Man-machine co-driving method, device and equipment for intelligent driving and vehicle

Abstract

The invention discloses a man-machine co-driving method, device and equipment for intelligent driving and a vehicle. The method comprises the following steps: acquiring historical driving information; learning and establishing a driving habit model according to the historical driving information; acquiring real-time driving information, wherein the real-time driving information comprises corresponding real-time lane line information, real-time vehicle speed information and real-time request torque; according to the real-time lane line information, the real-time vehicle speed information and the driving habit model, torque applying prediction information of a driver is calculated; and calculating output torque information according to the real-time request torque, the driver application torque prediction information and a first preset deviation threshold value, and sending the output torque information to the electric power steering system. According to the real-time driving information and based on the established driving habit model, the most possible torque application information of the driver is predicted in advance, and the torque information is calculated and output and is transmitted to the electric power steering system, so that the preemptive somatosensory of the driver in the process of accepting a steering wheel is weakened.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent driving, and in particular to a human-machine co-driving method, device, equipment and vehicle for intelligent driving. Background Art

[0002] As the level of vehicle intelligence improves, the role of intelligent driving systems in vehicle control is becoming increasingly important. ADAS (Advanced Driving Assistance System) controls the acceleration / braking / steering of the vehicle, and the driver does not need to directly control the vehicle under normal circumstances, but only needs to monitor the driving status of the vehicle. The lateral control function in ADAS is to send a request for the angle / torque to the EPS (Electric Power Steering) controller based on the current vehicle status after ADAS identifies the lane line, so that the vehicle can stay centered in the lane.

[0003] At present, the lateral control function in ADAS has the following problems: First, when the lateral control function in ADAS is just activated or exited, ADAS will send a steering angle / torque request to EPS based on the lane line information and the current vehicle status. At this time, EPS will respond immediately, causing the driver to feel a sense of snatching the steering wheel; Second, when ADAS is activated, the system keeps the vehicle centered, but when the vehicle is driving in the next lane and there is a large truck, the driver will want the vehicle to drive on one side of the lane, but the current system cannot enable the vehicle to drive on one side of the lane. Summary of the invention

[0004] To solve at least one aspect of the above problems, the present invention provides a human-machine co-driving method for intelligent driving, comprising the following steps: obtaining historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; learning and establishing a driving habit model based on the historical driving information; obtaining real-time driving information, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information, and real-time requested torque; calculating the driver applied torque prediction information based on the real-time lane line information, the real-time vehicle speed information, and the driving habit model; calculating the output torque information based on the real-time requested torque, the driver applied torque prediction information, and a first preset deviation threshold, and sending the output torque information to the electric power steering system.

[0005] Preferably, the following steps are also included: obtaining real-time driver-applied torque information; comparing the real-time driver-applied torque information with a first preset driver-applied torque threshold; starting the timing of the first duration when the real-time driver-applied torque information is not less than the first preset driver-applied torque threshold; stopping the timing of the first duration when the real-time driver-applied torque information is less than the first preset driver-applied torque threshold; determining to enter the human-machine co-driving mode when the first duration reaches the first preset duration threshold; when in the human-machine co-driving mode, calculating the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the second preset deviation threshold, and outputting the output torque information Send to the electric power steering system; compare the real-time driver applied torque information and the second preset driver applied torque threshold; when the real-time driver applied torque information is not greater than the second preset driver applied torque threshold, start the timing of the second duration; when the real-time driver applied torque information is greater than the second preset driver applied torque threshold, stop the timing of the second duration; when the second duration reaches the second preset duration threshold, determine to exit the human-machine co-driving mode; during the period of exiting the human-machine co-driving mode, calculate the output torque information according to the real-time requested torque, the real-time driver applied torque information and the third preset deviation threshold, and send the output torque information to the electric power steering system.

[0006] Preferably, the following steps are also included: when exiting the human-machine co-driving mode, comparing the real-time requested torque with the maximum output torque threshold; when the real-time requested torque is greater than the maximum output torque threshold, sending an emergency takeover alarm signal.

[0007] Preferably, the following steps are also included: when in human-machine co-driving mode, obtaining the real-time distance between the center of the front axle of the vehicle and the center line of the lane; comparing the real-time distance between the center of the front axle of the vehicle and the center line of the lane with a preset deviation distance threshold; when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is not less than the preset deviation distance threshold, controlling the vehicle to drive along the center line of the lane; when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is less than the preset deviation distance threshold, controlling the vehicle to drive according to the virtual lane line generated according to the current center of the front axle of the vehicle.

[0008] Preferably, the following steps are also included: comparing the current real-time output torque with the output torque at the previous moment; when the current real-time output torque changes compared with the output torque at the previous moment, determining the current output torque change slope based on the real-time lane line information and the real-time vehicle speed information and based on a preset output torque change slope limiting model, the output torque information sent to the electric power steering system includes the current real-time output torque and the current output torque change slope.

[0009] Preferably, when learning and establishing the driving habit model according to the historical driving information, a corresponding model between the vehicle speed and the driver's applied torque under different lane line curvature radii is established based on a main curve algorithm.

[0010] The present application also provides a human-machine co-driving device for intelligent driving, the device comprising: a first receiving module, configured to obtain historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; a learning module, configured to learn and establish a driving habit model based on the historical driving information; a second receiving module, configured to obtain real-time driving information, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information and real-time requested torque; a prediction module, configured to calculate the driver applied torque prediction information based on the real-time lane line information, real-time vehicle speed information and the driving habit model; a first calculation module, configured to calculate the output torque information based on the real-time requested torque, the driver applied torque prediction information and a first preset deviation threshold, and send the output torque information to the electric power steering system.

[0011] Preferably, the device also includes: a third receiving module, configured to obtain real-time driver-applied torque information; a first comparison module, configured to compare the real-time driver-applied torque information with a first preset driver-applied torque threshold; a first timing module, configured to start timing of a first duration when the real-time driver-applied torque information is not less than the first preset driver-applied torque threshold; and stop timing of the first duration when the real-time driver-applied torque information is less than the first preset driver-applied torque threshold; a first judgment module, configured to determine that the human-machine co-driving mode has been entered when the first duration reaches the first preset duration threshold; and a second calculation module, configured to calculate the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the second preset deviation threshold when in the human-machine co-driving mode, and output the torque information. The output torque information is sent to the electric power steering system; a second comparison module is configured to compare the real-time driver-applied torque information and the second preset driver-applied torque threshold; a second timing module is configured to start the timing of the second duration when the real-time driver-applied torque information is not greater than the second preset driver-applied torque threshold; when the real-time driver-applied torque information is greater than the second preset driver-applied torque threshold, stop the timing of the second duration; a second judgment module is configured to determine to exit the human-machine co-driving mode when the second duration reaches the second preset duration threshold; a third calculation module is configured to calculate the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the third preset deviation threshold during the period of exiting the human-machine co-driving mode, and send the output torque information to the electric power steering system.

[0012] The present application also provides a human-machine co-driving device for intelligent driving, the device comprising a memory and a processor, the memory storing a computer program, and implementing any one of the human-machine co-driving methods for intelligent driving described above when the computer program is executed by the processor.

[0013] The present application also provides a vehicle, which includes a human-machine co-driving device for intelligent driving according to the above description.

[0014] The human-machine co-driving method, device, equipment and vehicle for intelligent driving of the present invention have the following beneficial effects:

[0015] (1) This application predicts the most likely torque information to be applied by the driver in advance based on real-time lane information and real-time vehicle speed information, based on a driving habit model learned and established through historical driving information, and uses this strategy to calculate the output torque information during human-machine co-driving, calculate the output torque information and transmit it to the electric power steering system, which helps to reduce the driver's sense of grabbing the steering wheel during the process.

[0016] (2) The present application determines whether to enter or exit the human-machine co-driving mode based on the torque information applied by the driver to the steering wheel. During the period of entering the human-machine co-driving mode, during the period of being in the human-machine co-driving mode, and during the period of exiting the human-machine co-driving mode, the output torque information is calculated based on the torque information applied by the driver and the strategy of calculating the output torque information during the human-machine co-driving process. The output torque information is calculated and transmitted to the electric power steering system, which helps to reduce the driver's sense of grabbing the steering wheel.

[0017] (3) When exiting the human-machine co-driving mode, this application will determine whether the real-time requested torque exceeds the maximum output torque threshold of the electric power steering system based on real-time driving information. If it exceeds the threshold, an emergency takeover alarm signal will be sent, which will help improve safety during use.

[0018] (4) When the present application is in the human-machine co-driving mode, the real-time distance between the center of the front axle of the vehicle and the center line of the lane will be monitored. When the real-time distance between the center of the front axle of the vehicle and the center line of the lane is less than the preset deviation distance threshold, the vehicle will be controlled to drive along the virtual lane line generated according to the current center of the front axle of the vehicle. When the real-time distance between the center of the front axle of the vehicle and the center line of the lane is not less than the preset deviation distance threshold, the vehicle will be controlled to drive along the center line of the lane. This not only meets the safety requirements, but also enables the vehicle to drive within a certain range of deviation from the center line of the lane, thereby achieving the driver's desired vehicle driving on the side of the lane when there is a large truck in the lane next to the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to better understand the above and other purposes, features, advantages and functions of the present invention, reference may be made to the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings refer to the same components. It should be understood by those skilled in the art that the accompanying drawings are intended to schematically illustrate the preferred embodiments of the present invention and have no limiting effect on the scope of the present invention, and the components in the drawings are not drawn to scale.

[0020] Figure 1 A flow chart of a human-machine co-driving method for intelligent driving according to an embodiment of the present invention is shown;

[0021] Figure 2 A schematic diagram showing a corresponding model of vehicle speed and driver-applied torque under different lane curvature radii established in a human-machine co-driving method for intelligent driving according to an embodiment of the present invention;

[0022] Figure 3 A schematic diagram showing a preset output torque change slope limiting model of the human-machine co-driving method for intelligent driving according to an embodiment of the present invention is shown;

[0023] Figure 4 A structural block diagram of a human-machine co-driving device for intelligent driving according to an embodiment of the present invention is shown.

[0024] Description of reference numerals:

[0025] 101. First receiving module; 102. Learning module; 103. Second receiving module; 104. Prediction module; 105. First calculation module; 106. Third receiving module; 107. First comparison module; 108. First timing module; 109. First judgment module; 110. Second calculation module; 111. Second comparison module; 112. Second timing module; 113. Second judgment module; 114. Third calculation module; 115. Third comparison module; 116. Sending module; 117. Fourth receiving module; 118. Fourth comparison module; 119. Third judgment module. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0027] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0028] In order to at least partially solve the above problems and one or more of other potential problems, the embodiments of the present disclosure provide a human-machine co-driving method for intelligent driving, such as Figure 1 As shown, it can be divided into the stage of about to enter the human-machine co-driving mode, during the period of entering the human-machine co-driving mode, in the human-machine co-driving stage, during the period of exiting the human-machine co-driving mode, and when exiting the human-machine co-driving mode.

[0029] The stage of entering the human-machine co-driving mode includes the following steps: obtaining historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; in a specific embodiment, a number of sensors will be installed on the vehicle, such as sensors for photographing road lane lines, sensors for detecting vehicle speed, sensors for detecting the torque applied by the driver on the steering wheel, etc. The detection results of the several sensors will be processed by the corresponding processors and then output the analysis results to the bus, such as the curvature radius of the lane line, the distance between the center of the vehicle's front axle and the center line of the lane, the vehicle speed, the driver's applied torque information, etc. Some processors will receive certain analysis results on the bus for further processing and then output the analysis results to the bus again, such as requesting torque. Therefore, the present application can obtain driving information from the bus, and the driver will generate a large amount of driving information, namely historical driving information, during use.

[0030] Based on historical driving information, a driving habit model is learned and established; in a preferred embodiment, Figure 2 As shown, when learning and establishing a driving habit model based on historical driving information, a corresponding model between vehicle speed and driver-applied torque under different lane curvature radii is established based on the main curve algorithm. Specifically, the historical driving information is classified according to the lane curvature radius, and then the main curve algorithm is used to analyze the corresponding model between vehicle speed and driver-applied torque.

[0031] Real-time driving information is obtained from the bus, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information and real-time requested torque. According to the real-time lane line information, real-time vehicle speed information and driving habit model, the driver's applied torque prediction information is calculated. According to the real-time requested torque, the driver's applied torque prediction information and the first preset deviation threshold, the output torque information is calculated, and the output torque information is sent to the electric power steering system; in a preferred embodiment, the formula for calculating the output torque information at this stage is the same as the formula for calculating the output torque information in the human-machine co-driving mode, and the formula for calculating the output torque information is: output torque = requested torque - driver applied torque - preset deviation threshold, and the real-time requested torque, the driver's applied torque prediction information and the first preset deviation threshold are substituted into this formula to calculate the output torque at this time, wherein the first preset deviation threshold can be self-calibrated according to the driver's driving habits, and its range can be selected as 0.5~1.5Nm.

[0032] The present application also includes the following steps: obtaining real-time driver applied torque information from the bus; comparing the real-time driver applied torque information with a first preset driver applied torque threshold, where, as an example only, the first preset driver applied torque threshold can be selected as 0.4-1Nm, for example, the first preset driver applied torque threshold is 0.5Nm; when the real-time driver applied torque information is not less than the first preset driver applied torque threshold, starting the timing of the first duration; when the real-time driver applied torque information is less than the first preset driver applied torque threshold, stopping the timing of the first duration; when the first duration reaches the first preset duration threshold, determining to enter the human-machine co-driving mode, where the first preset duration threshold can be selected as 50-200ms, for example, the first preset duration threshold is 100ms.

[0033] In a preferred embodiment, during the period of entering the human-machine co-driving mode, the output torque information is calculated based on the above-mentioned formula for calculating the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the fourth preset deviation threshold, and the output torque information is sent to the electric power steering system, wherein the fourth preset deviation threshold may be equal to or different from the first preset deviation threshold, and the fourth preset deviation threshold may be self-calibrated according to the driver's driving habits, and its range may be selected to be 0.5 to 1.5 Nm.

[0034] When in the human-machine co-driving mode, the output torque information is calculated based on the above formula for calculating the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the second preset deviation threshold, and the output torque information is sent to the electric power steering system, wherein the second preset deviation threshold, the fourth preset deviation threshold and the first preset deviation threshold can be selected to be equal or unequal, and the second preset deviation threshold can be self-calibrated according to the driver's driving habits, and its range can be selected to be 0.5~1.5Nm.

[0035] In a preferred embodiment, the present application also includes the following steps: when in human-machine co-driving mode, obtaining the real-time distance between the center of the front axle of the vehicle and the center line of the lane; comparing the real-time distance between the center of the front axle of the vehicle and the center line of the lane with a preset deviation distance threshold; when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is not less than the preset deviation distance threshold, controlling the vehicle to travel along the center line of the lane; when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is less than the preset deviation distance threshold, controlling the vehicle to travel according to a virtual lane line generated according to the center of the front axle of the current vehicle, wherein the preset deviation distance threshold ranges from 100 to 300 mm, and the virtual lane line generated according to the center of the front axle of the current vehicle is parallel to the center line of the lane, and the distance between them is the real-time distance between the center of the front axle of the vehicle and the center line of the lane.

[0036] Compare the real-time driver applied torque information and the second preset driver applied torque threshold. As an example only, the second preset driver applied torque threshold can be selected as 0.1~0.3Nm, for example, the second preset driver applied torque threshold is 0.2Nm; when the real-time driver applied torque information is not greater than the second preset driver applied torque threshold, start the timing of the second duration; when the real-time driver applied torque information is greater than the second preset driver applied torque threshold, stop timing the second duration; when the second duration reaches the second preset duration threshold, determine to exit the human-machine co-driving mode, wherein the second preset duration threshold can be selected as 50~200ms, for example, the second preset duration threshold is 100ms.

[0037] Preferably, during the period of exiting the human-machine co-driving mode, the output torque information is calculated based on the above-mentioned formula for calculating the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the third preset deviation threshold, and the output torque information is sent to the electric power steering system, wherein the third preset deviation threshold, the second preset deviation threshold, the fourth preset deviation threshold and the first preset deviation threshold can be selected to be equal or unequal, and the third preset deviation threshold can be self-calibrated according to the driver's driving habits, and its range can be selected to be 0.5~1.5Nm.

[0038] In a preferred embodiment, the present application also includes the following steps: when exiting the human-machine co-driving mode, comparing the real-time requested torque with the maximum output torque threshold, wherein the maximum output torque threshold can be selected as 5 to 10 Nm, for example, the maximum output torque threshold is 8 Nm; when the real-time requested torque is greater than the maximum output torque threshold, sending an emergency takeover alarm signal.

[0039] In a preferred embodiment, when the calculation formula for calculating the output torque is used to calculate the output torque before entering the human-machine co-driving mode, during entering the human-machine co-driving mode, during the human-machine co-driving stage, and during exiting the human-machine co-driving mode, the following steps are also included: comparing the current real-time output torque with the output torque at the previous moment; when the current real-time output torque changes compared to the output torque at the previous moment, based on the real-time lane line information and the real-time vehicle speed information, based on a preset output torque change slope limiting model, such as Figure 3 As shown, the current output torque change slope is determined, and the output torque information sent to the electric power steering system includes the current real-time output torque and the current output torque change slope, so that the electric power steering system changes from the output torque at the previous moment to the current output torque at the current output torque change slope. The preset output torque change slope limiting model is a corresponding model of vehicle speed and output torque change slope under different lane curvature radii practiced during the research and development process.

[0040] The present application also provides a human-machine co-driving device for intelligent driving, such as Figure 4 As shown, the device includes: a first receiving module 101, configured to obtain historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; a learning module 102, configured to learn and establish a driving habit model based on historical driving information; a second receiving module 103, configured to obtain real-time driving information, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information and real-time requested torque; a prediction module 104, configured to calculate the driver applied torque prediction information based on the real-time lane line information, real-time vehicle speed information and the driving habit model; a first calculation module 105, configured to calculate the output torque information based on the real-time requested torque, the driver applied torque prediction information and a first preset deviation threshold, and send the output torque information to the electric power steering system.

[0041] Preferably, the device also includes: a third receiving module 106, configured to obtain real-time driver-applied torque information; a first comparison module 107, configured to compare the real-time driver-applied torque information with a first preset driver-applied torque threshold; a first timing module 108, configured to start timing of a first duration when the real-time driver-applied torque information is not less than the first preset driver-applied torque threshold; and stop timing of the first duration when the real-time driver-applied torque information is less than the first preset driver-applied torque threshold; a first judgment module 109, configured to determine that the human-machine co-driving mode has been entered when the first duration reaches the first preset duration threshold; a second calculation module 110, configured to calculate the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the second preset deviation threshold when in the human-machine co-driving mode, and This output torque information is sent to the electric power steering system; a second comparison module 111 is configured to compare the real-time driver-applied torque information and the second preset driver-applied torque threshold; a second timing module 112 is configured to start the timing of the second duration when the real-time driver-applied torque information is not greater than the second preset driver-applied torque threshold; when the real-time driver-applied torque information is greater than the second preset driver-applied torque threshold, stop the timing of the second duration; a second judgment module 113 is configured to determine to exit the human-machine co-driving mode when the second duration reaches the second preset duration threshold; a third calculation module 114 is configured to calculate the output torque information according to the real-time requested torque, the real-time driver-applied torque information and the third preset deviation threshold during the period of exiting the human-machine co-driving mode, and send this output torque information to the electric power steering system.

[0042] Preferably, the device further comprises: a third comparison module 115, configured to compare the real-time request torque with the maximum output torque threshold when exiting the human-machine co-driving mode; a sending module 116, configured to send an emergency takeover alarm signal when the real-time request torque is greater than the maximum output torque threshold. A fourth receiving module 117, configured to obtain the real-time distance between the center of the front axle of the vehicle and the center line of the lane when in the human-machine co-driving mode; a fourth comparison module 118, configured to compare the real-time distance between the center of the front axle of the vehicle and the center line of the lane with a preset deviation distance threshold; a third judgment module 119, configured to control the vehicle to drive in the center of the lane when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is not less than the preset deviation distance threshold; when the real-time distance between the center of the front axle of the vehicle and the center line of the lane is less than the preset deviation distance threshold, control the vehicle to drive in the center of the virtual lane line generated according to the center of the current front axle of the vehicle.

[0043] The present application also provides a human-machine co-driving device for intelligent driving, the device comprising a memory and a processor, the memory storing a computer program, and implementing any one of the human-machine co-driving methods for intelligent driving described above when the computer program is executed by the processor.

[0044] The present application also provides a vehicle, which includes a human-machine co-driving device for intelligent driving according to the above description.

[0045] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the present invention.

Claims

1. A human-machine co-driving method for intelligent driving, characterized in that: The following steps are involved: Acquire historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; Learn and build a driving habit model based on historical driving information; Acquire real-time driving information, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information and real-time requested torque; Calculate the driver's torque prediction information based on real-time lane line information, real-time vehicle speed information and driving habit model; Output torque information is calculated according to the real-time request torque, the driver applied torque prediction information and the first preset deviation threshold, and the output torque information is sent to the electric power steering system.

2. The human-machine co-driving method for intelligent driving according to claim 1, characterized in that: The following steps are also included: Obtain real-time driver applied torque information; comparing the real-time driver applied torque information with a first preset driver applied torque threshold; When the real-time driver applied torque information is not less than a first preset driver applied torque threshold, starting the timing of a first duration; When the real-time driver applied torque information is less than the first preset driver applied torque threshold, stopping the timing of the first duration; When the first duration reaches a first preset duration threshold, determining to enter the human-machine co-driving mode; When in the human-machine co-driving mode, the output torque information is calculated according to the real-time request torque, the real-time driver applied torque information and the second preset deviation threshold, and the output torque information is sent to the electric power steering system; comparing the real-time driver applied torque information with a second preset driver applied torque threshold; When the real-time driver applied torque information is not greater than a second preset driver applied torque threshold, starting the timing of the second duration; When the real-time driver applied torque information is greater than the second preset driver applied torque threshold, stopping the timing of the second duration; When the second duration reaches a second preset duration threshold, determining to exit the human-machine co-driving mode; During the period of exiting the human-machine co-driving mode, the output torque information is calculated according to the real-time requested torque, the real-time driver-applied torque information and the third preset deviation threshold, and the output torque information is sent to the electric power steering system.

3. The human-machine co-driving method for intelligent driving according to claim 2, characterized in that: The following steps are also included: When exiting the human-machine co-driving mode, compare the real-time requested torque with the maximum output torque threshold; When the real-time requested torque is greater than the maximum output torque threshold, an emergency takeover alarm signal is sent.

4. The human-machine co-driving method for intelligent driving according to claim 2, characterized in that: The following steps are also included: When in human-machine co-driving mode, obtain the real-time distance between the center of the vehicle's front axle and the center line of the lane; Comparing the real-time distance between the center of the front axle of the vehicle and the center line of the lane with a preset deviation distance threshold; When the real-time distance between the center of the front axle of the vehicle and the center line of the lane is not less than the preset deviation distance threshold, the vehicle is controlled to drive in the center of the lane center line; When the real-time distance between the center of the vehicle's front axle and the center line of the lane is less than a preset deviation distance threshold, the vehicle is controlled to drive in the center of a virtual lane line generated according to the current center of the vehicle's front axle.

5. A human-machine co-driving method for intelligent driving according to any one of claims 1 to 4, characterized in that: The following steps are also included: Compare the current real-time output torque with the output torque at the previous moment; When the current real-time output torque changes compared to the output torque at the previous moment, the current output torque change slope is determined according to the real-time lane line information and the real-time vehicle speed information and based on the preset output torque change slope limiting model, and the output torque information sent to the electric power steering system includes the current real-time output torque and the current output torque change slope.

6. The human-machine co-driving method for intelligent driving according to claim 1, characterized in that: When learning and establishing a driving habit model based on the historical driving information, a corresponding model between the vehicle speed and the driver's applied torque under different lane line curvature radii is established based on the main curve algorithm.

7. A human-machine co-driving device for intelligent driving, characterized in that: The device comprises: A first receiving module (101) is configured to obtain historical driving information, wherein the historical driving information includes corresponding historical lane line information, historical vehicle speed information, and historical driver applied torque information; A learning module (102), configured to learn and establish a driving habit model based on historical driving information; A second receiving module (103) is configured to obtain real-time driving information, wherein the real-time driving information includes corresponding real-time lane line information, real-time vehicle speed information and real-time requested torque; A prediction module (104), configured to calculate driver applied torque prediction information based on real-time lane line information, real-time vehicle speed information and a driving habit model; The first calculation module (105) is configured to calculate output torque information according to the real-time request torque, driver applied torque prediction information and a first preset deviation threshold, and send the output torque information to the electric power steering system.

8. The human-machine co-driving device for intelligent driving according to claim 7, characterized in that: The device also includes: A third receiving module (106), configured to obtain real-time driver applied torque information; A first comparison module (107) configured to compare the real-time driver applied torque information with a first preset driver applied torque threshold; A first timing module (108) is configured to start timing of a first duration when the real-time driver applied torque information is not less than a first preset driver applied torque threshold; and stop timing of the first duration when the real-time driver applied torque information is less than the first preset driver applied torque threshold; A first judgment module (109) is configured to determine that a human-machine co-driving mode has been entered when a first duration reaches a first preset duration threshold; A second calculation module (110) is configured to calculate output torque information according to real-time request torque, real-time driver applied torque information and a second preset deviation threshold when in a human-machine co-driving mode, and send the output torque information to the electric power steering system; A second comparison module (111) configured to compare the real-time driver applied torque information with a second preset driver applied torque threshold; A second timing module (112) is configured to start timing of a second duration when the real-time driver applied torque information is not greater than a second preset driver applied torque threshold; and stop timing of the second duration when the real-time driver applied torque information is greater than the second preset driver applied torque threshold; A second judgment module (113) is configured to determine to exit the human-machine co-driving mode when the second duration reaches a second preset duration threshold; The third calculation module (114) is configured to calculate output torque information according to real-time requested torque, real-time driver applied torque information and a third preset deviation threshold value during the period of exiting the human-machine co-driving mode, and send the output torque information to the electric power steering system.

9. A human-machine co-driving device for intelligent driving, characterized in that: The device includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, a human-machine co-driving method for intelligent driving according to any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: The vehicle includes a human-machine co-driving device for intelligent driving according to claim 9.

Images