is factor*1.2Nm / s.

[0219] In one possible implementation, ODD refers to the external environmental conditions suitable for the functional operation of the driving automation system determined when the driving automation system is designed, including road, traffic, weather, lighting and other conditions.

[0220] In a possible implementation, when the driving scene information is the second preset scene, that is, a merging occurs on the road, the initial assist torque information k=1.1 Nm / s, and the assist torque attenuation coefficient is factor*1.1 Nm / s.

[0221] In a possible implementation, when the driving scene information is the third preset scene, that is, pedestrians appear on the road, the initial assist torque information k=1.3 Nm / s, and the assist torque attenuation coefficient is factor*1.3 Nm / s.

[0222] In a possible implementation, when the driving scene information is the fourth preset scene, that is, a temporary construction area appears on the road, the initial assist torque information k=1.2 Nm / s, and the assist torque attenuation coefficient is factor*1.2 Nm / s.

[0223] In a possible implementation, when the driving scene information is the fifth preset scene, that is, it exceeds the processing range of the sensor, the initial assist torque information k=1.2 Nm / s, and the assist torque attenuation coefficient is factor*1.2 Nm / s.

[0224] In a possible implementation, when the driving scene information is the sixth preset scene, that is, a single point failure occurs in the system, the initial assist torque information k=1.1 Nm / s, and the assist torque attenuation coefficient is factor*1.2 Nm / s.

[0225] In one possible implementation, when the driving scene information indicates that the vehicle is about to collide, the system responds to steering input and actively assists to achieve rapid steering and reduce collision damage. During the entire process, driving reminders are given and after completion, all automatic driving and driving assistance functions are turned off.

[0226] In one possible implementation, Figure 5 The driver's steering information and DMS detection results are input into the automatic driving controller, so that the automatic driving controller makes a decision based on the input, controls the vehicle based on the decision, and displays the vehicle's operating status through the IP (instrument panel).

[0227] In one possible implementation, the product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient; the product of the assist torque attenuation coefficient and the initial assist torque information is calculated to obtain the attenuated assist torque; the input torque information is subtracted from the attenuated assist torque to obtain the corrected torque information.

[0228] In this implementation, when the automatic driving system requests the driver to take over, the risk factors of different scenarios are analyzed according to different scenarios, the attenuation assist torque is determined based on the risk factor, and the input torque information is corrected based on the attenuation assist torque, so that when responding to the driver's hand torque input, the assist torque of the automatic driving controller is attenuated at a uniform speed to avoid abrupt steering, thereby improving the safety of intelligent driving vehicles.

[0229] In step S109 , the vehicle is controlled to switch to a driver takeover mode according to the corrected assist torque.

[0230] In a possible implementation, the vehicle is controlled to switch to a driver takeover mode according to the corrected power-assist torque, and the driver is reminded that the vehicle has entered a driving assistance mode.

[0231] The beneficial effects of a driving takeover control method provided by the present solution are as follows: generating a driving takeover request instruction based on driving scenario information; obtaining the driver's input torque information to the steering wheel in response to the driving takeover request instruction; performing risk analysis based on the driving scenario information to obtain scenario risk information; performing correction processing on the input torque information based on the driving scenario information and the scenario risk information to obtain corrected torque information; controlling the vehicle to switch to the driver takeover mode according to the corrected assist torque. The torque limiting strategy is set based on different driving scenario information, so that the assist torque of the automatic driving controller attenuates the input torque according to different driving scenarios, avoiding abrupt steering and violent steering of the steering wheel, improving the driver's control over the vehicle, and solving the problem of mismatch between the control information of the vehicle intelligent driving system and the driver's input information during the driver takeover process.

[0232] Figure 6 The schematic diagram of the structure of a driving takeover control device 600 provided in an embodiment of the present application is shown. The device has the function of implementing the driving takeover control method in the above method embodiment. The function can be implemented by hardware or by hardware executing corresponding software. Figure 6 As shown, the device may include:

[0233] An instruction generation module 601 is used to generate a driving takeover request instruction based on driving scenario information;

[0234] An input torque information acquisition module 602 is used to acquire the driver's input torque information on the steering wheel in response to the driving takeover request instruction;

[0235] A risk analysis module 603 is used to perform risk analysis based on the driving scenario information to obtain scenario risk information;

[0236] A correction processing module 604 is used to perform correction processing on the input torque information based on the driving scene information and the scene risk information to obtain corrected torque information;

[0237] The control module 605 is used to control the vehicle to switch to the driver takeover mode according to the modified assist torque.

[0238] In a possible implementation, the instruction generation module 601 is used to:

[0239] Acquire the driving scene information, and determine whether the vehicle meets a preset trigger takeover condition according to the driving scene information:

[0240] When the driving scene information satisfies the preset trigger takeover condition, generating an activation takeover instruction, and determining that the activation takeover instruction is the driving takeover request instruction;

[0241] The instruction generation module is further used for:

[0242] When the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

[0243] In a possible implementation manner, the device further includes a preset scene set module, and the preset scene set module is used to:

[0244] Constructing a first preset scenario of the vehicle entering a boundary of an autonomous driving operation design domain;

[0245] Constructing a second preset scenario where a merging occurs on the road where the vehicle is located;

[0246] Constructing a third preset scenario where a pedestrian appears on the road where the vehicle is located;

[0247] Constructing a fourth preset scenario in which a temporary construction area appears on the road where the vehicle is located;

[0248] Constructing a fifth preset scenario that is beyond the sensor's processing range;

[0249] Constructing a sixth preset scenario in which a single point failure occurs in the system of the vehicle;

[0250] A preset scene set is constructed according to the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene.

[0251] In a possible implementation, the device further includes a takeover triggering judgment module, and the takeover triggering judgment module is used to:

[0252] Querying the preset scene set based on the driving scene information to obtain a query result;

[0253] When the query result indicates that the driving scene information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

[0254] In a possible implementation manner, the device further includes a risk coefficient determination module, and the risk coefficient determination module is used to:

[0255] Determine the risk level corresponding to the risk scenario according to the risk scenario;

[0256] If the risk scenario is a highway scenario, determining the risk level of the rural road scenario as the first risk level;

[0257] If the risk scenario is a rural road scenario, determining the risk level of the rural road scenario to be a second risk level;

[0258] If the risk scenario is a city street scenario, determining the risk level of the city street scenario to be the third risk level;

[0259] If the risk scenario is a complex intersection scenario, determining the risk level of the complex intersection scenario to be a fourth risk level;

[0260] If the risk scenario is a severe weather scenario, determining the risk level of the severe weather scenario to be the fifth risk level;

[0261] Determining a risk factor corresponding to the risk scenario based on the risk level corresponding to the risk scenario;

[0262] The first risk level is lower than the second risk level, the second risk level is lower than the third risk level, the third risk level is lower than the fourth risk level, and the fourth risk level is lower than the fifth risk level.

[0263] In a possible implementation, the risk factor determination module is further used to:

[0264] If the risk level is the first risk level, determining the risk coefficient corresponding to the risk scenario as the first risk coefficient;

[0265] If the risk level is the second risk level, determining the risk coefficient corresponding to the risk scenario as the second risk coefficient;

[0266] If the risk level is the third risk level, determining the risk coefficient corresponding to the risk scenario as the third risk coefficient;

[0267] If the risk level is the fourth risk level, determining the risk coefficient corresponding to the risk scenario as the fourth risk coefficient;

[0268] If the risk level is the fifth risk level, determining the risk coefficient corresponding to the risk scenario as the fifth risk coefficient;

[0269] The device further includes an association relationship library construction module, wherein the association relationship library construction module is used to:

[0270] According to the relationship between the risk scenario and the risk coefficient corresponding to the risk scenario, an association relationship library between the risk scenario and the risk coefficient is constructed.

[0271] In a possible implementation, the driving scenario information further includes risk scenario information, and the risk scenario information is at least one of the urban street scenario, the rural road scenario, the highway scenario, the complex intersection scenario, and the severe weather scenario.

[0272] The risk analysis module 603 is used to:

[0273] Based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information;

[0274] Determine the risk coefficient corresponding to the risk scenario information as the scenario risk information.

[0275] In a possible implementation, the correction processing module 604 is used to:

[0276] Acquiring initial assist torque information corresponding to the driving scene information;

[0277] Determining an assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information;

[0278] Calculating the product of the assist torque attenuation coefficient and the initial assist torque information to obtain the attenuated assist torque;

[0279] The input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

[0280] In a possible implementation, the correction processing module 604 is further configured to:

[0281] The product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient.

[0282] In a possible implementation, the correction processing module 604 is further configured to:

[0283] The input torque information is subtracted from the attenuation assist torque to obtain the correction torque information.

[0284] It should be noted that the device provided in the above embodiment, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0285] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement any one of the driving takeover control methods provided in the above method embodiments.

[0286] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0287] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a driving takeover control method. The at least one instruction or the at least one program is loaded and executed by the processor to implement any one of the driving takeover control methods provided in the above method embodiments.

[0288] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0289] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0290] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0291] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0292] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A control method for driving takeover, characterized in that: The method comprises: generating a driving takeover request instruction based on the driving scenario information; In response to the driving takeover request instruction, obtaining input torque information of the driver to the steering wheel; Performing risk analysis based on the driving scenario information to obtain scenario risk information; Correcting the input torque information based on the driving scene information and the scene risk information to obtain corrected torque information; The vehicle is controlled to switch to a driver takeover mode according to the corrected assist torque.

2. The control method for driving takeover according to claim 1, characterized in that: The generating of the driving takeover request instruction based on the driving scenario information includes: Acquire the driving scene information, and determine whether the vehicle meets a preset trigger takeover condition according to the driving scene information: When the driving scene information satisfies the preset trigger takeover condition, generating an activation takeover instruction, and determining that the activation takeover instruction is the driving takeover request instruction; The method further comprises: When the driving scene information does not satisfy the preset trigger takeover condition, a takeover prevention instruction is generated, and the takeover prevention instruction is determined to be the driving takeover request instruction.

3. The control method for driving takeover according to claim 1, characterized in that: The method further comprises: Constructing a first preset scenario of the vehicle entering a boundary of an autonomous driving operation design domain; Constructing a second preset scenario where a merging occurs on the road where the vehicle is located; Constructing a third preset scenario where a pedestrian appears on the road where the vehicle is located; Constructing a fourth preset scenario in which a temporary construction area appears on the road where the vehicle is located; Constructing a fifth preset scenario that is beyond the sensor's processing range; Constructing a sixth preset scenario in which a single point failure occurs in the system of the vehicle; A preset scene set is constructed according to the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene.

4. The control method for driving takeover according to claim 3, characterized in that: The determining, according to the driving scene information, whether the vehicle meets a preset trigger takeover condition includes: Querying the preset scene set based on the driving scene information to obtain a query result; When the query result indicates that the driving scene information is at least one of the first preset scene, the second preset scene, the third preset scene, the fourth preset scene, the fifth preset scene and the sixth preset scene, it is determined that the driving scene information satisfies the preset trigger takeover condition.

5. The control method for driving takeover according to claim 1, characterized in that: The method further comprises: Determine the risk level corresponding to the risk scenario according to the risk scenario; If the risk scenario is a highway scenario, determining the risk level of the rural road scenario as the first risk level; If the risk scenario is a rural road scenario, determining the risk level of the rural road scenario to be a second risk level; If the risk scenario is a city street scenario, determining that the risk level of the city street scenario is a third risk level; If the risk scenario is a complex intersection scenario, determining the risk level of the complex intersection scenario to be a fourth risk level; If the risk scenario is a severe weather scenario, determining the risk level of the severe weather scenario to be the fifth risk level; Determining a risk factor corresponding to the risk scenario based on the risk level corresponding to the risk scenario; The first risk level is lower than the second risk level, the second risk level is lower than the third risk level, the third risk level is lower than the fourth risk level, and the fourth risk level is lower than the fifth risk level.

6. The control method for driving takeover according to claim 5, characterized in that: The determining, based on the risk level corresponding to the risk scenario, a risk coefficient corresponding to the risk scenario includes: If the risk level is the first risk level, determining the risk coefficient corresponding to the risk scenario as the first risk coefficient; If the risk level is the second risk level, determining the risk coefficient corresponding to the risk scenario as the second risk coefficient; If the risk level is the third risk level, determining the risk coefficient corresponding to the risk scenario as the third risk coefficient; If the risk level is the fourth risk level, determining the risk coefficient corresponding to the risk scenario as the fourth risk coefficient; If the risk level is the fifth risk level, determining the risk coefficient corresponding to the risk scenario as the fifth risk coefficient; The method further comprises: According to the relationship between the risk scenario and the risk coefficient corresponding to the risk scenario, an association relationship library between the risk scenario and the risk coefficient is constructed.

7. The control method for driving takeover according to claim 6, characterized in that: The driving scenario information also includes risk scenario information, and the risk scenario information is at least one of the urban street scenario, the rural road scenario, the highway scenario, the complex intersection scenario, and the severe weather scenario. The performing risk analysis on the driving scene information to obtain the scene risk information includes: Based on the risk scenario information, a database of association relationships between the risk scenario and the risk coefficient is queried to obtain a risk coefficient corresponding to the risk scenario information; Determine the risk coefficient corresponding to the risk scenario information as the scenario risk information.

8. The control method for driving takeover according to claim 1, characterized in that: The correcting the input torque information based on the driving scenario information and the scenario risk information to obtain the corrected torque information includes: Acquiring initial assist torque information corresponding to the driving scene information; Determining an assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information; Calculating the product of the assist torque attenuation coefficient and the initial assist torque information to obtain the attenuated assist torque; The input torque information is corrected based on the attenuated assist torque to obtain the corrected torque information.

9. The control method for driving takeover according to claim 8, characterized in that: The determining of the assist torque attenuation coefficient based on the initial assist torque information and the scenario risk information includes: The product of the initial assist torque information and the scenario risk information is calculated to obtain the assist torque attenuation coefficient.

10. The control method for driving takeover according to claim 8, characterized in that: The correcting the input torque information based on the attenuated assist torque to obtain the corrected torque information includes: The input torque information is subtracted from the attenuation assist torque to obtain the correction torque information.

Images