Misacceleration determination, driving control method and device, storage medium and vehicle

Abstract

The present application relates to the technical field of automatic driving, and particularly provides a misacceleration determination method and device, a driving control method and device, a storage medium and a vehicle, aiming at solving the problem of how to more accurately determine misacceleration operation. To this end, the present application obtains the confidence of misacceleration condition based on the perception information and vehicle control information of the vehicle, and obtains the determination result of the misacceleration condition of the vehicle according to the confidence of the misacceleration condition. Since the perception information of the vehicle can contain perception data of multiple dimensions inside and outside the vehicle, combined with the vehicle control information, a judgment process based on multiple modalities of vehicle data and vehicle environment data can be realized, which can effectively improve the accuracy of misacceleration condition determination, and then the vehicle can be controlled based on the determination result. When there is indeed a misacceleration condition, the power supply of the vehicle can be timely blocked, thereby reducing the incidence of accidents.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, specifically providing a method, device, storage medium, and vehicle for detecting accidental acceleration. Background Technology

[0002] Sometimes, drivers mistakenly press the accelerator instead of the brake while driving. This operational error significantly increases the incidence of traffic accidents. However, if an autonomous driving system could recognize the driver's mistaken press of the accelerator and cut off the power supply, the incidence of such accidents could be greatly reduced.

[0003] In existing technologies, the judgment of a driver's accidental pressing of the accelerator is mostly based on information such as the vehicle's throttle opening and wheel speed, as well as GPS positioning information. This judgment method is often not very accurate.

[0004] Accordingly, there is a need in this field for a new scheme to detect accidental acceleration and solve the above problems. Summary of the Invention

[0005] To overcome the above-mentioned shortcomings, the present invention is proposed to provide a solution, or at least a partial solution, to the problem of how to more accurately determine accidental acceleration.

[0006] In a first aspect, the present invention provides a method for determining accidental acceleration, the method comprising:

[0007] Acquire vehicle perception information and vehicle control information;

[0008] Based on the perceived information and the vehicle control information, obtain the confidence level of the accidental acceleration situation;

[0009] Based on the confidence level, the determination result of whether the vehicle accidentally pressed the accelerator is obtained.

[0010] In one technical solution of the above-mentioned method for determining accidental acceleration, the sensing information includes external environmental sensing information, and the step of "obtaining the confidence level of the accidental acceleration situation" includes:

[0011] Based on the external environment perception information and the vehicle control information, obtain the first-level confidence level of the accidental acceleration situation;

[0012] When the first level of confidence is greater than the preset first confidence threshold, the second level of confidence for the accidental acceleration situation is obtained based on the perceived information, the vehicle control information, and the first level of confidence.

[0013] The second-order confidence level is used as the final confidence level for the case of accidental acceleration.

[0014] In one technical solution of the above-mentioned method for determining accidental acceleration, the step of "obtaining the first-level confidence level of the accidental acceleration situation" includes:

[0015] Based on the external environment perception information and the vehicle control information, obtain the first-level confidence discrimination parameters;

[0016] The first-level confidence level is obtained based on the first-level confidence level discrimination parameter.

[0017] In one technical solution of the above-mentioned method for detecting accidental accelerator pedal press, the first-level confidence discrimination parameters include an environmental target factor, a scene factor, and an accelerator pedal pressure factor. The step of "obtaining the first-level confidence discrimination parameters" includes:

[0018] Based on the external environment perception information and the vehicle control information, the environmental target factor and the scene factor are obtained;

[0019] The accelerator pedal pressure factor is obtained based on the vehicle control information.

[0020] In one technical solution of the above-mentioned method for detecting accidental acceleration, the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0021] Obtain the environmental target weight, scene weight, and accelerator pedal pressure weight corresponding to the preset environmental target factor, scene factor, and accelerator pedal pressure factor, respectively.

[0022] The first-level confidence level is obtained based on the environmental target factor, the scene factor, the accelerator pedal pressure factor, and the corresponding environmental target weight, scene weight, and accelerator pedal pressure weight.

[0023] In one technical solution of the above-mentioned method for determining accidental accelerator pedal press, the external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located, the vehicle control information includes accelerator pedal pressure and vehicle movement direction, and the step of "obtaining the environmental target factor and the scene factor" includes:

[0024] The environmental target factor is obtained based on the location of the environmental target and the direction of the vehicle's movement;

[0025] Based on the type of the scenario, obtain the scenario factor; and / or,

[0026] The steps for “obtaining the accelerator pedal pressure factor” include:

[0027] The accelerator pedal pressure factor is obtained based on the accelerator pedal pressure.

[0028] In one technical solution of the above-mentioned method for determining accidental acceleration, the step of "obtaining the environmental target factor based on the position of the environmental target and the direction of vehicle movement" includes:

[0029] Based on the location of the environmental target, the vehicle's own position, and the vehicle's direction of movement, the overlap between the environmental target and the vehicle within a first preset time period in the future is obtained.

[0030] The environmental target factor is obtained based on the degree of overlap.

[0031] In one technical solution of the above-mentioned method for determining accidental accelerator pedal press, the external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located; the vehicle control information includes accelerator pedal pressure and vehicle movement direction; the first-level confidence discrimination parameters include collision risk confidence and / or scene risk confidence; and the step of "obtaining the first-level confidence discrimination parameters" includes:

[0032] The collision risk confidence level is obtained based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of motion.

[0033] Based on the scenario and the accelerator pedal pressure, obtain the scenario risk confidence level.

[0034] In one technical solution of the above-mentioned method for determining accidental acceleration, the step of "obtaining the collision risk confidence level" includes:

[0035] Based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of movement, the degree of overlap between the vehicle and the environmental target within a first preset time period in the future is obtained.

[0036] The collision risk confidence level is obtained based on the overlap.

[0037] In one technical solution of the above-mentioned method for determining accidental accelerator pedal press, the step of "obtaining the risk confidence level of the scenario based on the scenario and the accelerator pedal pressure" includes:

[0038] The rate of change of the accelerator pedal pressure within a second preset time period is obtained;

[0039] Based on the rate of change and the scenario, obtain the scenario risk confidence level.

[0040] In one technical solution of the above-mentioned method for detecting accidental acceleration, the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0041] When the collision risk confidence level is greater than or equal to a preset third confidence level threshold and the scene risk confidence level is less than a preset fourth confidence level threshold, the first-level confidence level is obtained based on the collision risk confidence level.

[0042] When the scenario risk confidence level is greater than or equal to the fourth confidence level threshold and the collision risk confidence level is less than the third confidence level threshold, the first-level confidence level is obtained based on the scenario risk confidence level.

[0043] When the collision risk confidence is less than the third confidence threshold and the scene risk confidence is less than the fourth confidence threshold, or when the collision risk confidence is greater than or equal to the third confidence threshold and the scene risk confidence is greater than or equal to the fourth confidence threshold, the first-level confidence is obtained based on the collision risk confidence and the scene risk confidence.

[0044] In one technical solution of the above-mentioned method for detecting accidental acceleration, the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0045] The first-level confidence level is obtained by taking a weighted average of the collision risk confidence level and the scenario risk confidence level.

[0046] In one technical solution of the above-mentioned method for determining accidental acceleration, the perceived information includes the driver's perception information inside the vehicle, and the step of "obtaining the second-level confidence level of the accidental acceleration situation" includes:

[0047] The driver's behavior recognition result is obtained based on the driver's perception information;

[0048] By applying a preset neural network model, the second-level confidence level of the accidental acceleration situation is obtained based on the behavior recognition result, the vehicle control information, and the first-level confidence level.

[0049] The behavior recognition results include the driver's level of surprise and / or the driver's level of fatigue.

[0050] In one technical solution of the above-mentioned method for determining accidental acceleration, the sensing information includes radar sensing warning information, the vehicle control information includes brake pedal pressure and vehicle movement direction, and the step of "obtaining the second-level confidence level of the accidental acceleration situation" includes:

[0051] The behavior recognition results, brake pedal pressure, vehicle movement direction, first-level confidence score, and radar perception warning information of the same time length are time-aligned and used as input data for the neural network model.

[0052] The neural network model is used to extract features and calculate confidence levels from the input data to obtain the secondary confidence level.

[0053] In one technical solution of the above-mentioned method for determining accidental acceleration, the step of "obtaining the determination result of the accidental acceleration situation of the vehicle based on the confidence level" includes:

[0054] When the confidence level is greater than or equal to a preset second confidence threshold, it is determined that the vehicle has a risk of accidentally pressing the accelerator.

[0055] When the confidence level is less than the second confidence threshold, it is determined that there is no risk of the vehicle accidentally pressing the accelerator.

[0056] In a second aspect, the present invention provides a driving control method, the method comprising:

[0057] According to any one of the above-mentioned methods for determining accidental acceleration, the determination result of the vehicle's accidental acceleration is obtained.

[0058] Based on the determination result, the vehicle is controlled for driving.

[0059] In one technical solution of the above-mentioned driving control method, the step of "driving control of the vehicle according to the determination result" includes:

[0060] When there is a risk of accidentally pressing the accelerator pedal, the power supply to the vehicle is cut off.

[0061] In a third aspect, a control device is provided, comprising at least one processor and at least one storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute any one of the above-described methods for determining accidental accelerator pedal use or any one of the above-described methods for driving control.

[0062] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, the program codes being adapted to be loaded and run by a processor to perform any one of the above-described methods for determining accidental accelerator pedal use or any one of the above-described methods for driving control.

[0063] In a fifth aspect, a vehicle is provided, the vehicle including the control device described in the above-mentioned control device technical solution.

[0064] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0065] In implementing the technical solution of this invention, the invention obtains the confidence level of a case of accidental accelerator pedal press based on vehicle perception information and vehicle control information, and obtains the judgment result of the accidental accelerator pedal press based on the confidence level. Through the above configuration, since the vehicle perception information can include multiple dimensions of perception data from inside and outside the vehicle, combined with vehicle control information, a multi-modal judgment process based on vehicle data and vehicle environmental data can be realized, effectively improving the accuracy of judging accidental accelerator pedal press. Subsequently, the vehicle can be controlled based on the judgment result. In the event of accidental accelerator pedal press, the vehicle's power supply can be promptly cut off, thereby reducing the accident rate.

[0066] Solution 1. A method for detecting accidental acceleration, characterized in that the method includes:

[0067] Acquire vehicle perception information and vehicle control information;

[0068] Based on the perceived information and the vehicle control information, obtain the confidence level of the accidental acceleration situation;

[0069] Based on the confidence level, the determination result of whether the vehicle accidentally pressed the accelerator is obtained.

[0070] Solution 2. The method for determining accidental accelerator pedal press as described in Solution 1, characterized in that the sensing information includes external environmental sensing information, and the step of "obtaining the confidence level of accidental accelerator pedal press" includes:

[0071] Based on the external environment perception information and the vehicle control information, obtain the first-level confidence level of the accidental acceleration situation;

[0072] When the first level of confidence is greater than the preset first confidence threshold, the second level of confidence for the accidental acceleration situation is obtained based on the perceived information, the vehicle control information, and the first level of confidence.

[0073] The second-order confidence level is used as the final confidence level for the case of accidental acceleration.

[0074] Solution 3. The method for determining accidental accelerator pedal press according to Solution 2, characterized in that the step of "obtaining the first-level confidence level of the accidental accelerator pedal press situation" includes:

[0075] Based on the external environment perception information and the vehicle control information, obtain the first-level confidence discrimination parameters;

[0076] The first-level confidence level is obtained based on the first-level confidence level discrimination parameter.

[0077] Solution 4. The method for determining accidental accelerator pedal press as described in Solution 3, characterized in that the first-level confidence discrimination parameters include an environmental target factor, a scene factor, and an accelerator pedal pressure factor, and the step of "obtaining the first-level confidence discrimination parameters" includes:

[0078] Based on the external environment perception information and the vehicle control information, the environmental target factor and the scene factor are obtained;

[0079] The accelerator pedal pressure factor is obtained based on the vehicle control information.

[0080] Solution 5. The method for determining accidental acceleration as described in Solution 4, characterized in that the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0081] Obtain the environmental target weight, scene weight, and accelerator pedal pressure weight corresponding to the preset environmental target factor, scene factor, and accelerator pedal pressure factor, respectively.

[0082] The first-level confidence level is obtained based on the environmental target factor, the scene factor, the accelerator pedal pressure factor, and the corresponding environmental target weight, scene weight, and accelerator pedal pressure weight.

[0083] Solution 6. The method for determining accidental accelerator pedal press as described in Solution 4, characterized in that the external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located, the vehicle control information includes accelerator pedal pressure and vehicle movement direction, and the step of "obtaining the environmental target factor and the scene factor" includes:

[0084] The environmental target factor is obtained based on the location of the environmental target and the direction of the vehicle's movement;

[0085] Based on the type of the scenario, obtain the scenario factor; and / or,

[0086] The steps for “obtaining the accelerator pedal pressure factor” include:

[0087] The accelerator pedal pressure factor is obtained based on the accelerator pedal pressure.

[0088] Solution 7. The method for determining accidental accelerator pedal press according to Solution 6, characterized in that the step of "obtaining the environmental target factor based on the position of the environmental target and the direction of vehicle movement" includes:

[0089] Based on the location of the environmental target, the vehicle's own position, and the vehicle's direction of movement, the overlap between the environmental target and the vehicle within a first preset time period in the future is obtained.

[0090] The environmental target factor is obtained based on the degree of overlap.

[0091] Solution 8. The method for determining accidental accelerator pedal press as described in Solution 3, characterized in that the external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located; the vehicle control information includes accelerator pedal pressure and vehicle movement direction; the first-level confidence discrimination parameters include collision risk confidence and / or scene risk confidence; and the step of "obtaining the first-level confidence discrimination parameters" includes:

[0092] The collision risk confidence level is obtained based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of motion.

[0093] Based on the scenario and the accelerator pedal pressure, obtain the scenario risk confidence level.

[0094] Solution 9. The method for determining accidental acceleration as described in Solution 8, characterized in that the step of "obtaining the collision risk confidence level" includes:

[0095] Based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of movement, the degree of overlap between the vehicle and the environmental target within a first preset time period in the future is obtained.

[0096] The collision risk confidence level is obtained based on the overlap.

[0097] Solution 10. The method for determining accidental accelerator pedal press as described in Solution 8, characterized in that the step of "obtaining the risk confidence level of the scenario based on the scenario and the accelerator pedal pressure" includes:

[0098] The rate of change of the accelerator pedal pressure within a second preset time period is obtained;

[0099] Based on the rate of change and the scenario, obtain the scenario risk confidence level.

[0100] Solution 11. The method for determining accidental acceleration as described in Solution 8, characterized in that the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0101] When the collision risk confidence level is greater than or equal to a preset third confidence level threshold and the scene risk confidence level is less than a preset fourth confidence level threshold, the first-level confidence level is obtained based on the collision risk confidence level.

[0102] When the scenario risk confidence level is greater than or equal to the fourth confidence level threshold and the collision risk confidence level is less than the third confidence level threshold, the first-level confidence level is obtained based on the scenario risk confidence level.

[0103] When the collision risk confidence is less than the third confidence threshold and the scene risk confidence is less than the fourth confidence threshold, or when the collision risk confidence is greater than or equal to the third confidence threshold and the scene risk confidence is greater than or equal to the fourth confidence threshold, the first-level confidence is obtained based on the collision risk confidence and the scene risk confidence.

[0104] Solution 12. The method for determining accidental acceleration as described in Solution 8, characterized in that the step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes:

[0105] The first-level confidence level is obtained by taking a weighted average of the collision risk confidence level and the scenario risk confidence level.

[0106] Solution 13. The method for determining accidental accelerator pedal press according to Solution 2, characterized in that the perceived information includes the driver's perceived information inside the vehicle, and the step of "obtaining the second-level confidence level of the accidental accelerator pedal press" includes:

[0107] The driver's behavior recognition result is obtained based on the driver's perception information;

[0108] By applying a preset neural network model, the second-level confidence level of the accidental acceleration situation is obtained based on the behavior recognition result, the vehicle control information, and the first-level confidence level.

[0109] The behavior recognition results include the driver's level of surprise and / or the driver's level of fatigue.

[0110] Solution 14. The method for determining accidental accelerator pedal press according to Solution 13, characterized in that the sensing information includes radar sensing warning information, the vehicle control information includes brake pedal pressure and vehicle movement direction, and the step of "obtaining the second-level confidence level of the accidental accelerator pedal press" includes:

[0111] The behavior recognition results, brake pedal pressure, vehicle movement direction, first-level confidence score, and radar perception warning information of the same time length are time-aligned and used as input data for the neural network model.

[0112] The neural network model is used to extract features and calculate confidence levels from the input data to obtain the secondary confidence level.

[0113] Solution 15. The method for determining accidental acceleration as described in Solution 1, characterized in that the step of "obtaining the determination result of the accidental acceleration situation of the vehicle based on the confidence level" includes:

[0114] When the confidence level is greater than or equal to a preset second confidence threshold, it is determined that the vehicle has a risk of accidentally pressing the accelerator.

[0115] When the confidence level is less than the second confidence threshold, it is determined that there is no risk of the vehicle accidentally pressing the accelerator.

[0116] Option 16. A driving control method, characterized in that the method includes:

[0117] The determination result of the vehicle's accidental acceleration is obtained according to any one of Schemes 1 to 15;

[0118] Based on the determination result, the vehicle is controlled for driving.

[0119] Solution 17. The driving control method according to Solution 16, characterized in that the step of "performing driving control of the vehicle according to the determination result" includes:

[0120] When there is a risk of accidentally pressing the accelerator pedal, the power supply to the vehicle is cut off.

[0121] Scheme 18. A control device comprising at least one processor and at least one storage device, the storage device being adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to perform the method for determining accidental accelerator pedal use as described in any one of Schemes 1 to 15 or the driving control method as described in any one of Schemes 16 to 17.

[0122] Scheme 19. A computer-readable storage medium storing a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by a processor to perform the method for determining accidental accelerator pedal use as described in any one of Schemes 1 to 15 or the driving control method as described in any one of Schemes 16 to 17.

[0123] Option 20. A vehicle, characterized in that the vehicle includes the control device described in Option 18. Attached Figure Description

[0124] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Wherein:

[0125] Figure 1 This is a schematic flowchart of the main steps of a method for determining accidental accelerator pedal use according to an embodiment of the present invention;

[0126] Figure 2 This is a schematic diagram of the main system structure of a real-number method for determining accidental accelerator pedal use according to an embodiment of the present invention;

[0127] Figure 3This is a schematic diagram of the main system structure for obtaining a first-level confidence level using a real number method according to an embodiment of the present invention;

[0128] Figure 4 This is a schematic diagram of the main steps for obtaining a second-level confidence level using a real number method according to an embodiment of the present invention;

[0129] Figure 5 This is a schematic flowchart of the main steps of a driving control method according to an embodiment of the present invention. Detailed Implementation

[0130] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0131] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0132] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a method for detecting accidental accelerator pedal press according to an embodiment of the present invention. Figure 1 As shown, the method for determining accidental acceleration in this embodiment of the invention mainly includes the following steps S101-S103.

[0133] Step S101: Obtain vehicle perception information and vehicle control information.

[0134] In this embodiment, vehicle perception information and vehicle control information can be acquired.

[0135] In one embodiment, the vehicle's perception information may include external environment perception information, driver perception information, etc. External environment perception information may include environmental targets around the vehicle and the scene in which the vehicle is located. Vehicle control information may include accelerator pedal pressure, brake pedal pressure, vehicle direction of movement, etc.

[0136] Step S102: Based on the perception information and vehicle control information, obtain the confidence level of the accidental acceleration situation.

[0137] In this embodiment, the confidence level of the accidental acceleration can be obtained based on perception information and vehicle control information.

[0138] In one implementation, the perception information and vehicle control information can be assigned corresponding weights based on their respective influence on the accidental acceleration situation. The confidence level of the accidental acceleration situation can be obtained by scoring the perception information and vehicle control information separately and then weighting the scores.

[0139] Step S103: Based on the confidence level, obtain the determination result of the vehicle's accidental acceleration.

[0140] In this embodiment, the determination result of the vehicle's accidental acceleration can be obtained based on the confidence level obtained in step S102.

[0141] Based on steps S101-S103 above, this embodiment of the invention obtains the confidence level of a case of accidental accelerator pedal press based on vehicle perception information and vehicle control information, and obtains the judgment result of the accidental accelerator pedal press based on the confidence level. Through this configuration, since the vehicle perception information can include multiple dimensions of perception data from inside and outside the vehicle, combined with vehicle control information, a multi-modal judgment process based on vehicle data and environmental data can be achieved, effectively improving the accuracy of judging accidental accelerator pedal press. Subsequently, the vehicle can be controlled based on the judgment result. In the event of accidental accelerator pedal press, the vehicle's power supply can be promptly cut off, thereby reducing the accident rate.

[0142] The following provides a further explanation of steps S102 and S103.

[0143] In one embodiment of the present invention, step S102 may include steps S1021 to S1023:

[0144] Step S1021: Based on the external environment perception information and vehicle control information, obtain the first-level confidence level of the accidental acceleration situation.

[0145] In this embodiment, step S1021 may further include the following steps S10211 and S10212:

[0146] Step S10211: Obtain the first-level confidence discrimination parameters based on the external environment perception information and vehicle control information.

[0147] Step S10212: Obtain the first-level confidence level based on the first-level confidence level discrimination parameter.

[0148] In one embodiment, the first-level confidence discrimination parameter may include an environmental target factor, a scenario factor, and an accelerator pedal pressure factor. Step S10211 may further include the following steps S102111 and S102112:

[0149] Step S102111: Based on the external environment perception information and vehicle control information, obtain the environmental target factor and scene factor.

[0150] In this embodiment, environmental target factors can be obtained based on the location of the environmental target and the vehicle's direction of movement. For example, the overlap between the environmental target and the vehicle (automobile) within a first preset time period (e.g., 5 seconds) can be obtained based on the location of the environmental target, the vehicle's (automobile's) position, and the vehicle's (automobile's) direction of movement, and the environmental target factors can be obtained based on the overlap.

[0151] In one implementation, the higher the degree of overlap, the larger the value of the environmental target factor.

[0152] In one implementation, environmental targets may include dynamic targets (such as vehicles, people, etc.) and static targets (such as fences, traffic lights, etc.).

[0153] In one implementation, scene factors can be determined based on scene type. For example, the scene type of the vehicle is currently in (such as street, internal road, parking lot, highway, etc.) can be determined based on perception information. Different scene factor values ​​can be set for different scenes. For example, the scene factor value for parking lot is 0.9, the scene factor value for street is 0.3, the scene factor value for highway is 0.05, and the scene factor value for internal road is 0.5.

[0154] Step S102112: Obtain the accelerator pedal pressure factor based on the vehicle control information.

[0155] In this embodiment, the accelerator pedal pressure can be obtained based on vehicle control information, and then the accelerator pedal pressure factor can be obtained based on the accelerator pedal pressure.

[0156] In one implementation, the accelerator pedal pressure factor can be obtained according to the following formula (1):

[0157] p_pressure=pressure / 100 (1)

[0158] Where p_pressure is the accelerator pedal pressure factor and pressure is the accelerator pedal pressure.

[0159] Step S10212 may further include the following steps S102121 and S102122:

[0160] Step S102121: Obtain the environmental target weight, scene weight, and accelerator pedal pressure weight corresponding to the preset environmental target factor, scene factor, and accelerator pedal pressure factor, respectively.

[0161] Step S102122: Obtain the first-level confidence level based on the environmental target factor, scenario factor, and accelerator pedal pressure factor, and the corresponding environmental target weight, scenario weight, and accelerator pedal pressure weight.

[0162] In this embodiment, the first-level confidence level can be obtained by weighted averaging of environmental target factors, scene factors, and accelerator pedal factors.

[0163] In another embodiment, the first-level confidence level discrimination parameter may include collision risk confidence and scene risk confidence. Step S10211 may further include the following steps S102113 and S102114:

[0164] Step S102113: Obtain the collision risk confidence level based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of motion.

[0165] In this embodiment, the overlap between the vehicle (automobile) and the environmental target within a first preset time period (e.g., 5 seconds) can be obtained based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of movement. The collision risk confidence level is then determined based on the overlap level. A higher overlap level indicates a higher collision risk confidence level.

[0166] Step S102114: Obtain the scenario risk confidence level based on the scenario and accelerator pedal pressure.

[0167] In this embodiment, the rate of change of accelerator pedal pressure over a second preset time period can be obtained, and the scenario risk confidence level can be determined based on the rate of change and the scenario. That is, from the perspective of the scenario, when the vehicle is in a parking lot, underground garage, or road inside the park, there will not be a situation where the accelerator pedal is pressed hard under normal circumstances. Therefore, when the above scenario occurs and the accelerator pedal pressure suddenly changes by a large margin, it is possible that the accelerator pedal was pressed accidentally, which means that the scenario risk confidence level will be high.

[0168] In one embodiment, step S10212 may further include steps S102123 and S102125:

[0169] Step S102123: When the collision risk confidence is greater than or equal to the preset third confidence threshold and the scene risk confidence is less than the preset fourth confidence threshold, obtain the first level confidence based on the collision risk confidence.

[0170] Step S102124: When the scene risk confidence level is greater than or equal to the fourth confidence level threshold and the collision risk confidence level is less than the third confidence level threshold, obtain the first-level confidence level based on the scene risk confidence level.

[0171] Step S102125: When the collision risk confidence is less than the third confidence threshold and the scene risk confidence is less than the fourth confidence threshold, or when the collision risk confidence is greater than or equal to the third confidence threshold and the scene risk confidence is greater than or equal to the fourth confidence threshold, obtain the first-level confidence based on the collision risk confidence and the scene risk confidence.

[0172] In this implementation, when either the collision risk confidence level or the scene risk confidence level is higher, the higher of the two values ​​can be used to determine the first-level confidence level. In other words, if either the collision risk confidence level or the scene risk confidence level is higher, a risk is identified, and a second-level confidence level calculation is required.

[0173] In another embodiment, step S10212 may further include the following step S102126:

[0174] Step S102126: Take a weighted average of the collision risk confidence and the scenario risk confidence to obtain the first-level confidence.

[0175] In this embodiment, the collision risk confidence level and the scene risk confidence level can be weighted and averaged to obtain the first-level confidence level.

[0176] Step S1022: When the first level of confidence is greater than the preset first level of confidence threshold, the second level of confidence for the case of accidental acceleration is obtained based on the perception information, vehicle control information and the first level of confidence.

[0177] In this embodiment, step S1022 may further include steps S10221 to S10222:

[0178] Step S10221: Obtain the driver's behavior recognition results based on the driver's perception information. The behavior recognition results include the driver's level of surprise and the driver's level of fatigue.

[0179] In this embodiment, the driver's behavior recognition results can be obtained through a DMS (Driver Monitor System). When the accelerator pedal is accidentally pressed, there are generally two situations: 1. The driver is fatigued, leading to the misoperation, and the driver's fatigue level will be detected. 2. The driver thought they had pressed the brake but mistakenly pressed the accelerator, causing the vehicle to accelerate rapidly and increasing the driver's expression of surprise. Therefore, the driver's fatigue level and the driver's surprise level can be obtained.

[0180] Step S10222: Apply the preset neural network model to obtain the second confidence level of the accidental acceleration situation based on the behavior recognition results, vehicle control information and first-level confidence level.

[0181] In this embodiment, step S10222 may further include steps S102221 and S102222:

[0182] Step S102221: Time-series alignment of behavior recognition results, brake pedal pressure, vehicle movement direction, first-level confidence level, and radar perception warning information of the same time length is used as input data for the neural network model.

[0183] Step S102222: Apply a neural network model to extract features and calculate confidence scores from the input data to obtain the secondary confidence score.

[0184] In this embodiment, when the accelerator pedal is accidentally pressed, the driver may react in two ways: either slamming on the brakes to counteract the acceleration, or swerving to avoid a potential collision. Simultaneously, the vehicle's (self-vehicle's) radar perception warning information will also issue a warning regarding a potential collision. Therefore, the behavior recognition results, brake pedal pressure, vehicle direction of movement, first-level confidence score, and radar perception warning information of the same time duration can be time-aligned and input into a neural network model. The neural network model then performs feature extraction and confidence score calculation on the input data to obtain the second-level confidence score.

[0185] Step S1023: Use the second-level confidence level as the final confidence level for the case of accidentally pressing the accelerator.

[0186] In this embodiment, the obtained secondary confidence level can be used as the final confidence level for the case of accidental acceleration.

[0187] In one real-number embodiment of the present invention, step S103 may further include the following steps S1031 and S1032:

[0188] Step S1031: When the confidence level is greater than or equal to the preset second confidence level threshold, it is determined that there is a risk of the vehicle accidentally pressing the accelerator.

[0189] Step S1032: When the confidence level is less than the second confidence level threshold, it is determined that there is no risk of the vehicle accidentally pressing the accelerator.

[0190] In this embodiment, the final confidence level can be compared with the second confidence level threshold to determine whether the vehicle truly poses a risk of accidentally pressing the accelerator.

[0191] In one implementation, see Appendix Figure 2 , Figure 2 This is a schematic diagram of the main system structure of a real-number method for detecting accidental accelerator pedal press according to an embodiment of the present invention. Figure 2 As shown, perceived information (including moving targets, stationary targets, and scenes) and vehicle chassis data (including accelerator pedal pressure and vehicle direction) can be input into the first-level discriminator to obtain the first-level confidence level. The first-level confidence level, DMS (including driver surprise level and driver fatigue level), chassis data (including brake pedal pressure and vehicle direction), and radar (including radar warning) are then input into the second-level discriminator to obtain the final confidence level.

[0192] In one implementation, see Appendix Figure 3 , Figure 3 This is a schematic diagram of the main system structure for obtaining a first-level confidence level according to an embodiment of the present invention. Figure 3 As shown, collision risk can be determined and collision risk confidence can be predicted based on moving targets, stationary targets, accelerator pedal pressure, and vehicle direction; scene risk can be determined and scene risk confidence can be predicted based on scene recognition; and then the first-level discriminator obtains the first-level confidence based on the collision risk confidence and scene risk confidence.

[0193] In one implementation, see Appendix Figure 4 , Figure 4 This is a schematic flowchart illustrating the main steps of obtaining a second-level confidence level according to one embodiment of the present invention. Figure 4 As shown, the DMS surprise (driver's surprise level), DMS fatigue (driver's fatigue level), brake pedal (pressure), radar warning, and primary confidence level can be time-aligned and input into the secondary discriminant network (neural network model) to obtain the secondary confidence level. The secondary confidence level is then used as the final confidence level for the case of accidental accelerator pedal press. Here, 1, 2, 3, 4, ..., n-3, n-2, n-1 refer to the time-aligned frame numbers of the input data.

[0194] It should be noted that the aforementioned first confidence threshold, second confidence threshold, third confidence threshold, fourth confidence threshold, first preset duration, second preset duration, and other parameters can be set by those skilled in the art according to the needs of actual applications, and different numerical settings are all within the protection scope of this invention.

[0195] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0196] Furthermore, the present invention also provides a driving control method.

[0197] See appendix Figure 5 , Figure 5 This is a schematic flowchart illustrating the main steps of a driving control method according to an embodiment of the present invention. Figure 5 As shown, the driving control method in this embodiment of the invention mainly includes the following steps S201 to S202.

[0198] Step S201: Obtain the determination result of the vehicle's accidental acceleration situation according to the accidental acceleration determination method in the above embodiment of the accidental acceleration determination method.

[0199] Step S202: Based on the judgment result, perform driving control on the vehicle.

[0200] In one implementation, step S202 may further include:

[0201] When there is a risk of accidentally pressing the accelerator, the vehicle's power supply is cut off.

[0202] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0203] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the accelerator pedal misoperation determination method of the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for executing the accelerator pedal misoperation determination method of the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This control device can be a control device device comprising various electronic devices.

[0204] In embodiments of the present invention, the control device may be a control device device comprising various electronic devices. In some possible implementations, the control device may include multiple storage devices and multiple processors. The program executing the accidental acceleration detection method of the above method embodiments can be divided into multiple subroutines, each subroutine can be loaded and run by a processor to execute different steps of the accidental acceleration detection method of the above method embodiments. Specifically, each subroutine can be stored in different storage devices, and each processor can be configured to execute programs in one or more storage devices to jointly implement the accidental acceleration detection method of the above method embodiments, that is, each processor executes different steps of the accidental acceleration detection method of the above method embodiments to jointly implement the accidental acceleration detection method of the above method embodiments.

[0205] The aforementioned multiple processors can be processors deployed on the same device. For example, the aforementioned control device can be a high-performance device composed of multiple processors, and the aforementioned multiple processors can be processors configured on that high-performance device. Alternatively, the aforementioned multiple processors can also be processors deployed on different devices. For example, the aforementioned control device can be a server cluster, and the aforementioned multiple processors can be processors on different servers within the server cluster.

[0206] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for executing the accidental acceleration detection method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described accidental acceleration detection method. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0207] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the driving control method of the above-described method embodiments, and the processor can be configured to execute the program in the storage device. The program includes, but is not limited to, a program for executing the driving control method of the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The control device can be a control device device comprising various electronic devices.

[0208] In embodiments of the present invention, the control device may be a control device device comprising various electronic devices. In some possible implementations, the control device may include multiple storage devices and multiple processors. The program executing the driving control method of the above method embodiments can be divided into multiple subroutines, each subroutine can be loaded and run by a processor to execute different steps of the driving control method of the above method embodiments. Specifically, each subroutine can be stored in different storage devices, and each processor can be configured to execute programs in one or more storage devices to jointly implement the driving control method of the above method embodiments, that is, each processor executes different steps of the driving control method of the above method embodiments to jointly implement the driving control method of the above method embodiments.

[0209] The aforementioned multiple processors can be processors deployed on the same device. For example, the aforementioned control device can be a high-performance device composed of multiple processors, and the aforementioned multiple processors can be processors configured on that high-performance device. Alternatively, the aforementioned multiple processors can also be processors deployed on different devices. For example, the aforementioned control device can be a server cluster, and the aforementioned multiple processors can be processors on different servers within the server cluster.

[0210] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program that performs the driving control method of the above-described method embodiments, the program being loaded and run by a processor to implement the above-described driving control method. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices; optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0211] Furthermore, the present invention also provides a vehicle. In one embodiment of the invention, the vehicle may include a control device as described in the control device embodiment.

[0212] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0213] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0214] The relevant user personal information that may be involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and includes personal information that users actively provide or that is generated as a result of using the product / service, as well as personal information obtained with user authorization.

[0215] The personal information of users processed by the applicant will vary depending on the specific product / service scenario and will be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. The applicant will treat the user's personal information and its processing with a high degree of diligence.

[0216] The applicant attaches great importance to the security of users' personal information and has taken reasonable and feasible security protection measures that meet industry standards to protect users' information and prevent unauthorized access, disclosure, use, modification, damage or loss of personal information.

[0217] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An accelerator misoperation determination method characterized by comprising: The method includes: Acquire vehicle perception information and vehicle control information; Based on the perceived information and the vehicle control information, obtain the confidence level of the accidental acceleration situation; Based on the confidence level, the determination result of the vehicle's accidental acceleration is obtained; The perceived information includes external environmental perception information. The step of "obtaining the confidence level of the accidental acceleration" includes: Based on the external environment perception information and the vehicle control information, obtain the first-level confidence level of the accidental acceleration situation; When the first level of confidence is greater than the preset first confidence threshold, the second level of confidence for the accidental acceleration situation is obtained based on the perceived information, the vehicle control information, and the first level of confidence. The second-order confidence level is taken as the final confidence level for the accidental acceleration situation; The perceived information includes in-vehicle driver perception information, and the step of "obtaining the second-level confidence level of the accidental acceleration situation" includes: The driver's behavior recognition result is obtained based on the driver's perception information; By applying a preset neural network model, the second-level confidence level of the accidental acceleration situation is obtained based on the behavior recognition result, the vehicle control information, and the first-level confidence level. The behavior recognition results include the driver's level of surprise and / or the driver's level of fatigue.

2. The false acceleration determination method according to claim 1, characterized by, The steps for "obtaining the first-level confidence level of the accidental acceleration situation" include: Based on the external environment perception information and the vehicle control information, obtain the first-level confidence discrimination parameters; The first-level confidence level is obtained based on the first-level confidence level discrimination parameter.

3. The false acceleration determination method according to claim 2, characterized by, The first-level confidence discrimination parameters include environmental target factors, scene factors, and accelerator pedal pressure factors. The steps for "obtaining the first-level confidence discrimination parameters" include: Based on the external environment perception information and the vehicle control information, the environmental target factor and the scene factor are obtained; The accelerator pedal pressure factor is obtained based on the vehicle control information.

4. The false acceleration determination method according to claim 3, characterized by, The step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes: Obtain the environmental target weight, scene weight, and accelerator pedal pressure weight corresponding to the preset environmental target factor, scene factor, and accelerator pedal pressure factor, respectively. The first-level confidence level is obtained based on the environmental target factor, the scene factor, the accelerator pedal pressure factor, and the corresponding environmental target weight, scene weight, and accelerator pedal pressure weight.

5. The false acceleration determination method according to claim 3, characterized by, The external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located; the vehicle control information includes accelerator pedal pressure and vehicle movement direction; the step of "obtaining the environmental target factors and the scene factors" includes: The environmental target factor is obtained based on the location of the environmental target and the direction of the vehicle's movement; Based on the type of the scenario, obtain the scenario factor; and / or, The steps for "obtaining the accelerator pedal pressure factor" include: The accelerator pedal pressure factor is obtained based on the accelerator pedal pressure.

6. The false acceleration determination method according to claim 5, characterized by The step of "obtaining the environmental target factor based on the location of the environmental target and the direction of the vehicle's movement" includes: Based on the location of the environmental target, the vehicle's own position, and the vehicle's direction of movement, the overlap between the environmental target and the vehicle within a first preset time period in the future is obtained. The environmental target factor is obtained based on the degree of overlap.

7. The false acceleration determination method according to claim 3, characterized by, The external environment perception information includes environmental targets around the vehicle and the scene in which the vehicle is located; the vehicle control information includes accelerator pedal pressure and vehicle direction of movement; the first-level confidence discrimination parameters include collision risk confidence and / or scene risk confidence; the steps of "obtaining the first-level confidence discrimination parameters" include: The collision risk confidence level is obtained based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of motion. Based on the scenario and the accelerator pedal pressure, obtain the scenario risk confidence level.

8. The false acceleration determination method according to claim 7, characterized by, The steps for "obtaining the collision risk confidence level" include: Based on the location of the environmental target, the accelerator pedal pressure, and the vehicle's direction of movement, the degree of overlap between the vehicle and the environmental target within a first preset time period in the future is obtained. The collision risk confidence level is obtained based on the overlap.

9. The false acceleration determination method according to claim 7, characterized by, The step of "obtaining the risk confidence level of the scenario based on the scenario and the accelerator pedal pressure" includes: The rate of change of the accelerator pedal pressure within a second preset time period is obtained; Based on the rate of change and the scenario, obtain the scenario risk confidence level.

10. The method for determining accidental acceleration according to claim 7, characterized in that, The step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes: When the collision risk confidence level is greater than or equal to a preset third confidence level threshold and the scene risk confidence level is less than a preset fourth confidence level threshold, the first-level confidence level is obtained based on the collision risk confidence level. When the scenario risk confidence level is greater than or equal to the fourth confidence level threshold and the collision risk confidence level is less than the third confidence level threshold, the first-level confidence level is obtained based on the scenario risk confidence level. When the collision risk confidence is less than the third confidence threshold and the scene risk confidence is less than the fourth confidence threshold, or when the collision risk confidence is greater than or equal to the third confidence threshold and the scene risk confidence is greater than or equal to the fourth confidence threshold, the first-level confidence is obtained based on the collision risk confidence and the scene risk confidence.

11. The method for determining accidental acceleration according to claim 7, characterized in that, The step of "obtaining the first-level confidence level based on the first-level confidence level discrimination parameter" includes: The first-level confidence level is obtained by taking a weighted average of the collision risk confidence level and the scenario risk confidence level.

12. The method for determining accidental acceleration according to claim 1, characterized in that, The perception information includes radar perception and warning information, and the vehicle control information includes brake pedal pressure and vehicle movement direction. The step of "obtaining the second-level confidence level of the accidental acceleration situation" includes: The behavior recognition results, brake pedal pressure, vehicle movement direction, first-level confidence score, and radar perception warning information of the same time length are time-aligned and used as input data for the neural network model. The neural network model is used to extract features and calculate confidence levels from the input data to obtain the secondary confidence level.

13. The method for determining accidental acceleration according to claim 1, characterized in that, The step of "obtaining the determination result of the vehicle's accidental acceleration based on the confidence level" includes: When the confidence level is greater than or equal to a preset second confidence threshold, it is determined that the vehicle has a risk of accidentally pressing the accelerator. When the confidence level is less than the second confidence threshold, it is determined that there is no risk of the vehicle accidentally pressing the accelerator.

14. A driving control method, characterized in that, The method includes: The method for determining accidental acceleration according to any one of claims 1 to 13 obtains the determination result of accidental acceleration in a vehicle. Based on the determination result, the vehicle is controlled for driving.

15. The driving control method according to claim 14, characterized in that, The step of "performing driving control of the vehicle based on the determination result" includes: When there is a risk of accidentally pressing the accelerator pedal, the power supply to the vehicle is cut off.

16. A control device comprising at least one processor and at least one storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the method for determining accidental accelerator pedal use as described in any one of claims 1 to 13 or the driving control method as described in any one of claims 14 to 15.

17. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the method for determining accidental accelerator pedal use as described in any one of claims 1 to 13 or the driving control method as described in any one of claims 14 to 15.

18. A vehicle, characterized in that, The vehicle includes the control device as described in claim 16.

Images