Hands-off detection method, device, equipment and computer-readable storage medium

Abstract

A hands-off detection method, device, equipment, and computer-readable storage medium are disclosed. The method includes: determining whether the HOD system is trustworthy; determining whether the EPS is trustworthy, and setting different hand torque reference thresholds based on the trustworthiness of the HOD system; if both the HOD system and the EPS are trustworthy, detecting whether the hands are off using the HOD system and the EPS respectively; if either detection result indicates that the hands are not off, outputting a determination result of "hands not off"; if both detection results indicate that the hands are off, outputting a determination result of "hands off"; if only one of the HOD system and the EPS is trustworthy, detecting whether the hands are off using the trusted system alone and outputting a determination result. The hands-off detection method, device, equipment, and computer-readable storage medium disclosed in the present invention can solve the technical problem of the prior art in being unable to accurately detect hands-off.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a hands-off detection method, device, equipment, and computer-readable storage medium. Background Art

[0002] With the increasing popularity of advanced intelligent driving applications, many functions require the driver to maintain a hands-on grip on the steering wheel, allowing them to take over vehicle control in emergencies. Prolonged hands-off driving poses significant safety risks. To ensure safety, intelligent driving systems must accurately detect hands-off behavior and issue a hands-off warning or terminate intelligent driving control after a certain period of time. Therefore, accurate hands-off detection has become a crucial requirement for intelligent driving systems.

[0003] In the current state of the art, a low-cost and effective method is to indirectly detect hands-off control using EPS hand torque. However, this method requires hand torque fluctuations, and a driver's loose grip on the steering wheel will not be detected. Furthermore, this method requires high consistency in EPS hand torque. In practice, due to variations in vehicle manufacturing consistency or after steering system repairs, EPS hand torque values may fluctuate widely. Relying solely on EPS detection methods cannot fully and accurately detect hand torque, and this indirect detection method is prone to missed or false detections.

[0004] Another existing hands-off detection method, used in some luxury vehicles, involves integrating a capacitive pressure sensor into the steering wheel to create a hands-off detection system. This system detects whether the driver's hands are off the wheel and issues an alarm if the hands are off the wheel for a certain period of time. However, capacitive steering wheels can also fail, for example, when the driver is wearing gloves or a steering wheel cover, in inclement weather (such as extreme cold or heat), or when the capacitive steering wheel malfunctions. Summary of the Invention

[0005] The present application provides a hands-off detection method, device, equipment and computer-readable storage medium, which can solve the technical problem of the existing technology that cannot accurately solve the hands-off detection problem.

[0006] In a first aspect, an embodiment of the present application provides a hands-off detection method, the method comprising:

[0007] Determine whether the HOD system is trustworthy; determine whether the EPS is trustworthy; if both the HOD system and the EPS are trustworthy, then detect whether the hands are released based on the HOD system and EPS respectively. When either detection result is not released, the output judgment result is not released; when both judgment results are hands-off, the output judgment result is hands-off; if only one of the HOD system and the EPS is trustworthy, use the trusted system alone to detect whether the hands are released and output the judgment result.

[0008] In conjunction with the first aspect, in one embodiment, the step of determining whether the HOD system is trustworthy specifically includes:

[0009] When the HOD system informs that the operating status is good, the default HOD status is credible, and the EPS hand torque value collected at time t is recorded as Torque t The value after filtering the absolute value of the EPS hand torque value collected at time t is Tor t ; When any of the following conditions are met during vehicle operation, the HOD system is judged to be untrustworthy: a) If the HOD system determines that the hands-free mode is released during the power-on cycle, Tor t If the value is greater than the preset threshold for more than the first time, the HOD system still determines that the hands are released; b) If the HOD system determines that the hands are not released during the power-on cycle, Tor t If the value is less than the preset lower threshold for more than the first time, the HOD system still determines that the hands have not been released; c) the HOD system reports a fault.

[0010] In another embodiment, when the HOD system is credible, the step of determining whether the EPS is credible specifically includes:

[0011] When the car is powered on, the EPS is judged to be credible by default; when the HOD system is credible and the detection result is hands-off, the EPS detection result is that the hands are not released and the duration exceeds the second time, and the filtered hand torque value continues to fluctuate within the preset range, then the EPS is judged to be untrustworthy at this time; when the EPS is in an untrustworthy state, the HOD system is credible and the detection result is hands-off, and the EPS hand torque can determine that the hands are released for more than the fourth time, the EPS is changed to credible.

[0012] In another embodiment, different hand torque reference thresholds are set according to the credibility of the HOD system. The hand torque reference thresholds include setting a first hand torque reference threshold when the HOD system is credible and a second hand torque reference threshold when the HOD system is untrustworthy.

[0013] Based on the above scheme, when the HOD system is credible and the result of the HOD system judgment is hands-off, it also includes: using the hand torque value obtained by the HOD system detection to self-learn and calibrate the first hand torque reference threshold when the EPS is credible.

[0014] Specifically, the self-learning calibration of the first hand torque reference threshold when the EPS is reliable using the hand torque value detected by the HOD system includes:

[0015] The hand torque value in the LCC control process after the hands-off state is determined by the HOD system is collected, the hand torque is filtered, and the maximum and minimum hand torque values in the control process in the hands-off state are obtained; when the first hand torque lower reference threshold is greater than the minimum hand torque value in the control process, the correction process is exited; when the first hand torque lower reference threshold is less than or equal to the minimum hand torque value, the first hand torque lower reference threshold is corrected to the minimum hand torque value plus a first adjustment constant.

[0016] Specifically, when the hand torque value in the control process is greater than or equal to the first hand torque reference upper threshold, the time t when the value appears and the filtered value Tor of the absolute value of the EPS hand torque value at that moment are recorded. t , until the hand torque value in the control process is less than the first hand torque reference upper threshold or the HOD system determines that the hand is not released;

[0017] If the hand torque value in the control process is greater than or equal to the first hand torque benchmark upper threshold and the maintenance time exceeds the third time, the first hand torque benchmark upper threshold is corrected to the minimum value of the filtered value of the absolute value of the EPS hand torque value in the recording time period plus the first adjustment constant.

[0018] In a second aspect, an embodiment of the present application provides a hands-off detection device, comprising:

[0019] A credibility determination module is used to determine whether the HOD system and EPS are trustworthy; a threshold management module is used to set different hand torque reference thresholds according to the credibility of the HOD system; a hands-off judgment module is used to detect whether the hands are off-camera based on the HOD system and EPS respectively when both the HOD system and EPS are trustworthy. When either detection result is that the hands are not off-camera, the judgment result is output as not off-camera; when both judgment results are that the hands are off-camera, the judgment result is output as hands off-camera; and when only one of the HOD system and EPS is trustworthy, the trusted system is used alone to detect whether the hands are off-camera and output the judgment result.

[0020] In a third aspect, an embodiment of the present application provides a hands-off detection device, which includes a processor, a memory, and a hands-off detection program stored in the memory and executable by the processor, wherein when the hands-off detection program is executed by the processor, the steps of the hands-off detection method described in any of the previous items are implemented.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a hands-off detection program is stored, wherein when the hands-off detection program is executed by a processor, the steps of the hands-off detection method as described in any of the preceding items are implemented.

[0022] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0023] By successively judging whether the HOD system and EPS are credible, if both are credible, the HOD system and EPS are used to detect whether the hands are out of the car. By combining the capacitive sensor and EPS hand torque to jointly detect whether the driver is in a hands-off state, the problem of large error fluctuations when only a single sensor is used for detection in related technologies is solved, and the advantages of both can be used to more accurately determine the hands-off behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of an embodiment of the hands-off detection method of the present application;

[0025] Figure 2 This is a flow chart of another embodiment of the hands-off detection method of the present application;

[0026] Figure 3 Schematic diagram of the hardware structure of the hands-off detection device involved in the embodiment of the present application;

[0027] Figure 4 This is a schematic diagram of the functional modules of an embodiment of the hands-off detection device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] First, some technical terms in this application are explained to facilitate those skilled in the art to understand this application.

[0030] EPS: Electric Power Steering, electronic power steering system.

[0031] HOD: Hands Off Detection, hands off detection.

[0032] LCC: Lane Center Control, lane center control.

[0033] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0034] In a first aspect, embodiments of the present application provide a hands-off detection method.

[0035] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the hands-off detection method of this application. Figure 1 As shown, the hands-off detection method includes:

[0036] Determine whether the HOD system is trustworthy; determine whether the EPS is trustworthy; if both the HOD system and the EPS are trustworthy, then detect whether the hands are released based on the HOD system and EPS respectively. When either detection result is not released, the output judgment result is not released; when both judgment results are hands-off, the output judgment result is hands-off; if only one of the HOD system and the EPS is trustworthy, use the trusted system alone to detect whether the hands are released and output the judgment result.

[0037] In actual situations, the advantage of the HOD system using a capacitive steering wheel is that it can detect when the hands are on the steering wheel but not turning the steering wheel, and it can accurately detect the hands-on state (i.e., when the hands are holding the steering wheel, the detection state is handson). When the driver wears gloves or the HOD system is not sensitive, the HOD system fails, and the hands-on state cannot be detected, and it is mistakenly detected as the hands-off state (i.e., when the hands are off the steering wheel, the detection state is handoff). When the HOD system fails, the hands-off state detection result is unreliable. The EPS detection result is determined by a preset hand torque reference threshold. If the preset hand torque reference threshold is larger, the credibility of the hands-on state judgment result is high, and if the preset hand torque reference threshold is smaller, the credibility of the hands-off state judgment result is high. Therefore, the HOD system and EPS each have advantages and disadvantages when used for hands-off state detection. It is necessary to combine the advantages and disadvantages of the two to design a more accurate judgment method.

[0038] In this embodiment, by combining the capacitive sensor and EPS hand torque to jointly detect whether the driver is in a hands-off state, the problem of large error fluctuations when only a single sensor is used for detection in related technologies is solved, and the advantages of both can be used to more accurately judge the hands-off behavior.

[0039] Furthermore, in one embodiment, the step of determining whether the HOD system is trustworthy specifically includes:

[0040] When the HOD system informs the HOD sensor that the operating status is good (i.e., HOD_Status = No error), the HOD status is assumed to be credible, and the EPS hand torque value collected at time t is recorded as Torque t The value after filtering the absolute value of the EPS hand torque value collected at time t is Tor t , a common filtering method, Tor t=(1-Q)*Tor t-1 +Q*Torque t ,Q value is the quality factor determined by the filter performance; when any of the following conditions are met during vehicle operation, the HOD system is judged to be untrustworthy: a) If the HOD system determines that the hands-free mode is released during the power-on cycle, Tor t If the force is greater than the preset threshold of 0.6Nm for more than 400ms, the HOD system still determines that the hands are released; b) If the HOD system determines that the hands are not released during the power-on cycle, Tor t If the force is less than the preset lower threshold of 0.1Nm for more than 400ms, the HOD system still determines that the hands are not released; c) The HOD system reports a fault. This solution avoids the situation where the HOD system incorrectly determines that the driver is wearing gloves, the steering wheel cover, or the capacitive hardware detection fails, but the HOD system does not report a fault.

[0041] When the HOD system is judged to be untrustworthy, and there is no fault in the HOD system, and the following conditions are met, the HOD system can be switched from untrustworthy to trusted state: 1. The HOD system judges to be untrustworthy, when Tor t If the force is greater than the preset threshold A (such as 0.5Nm) for more than the preset time (such as 500ms), and the HOD system determines that the hands are out of the way, then the HOD is considered to be reliable. t If the force is less than threshold A (e.g., 0.1 Nm) for a preset time (e.g., 500 ms), the HOD will be judged as hands-off and the HOD will be considered reliable. This approach further avoids the situation where the system mistakenly believes that the HOD system detection is correct, resulting in a false alarm or a false alarm that cannot be cleared.

[0042] Furthermore, when the HOD system is trustworthy, the steps for determining whether the EPS is trustworthy specifically include:

[0043] When the car is powered on, the EPS is judged to be credible by default; when the HOD system is credible and the detection result is hands-off, the EPS detection result is that the hands are not released and the duration exceeds the second time, and the filtered hand torque value continues to fluctuate within the preset range, then the EPS is judged to be untrustworthy at this time; when the EPS is in an untrustworthy state, the HOD system is credible and the detection result is hands-off, and the EPS hand torque can determine that the hands are released for more than the fourth time, the EPS is changed to credible.

[0044] Using EPS for hands-off detection requires setting hand torque thresholds. These thresholds include an upper hand torque threshold C and a lower hand torque threshold D. If the hand torque value (torque > C) persists for more than a third time, the hands are considered to be on the vehicle. A timer starts when the hand torque is significantly less than the lower hand torque threshold D. If the duration of torque < C exceeds a certain time (T4), the hands are considered off. The upper hand torque threshold C and the lower hand torque threshold D are determined based on vehicle testing and calibration during the development phase. In another embodiment, different upper and lower hand torque thresholds are set based on the HOD system's reliability. The relevant steps specifically include setting a first hand torque threshold when the HOD system is reliable and a second hand torque threshold when the HOD system is unreliable. For example, the first hand torque threshold when the HOD system is reliable is set to C1 and D1, and the first hand torque threshold when the EPS is unreliable is set to C2 and D2, where C1 is greater than C2, D1 is greater than D2, and the difference between C1 and D1 is equal to the difference between C2 and D2. Through the setting of the above steps, this embodiment further sets different hand torque reference thresholds under different trustworthy conditions of the HOD system, thereby solving the problem that in the existing EPS hands-off detection scheme, in order to ensure high accuracy of EPS hands-off detection, the judgment threshold is increased, which correspondingly generates some false alarms, resulting in the inability to detect the hands-on state after the HOD system fails.

[0045] Specifically, in this embodiment, the aforementioned steps of "detecting whether the hands are off using both the HOD system and the EPS; if either detection result indicates that the hands are not off, outputting a judgment result of "not off"; if both detection results indicate that the hands are off, outputting a judgment result of "hands off"; and if only one of the HOD system and the EPS is trustworthy, using the trustworthy system alone to detect whether the hands are off and outputting a judgment result" are specifically executed as follows:

[0046] 1. When the HOD system determines that the information is reliable and the EPS system determines that the information is reliable:

[0047] The system determines that the hands are not released if: the HOD system determines that the hands are not released or the EPS system determines that the hands are not released (using the C1 value for judgment);

[0048] The conditions for the system to judge as hands-off are: the HOD system judges that the hands are not released and the EPS judges that the hands are released (using the C1 value for judgment).

[0049] 2. When the HOD system determines that the data is credible, but the EPS system determines that the data is not credible:

[0050] The conditions for the system to judge that the hands are not released are: the HOD system judges that the hands are not released;

[0051] The conditions for the system to judge as disposal are: HOD system judges disposal.

[0052] 3. When the HOD system determines that the device is untrustworthy:

[0053] The conditions for the system to judge that the stock has not been sold are: EPS judges that the stock has not been sold (using the C2 value for judgment);

[0054] The conditions for the system to judge as selling are: EPS judges to sell (using C2 value for judgment).

[0055] Building on the above solution, when the HOD system is reliable and the HOD system determines that the hands are off, the solution also includes: using the hand torque value detected by the HOD system to self-learn and calibrate the first hand torque reference threshold for the EPS when it is reliable. This solution addresses the problem of HOD system failure or unreliable HOD system detection methods, requiring the use of EPS detection methods, but the inherent limitations of EPS detection can lead to inaccurate detection in some situations. This solution improves the accuracy of EPS hand torque detection and provides each vehicle with the ability to self-learn and calibrate EPS detection parameters.

[0056] Specifically, the self-learning calibration of the first hand torque reference threshold when the EPS is reliable using the hand torque value detected by the HOD system includes:

[0057] The result of the HOD system judgment is the hand torque value in the LCC control process after the hands are released. The hand torque is filtered and the filtered hand torque value at time t is Tor. t . Get the maximum and minimum values of the hand torque value in the control process of the hands-off state, wherein the minimum value of the hand torque in the hands-off state Tor is obtained. min =min{Tor0, Tor1,...Tor t}, get the maximum torque Tor of the hand in the hands-off state max =max{Tor0, Tor1,...Tor t}; When the first hand torque reference lower threshold is greater than the minimum value of the hand torque value in the control process, exit the correction process; when the first hand torque reference lower threshold is less than or equal to the minimum value of the hand torque value, correct the first hand torque reference lower threshold to the minimum value of the hand torque value plus the first adjustment constant.

[0058] Specifically, when the hand torque value in the control process is greater than or equal to the first hand torque reference upper threshold, the time t when the value appears and the filtered value Tor of the absolute value of the EPS hand torque value at that moment are recorded. t , until the hand torque value in the control process is less than the first hand torque reference upper threshold or the HOD system determines that the hand is not released;

[0059] If the hand torque value in the control process is greater than or equal to the first hand torque benchmark upper threshold and the maintenance time exceeds the third time, the first hand torque benchmark upper threshold is corrected to the minimum value of the filtered value of the absolute value of the EPS hand torque value in the recording time period plus the first adjustment constant.

[0060] Furthermore, in this embodiment, if the calibration values of C1 and D1 are too large, they need to be reduced to prevent excessive false alarms. The calibration method is:

[0061] If C1 is much larger than Tor max , i.e. C1>Tor max +Z (Z is a preset parameter, such as 0.15Nm in this embodiment), then C1 needs to be reduced; then set C1 = Tor max +0.1, and reset D1 according to the preset difference between C1 and C1, while ensuring that the reset D1>Tor min In order to prevent the correction data from being too little and causing omission, the corrected minimum value of C1 is not less than the preset minimum parameter (such as 0.2 Nm in this embodiment).

[0062] The above method is used to continuously correct the upper threshold value and the lower threshold value of the first hand torque benchmark. The more test data, the better the correction effect. Repeat the above method to correct the data of different vehicle speed ranges until no sensitive data is recorded, and the correction process of the hands-off parameters, i.e., the upper threshold value and the lower threshold value of the first hand torque benchmark, is completed.

[0063] Second, as Figure 4 As shown, an embodiment of the present application also provides a hands-off detection device.

[0064] In one embodiment, the hands-off detection device includes:

[0065] A credibility determination module is used to determine whether the HOD system and EPS are trustworthy; a threshold management module is used to set different hand torque reference thresholds according to the credibility of the HOD system; a hands-off judgment module is used to detect whether the hands are off-camera based on the HOD system and EPS respectively when both the HOD system and EPS are trustworthy. When either detection result is that the hands are not off-camera, the judgment result is output as not off-camera; when both judgment results are that the hands are off-camera, the judgment result is output as hands off-camera; and when only one of the HOD system and EPS is trustworthy, the trusted system is used alone to detect whether the hands are off-camera and output the judgment result.

[0066] Furthermore, in one embodiment, the credibility determination module in the hands-off detection device is further configured to: determine that the HOD state is credible when the HOD system informs that the operating state is good; collect the EPS hand torque value at time t collected by the EPS as Torque t, the value obtained by filtering the absolute value of the EPS hand torque value collected at time t is Tort; and when any of the following conditions is met during vehicle operation, the HOD system is determined to be untrustworthy:

[0067] a) If, during the power-on cycle, the HOD system determines that the handset has been released, and Tort exceeds the preset threshold for a period of time exceeding the first time, the HOD system still determines that the handset has been released; b) If, during the power-on cycle, the HOD system determines that the handset has not been released, and Tort is less than the preset lower threshold for a period of time exceeding the first time, the HOD system still determines that the handset has not been released; c) The HOD system reports a fault.

[0068] Furthermore, in one embodiment, the credibility judgment module in the hands-off detection device is also used to: when the car is powered on, the EPS is judged to be credible by default; when the HOD system is credible and the detection result is hands-off, the EPS detection result is that the hands are not released and the duration exceeds the second time, and the filtered hand torque value continues to fluctuate within the preset range, then the EPS is judged to be unreliable at this time; when the EPS is in an unreliable state, the HOD system is credible and the detection result is hands-off and the EPS hand torque can determine that the hands are released for more than a fourth time, then the EPS is changed to credible.

[0069] Furthermore, in one embodiment, the threshold management module in the hands-off detection device is further configured to set a first hand torque reference threshold when the EPS is credible and a second hand torque reference threshold when the EPS is untrustworthy.

[0070] Furthermore, in one embodiment, the threshold management module in the hands-off detection device is also used to: when the HOD system is credible and the HOD system determines that the hands are off, use the hand torque value obtained by the HOD system detection to self-learn and calibrate the first hand torque reference threshold when the EPS is credible.

[0071] Furthermore, in one embodiment, the threshold management module in the hands-off detection device is further configured to: self-learn and calibrate the first hand torque reference threshold when the EPS is reliable using the hand torque value detected by the HOD system, including:

[0072] The hand torque value in the LCC control process after the hands-off state is determined by the HOD system is collected, the hand torque is filtered, and the maximum and minimum hand torque values in the control process in the hands-off state are obtained; when the first hand torque lower reference threshold is greater than the minimum hand torque value in the control process, the correction process is exited; when the first hand torque lower reference threshold is less than or equal to the minimum hand torque value, the first hand torque lower reference threshold is corrected to the minimum hand torque value plus a first adjustment constant.

[0073] Furthermore, in one embodiment, the threshold management module in the hands-off detection device is further configured to:

[0074] When the hand torque value in the control process is greater than or equal to the first hand torque benchmark upper threshold, the time t at which the value appears and the value Tort after filtering the absolute value of the EPS hand torque value at that moment are recorded until the hand torque value in the control process is less than the first hand torque benchmark upper threshold or the HOD system determines that the hand is not released; if the hand torque value in the control process is greater than or equal to the first hand torque benchmark upper threshold and the state is maintained for more than a third time, the first hand torque benchmark upper threshold is corrected to the minimum value of the value after filtering the absolute value of the EPS hand torque value in the recording time period plus the first adjustment constant.

[0075] Among them, the functional implementation of each module in the above-mentioned hands-off detection device corresponds to the various steps in the above-mentioned hands-off detection method embodiment, and their functions and implementation processes will not be repeated here one by one.

[0076] In a third aspect, an embodiment of the present application provides a hands-off detection device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0077] Reference Figure 3 , Figure 3 FIG2 is a schematic diagram of the hardware structure of the hands-off detection device involved in the embodiment of the present application. In the embodiment of the present application, the hands-off detection device may include a processor, a memory, a communication interface, and a communication bus.

[0078] The communication bus may be of any type and is used to interconnect the processor, memory, and communication interface.

[0079] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect components within the hands-off detection device, as well as interfaces used to interconnect the hands-off detection device with other devices (such as other computing devices or user devices). Physical interfaces can be Ethernet, fiber, or ATM interfaces; user devices can be displays or keyboards.

[0080] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0081] The processor may be a general-purpose processor that can call a hands-off detection program stored in a memory and execute the hands-off detection method provided in the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the hands-off detection program is called can be referred to in the various embodiments of the hands-off detection method of the present application and will not be further described here.

[0082] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation to the present application and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0083] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0084] The computer-readable storage medium of the present application stores a hands-off detection program, wherein when the hands-off detection program is executed by a processor, the steps of the hands-off detection method described above are implemented.

[0085] Among them, the method implemented when the hands-off detection program is executed can refer to the various embodiments of the hands-off detection method of this application, and will not be repeated here.

[0086] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0087] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit the "first", "second" and "third" to different types.

[0088] In the description of the embodiments of this application, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0089] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0090] In some processes described in the embodiments of the present application, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be performed in the order in which they appear in the embodiments of the present application or may be performed in parallel. The sequence numbers of the operations are only used to distinguish between different operations, and the sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations or steps may be performed in sequence or in parallel, and these operations or steps may be combined.

[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present application.

[0092] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A hands-off detection method, characterized in that: The hands-off detection method comprises: Determine whether the HOD system is trustworthy; Determine whether EPS is credible; When using EPS for hands-off detection, different EPS hand torque reference thresholds are set according to the reliability of the HOD system. The EPS hand torque reference thresholds include a first hand torque reference threshold when the HOD system is reliable and a second hand torque reference threshold when the HOD system is unreliable. If both the HOD system and the EPS are reliable, the HOD system and the EPS will detect whether the hands are off. If either detection result indicates that the hands are not off, the output judgment result is not off. If both detection results indicate that the hands are off, the output judgment result is off. If only one of the HOD system and the EPS is trustworthy, the trustworthy system is used to detect whether the hands-off status is established and output the judgment result.

2. The hands-off detection method according to claim 1, wherein: The steps of determining whether the HOD system is trustworthy specifically include: When the HOD system informs that the operating status is good, the default HOD status is credible, and the EPS hand torque value collected at time t is recorded as Torque t The value after filtering the absolute value of the EPS hand torque value collected at time t is Tor t ; When any of the following conditions are met during vehicle operation, the HOD system is considered untrustworthy: a) If the HOD system determines that the hand is released during the power-on cycle, Tor t If the value is greater than the preset threshold for more than the first time, the HOD system still determines that the hands are released; b) If the HOD system determines that the hand is not released during the power-on cycle, Tor t When the vehicle is less than the preset lower threshold for more than the first time, the HOD system still determines that the vehicle has not been released; c) HOD system reports a fault.

3. The hands-off detection method according to claim 1, wherein: The steps of determining whether the EPS is credible specifically include: When the car is powered on, the EPS is judged to be trustworthy by default; When the HOD system is credible and the detection result is hands-off, the EPS detection result is hands-on and the duration exceeds the second time, and the filtered hand torque value continues to fluctuate within the preset range, then the EPS is judged to be untrustworthy at this time; When the EPS is in an untrusted state, the HOD system is trusted, the detection result is hands-off, and the EPS hand torque can determine that the hands-off exceeds the fourth time, the EPS is changed to trusted.

4. The hands-off detection method according to claim 1, wherein: When the HOD system is credible and the result of the HOD system's judgment is a hands-off, it also includes: The hand torque value detected by the HOD system is used to self-learn and calibrate the first hand torque reference threshold.

5. The hands-off detection method according to claim 4, wherein: The self-learning calibration of the first hand torque reference threshold using the hand torque value detected by the HOD system includes: Collecting the hand torque value during the LCC control process after the HOD system determines that the hand is released, filtering the hand torque, and obtaining the maximum and minimum hand torque values during the control process in the hands-off state; When the first hand torque reference lower threshold is greater than the minimum value of the hand torque value in the control process, the correction process is exited; when the first hand torque reference lower threshold is less than or equal to the minimum value of the hand torque value, the first hand torque reference lower threshold is corrected to the minimum value of the hand torque value plus the first adjustment constant.

6. The hands-off detection method according to claim 5, wherein: Also includes: When the hand torque value in the control process is greater than or equal to the first hand torque reference upper threshold, the time t when the value appears and the filtered value Tor of the absolute value of the EPS hand torque value at that moment are recorded. t , until the hand torque value in the control process is less than the first hand torque reference upper threshold or the HOD system determines that the hand is not released; If the hand torque value in the control process is greater than or equal to the first hand torque benchmark upper threshold and the maintenance time exceeds the third time, the first hand torque benchmark upper threshold is corrected to the minimum value of the filtered value of the absolute value of the EPS hand torque value in the recording time period plus the first adjustment constant.

7. A hands-off detection device, characterized in that: The hands-off detection device comprises: Credibility determination module, which is used to determine whether the HOD system and EPS are credible; A threshold management module, configured to set different EPS hand torque reference thresholds based on the reliability of the HOD system when using EPS for hands-off detection; the EPS hand torque reference thresholds include a first hand torque reference threshold when the HOD system is reliable and a second hand torque reference threshold when the HOD system is unreliable; The hands-off judgment module is used to detect whether the hands are off based on the HOD system and EPS respectively when both the HOD system and EPS are trustworthy. When either detection result is that the hands are not off, the judgment result is output as not off; when both judgment results are that the hands are off, the judgment result is output as hands off; and when only one of the HOD system and EPS is trustworthy, the trusted system is used alone to detect whether the hands are off and output the judgment result.

8. A hands-off detection device, characterized in that: The hands-off detection device includes a processor, a memory, and a hands-off detection program stored in the memory and executable by the processor, wherein when the hands-off detection program is executed by the processor, the steps of the hands-off detection method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a hands-off detection program, wherein when the hands-off detection program is executed by a processor, the steps of the hands-off detection method according to any one of claims 1 to 6 are implemented.

Images