Steering control system and method for new energy vehicle

Abstract

The invention provides a new energy vehicle steering control system and method, and belongs to the technical field of traffic control systems. According to the method, the stress of the steering wheel is collected, the control force of the steering wheel is divided into three grades, the stress is divided into the first grade, the second grade and the third grade from large to small, and different steering control strategies are adopted under different grades in combination with image collection and state analysis of a driver; and on the premise of ensuring the driving safety, the experience feeling of a driver is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control systems, and in particular to a steering control system and method for new energy vehicles. Background Art

[0002] The working principle of electric vehicles mainly involves the conversion of electrical energy into mechanical energy. Generally speaking, electric vehicles use an on-board power source (such as a battery pack) to provide electrical energy to the motor, which converts electrical energy into mechanical energy and drives the wheels through the transmission system. Specifically, the working principle of electric vehicles includes the following steps: the battery stores electrical energy, the current enters the motor through the power conditioner, the motor converts electrical energy into mechanical energy, and the power transmission system transmits the mechanical energy to the wheels to drive the car.

[0003] It is precisely because of the sufficient power supply and fast electronic control response speed that intelligent driving becomes possible. Intelligent driving, also known as autonomous driving or intelligent vehicle technology, refers to the technology that uses sensors, controllers, actuators, communication modules and other equipment to assist the driver or completely replace the driver in controlling the vehicle.

[0004] With the further development of electric vehicles, the intelligence level of smart driving is getting higher and higher, such as steering control when encountering abnormal situations, but its trust level is still low. For experienced drivers, they are more willing to use it as a driving aid. Many users want to experience the fun of smart driving but are unwilling to have too much intervention from smart driving, which makes it easy to lose control of steering. Although some models have added a switch button for the assisted driving function, turning off the assisted driving will reduce the experience of electric vehicles, which makes users have great contradictions when using them. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a steering control system and method for a new energy vehicle. By collecting the force on the steering wheel, the control force of the steering wheel is divided into three levels, and the force is respectively the first level, the second level and the third level from large to small. Combined with image collection and status analysis of the driver, different steering control strategies are adopted at different levels, which greatly improves the driver's experience while ensuring driving safety.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a steering control system for a new energy vehicle.

[0007] A new energy vehicle steering control system, comprising: a vehicle-mounted control terminal, a vehicle-mounted laser radar device and a vehicle-mounted image acquisition device, wherein the vehicle-mounted control terminal is respectively connected to the vehicle-mounted laser radar device and the vehicle-mounted image acquisition device for communication; The vehicle-mounted laser radar device is used to collect point cloud data around the vehicle in real time and send it to the vehicle-mounted control terminal. The vehicle-mounted image acquisition device collects the image of the driver in the vehicle in real time and sends it to the vehicle-mounted control terminal; The vehicle control terminal is configured to perform the following process: Identify objects around the vehicle based on the collected point cloud data to obtain identification results of the surrounding objects, determine the relative distance and relative speed between each object identification result and the vehicle in real time, make abnormality judgment based on the relative distance and relative speed, and execute the steering control judgment step when an abnormality requiring steering control occurs; The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

[0008] As a further limitation of the first aspect of the present invention, the abnormalities requiring steering control include: the vehicle ahead suddenly decelerates and the speed at which the relative distance decreases is greater than a set threshold, or a pedestrian appears ahead and the relative distance is less than the braking distance, or the speed at which the distance between vehicles on both sides decreases is greater than a set value.

[0009] As a further limitation of the first aspect of the present invention, the driver status is abnormal, including: the driver is detected yawning N times in a set time, or the driver's hands are detected off the steering wheel N times in a set time, or the driver is detected checking the mobile phone N times in a set time, or the driver is detected with an anxious expression N times in a set time, where N is greater than or equal to 3.

[0010] As a further limitation of the first aspect of the present invention, the intelligent steering control actively intervenes after an alarm, and also includes: setting a difference time between the alarm and the active intervention, and terminating the active intervention of the steering control according to the driver's interruption voice command during the time period between the alarm and the active intervention.

[0011] As a further limitation of the first aspect of the present invention, the number of active interventions is counted within a set time period, and when the number is greater than a set threshold, it is determined that the driver relies on active intervention at this time, and no further determination is made at this time to directly enter the active intervention mode; The number of interrupted voice commands is counted within a set time period. When the number is greater than a set threshold, it is determined that the driver is relying on self-driving at this time. No judgment will be made in the subsequent set time period and the active intervention mode will not be entered.

[0012] In a second aspect, the present invention provides a steering control method for a new energy vehicle.

[0013] A steering control method for a new energy vehicle includes the following steps: Identify objects around the vehicle based on the collected point cloud data to obtain identification results of the surrounding objects, determine the relative distance and relative speed between each object identification result and the vehicle in real time, make abnormality judgment based on the relative distance and relative speed, and execute the steering control judgment step when an abnormality requiring steering control occurs; The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

[0014] As a further limitation of the second aspect of the present invention, the abnormalities that require steering control include: the vehicle in front suddenly decelerates and the speed at which the relative distance decreases is greater than a set threshold, or a pedestrian appears in front and the relative distance is less than the braking distance, or the speed at which the distance between vehicles on both sides decreases is greater than a set value.

[0015] As a further limitation of the second aspect of the present invention, the driver status is abnormal, including: the driver is detected yawning N times in a set time, or the driver's hands are detected off the steering wheel N times in a set time, or the driver is detected checking the mobile phone N times in a set time, or the driver is detected with an anxious expression N times in a set time, where N is greater than or equal to 3.

[0016] As a further limitation of the second aspect of the present invention, the intelligent steering control actively intervenes after an alarm, and also includes: setting a difference time between the alarm and the active intervention, and terminating the active intervention of the steering control according to the driver's interruption voice command during the time period between the alarm and the active intervention.

[0017] As a further limitation of the second aspect of the present invention, the number of active interventions is counted within a set time period, and when the number is greater than a set threshold, it is determined that the driver relies on active intervention at this time, and no further determination is made at this time to directly enter the active intervention mode; The number of interrupted voice commands is counted within a set time period. When the number is greater than a set threshold, it is determined that the driver is relying on self-driving at this time. No judgment will be made in the subsequent set time period and the active intervention mode will not be entered.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention innovatively proposes a steering control system for new energy vehicles. By collecting the force on the steering wheel, the control force of the steering wheel is divided into three levels, and the force is respectively the first level, the second level and the third level from large to small. Combined with the image collection and status analysis of the driver, different steering control strategies are adopted at different levels, which greatly improves the driver's experience while ensuring driving safety.

[0019] 2. The present invention counts the number of active interventions within a set time period. When the number is greater than a set threshold, it is determined that the driver relies on active intervention at this time, and no further judgment is made at this time to directly enter the active intervention mode; the present invention counts the number of interrupted voice commands within a set time period. When the number is greater than a set threshold, it is determined that the driver relies on self-driving at this time, and no further judgment is made within a subsequent set time period and the active intervention mode will not be entered. The mode is actively switched through statistical data during driving, which can adapt to different needs of the driver and further improve the driving experience.

[0020] 3. The present invention sets a time difference between warning and active intervention. In the time period between warning and active intervention, active intervention of steering control is terminated according to the driver's interruption voice command, which can give priority to ensuring the driver's active judgment and manual control, avoid the risks brought by active intervention of steering control, and improve driving safety.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] Figure 1 This is a functional principle block diagram of a new energy vehicle steering control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0025] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0026] Vehicle intelligent steering control refers to the use of sensors and algorithms to achieve automatic control of vehicle steering through an intelligent system installed on the vehicle. This technology can autonomously adjust the steering angle according to the vehicle's driving status and environmental information to maintain the stability and safety of the vehicle during driving. It mainly uses various sensors (such as cameras, radars, lidars, and ultrasonic sensors) to obtain information such as roads, obstacles, and traffic signs around the vehicle in real time, and uses inertial measurement units (IMUs) and vehicle speed sensors to obtain information such as the acceleration, angular velocity, and speed of the vehicle, so as to estimate the vehicle's posture and motion state; based on the results of environmental perception and motion estimation, determine the best path the vehicle should travel; and achieve steering control by controlling the vehicle's steering system (composed of a steering motor and a steering mechanism). Usually, an electronic control unit (ECU) is used to control the output torque and direction of the steering motor.

[0027] However, as described in the background technology, the existing intelligent steering control strategy often conflicts with the driver's self-driving control, resulting in a poor driving experience. In view of this, the present application proposes a new energy vehicle steering control system, such as Figure 1 As shown, it includes: a vehicle-mounted control terminal, a vehicle-mounted laser radar device and a vehicle-mounted image acquisition device, and the vehicle-mounted control terminal is respectively communicated with the vehicle-mounted laser radar device and the vehicle-mounted image acquisition device; The vehicle-mounted laser radar device is used to collect point cloud data around the vehicle in real time and send it to the vehicle-mounted control terminal. The vehicle-mounted image acquisition device collects the image of the driver in the vehicle in real time and sends it to the vehicle-mounted control terminal; The vehicle control terminal is configured to perform the following process: Identify objects around the vehicle based on the collected point cloud data to obtain identification results of the surrounding objects, determine the relative distance and relative speed between each object identification result and the vehicle in real time, make abnormality judgment based on the relative distance and relative speed, and execute the steering control judgment step when an abnormality requiring steering control occurs; The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

[0028] In this implementation, the existing deep learning algorithm model can be used to judge the driver's abnormality; at the same time, in some other implementations, a residual neural network model can also be introduced for behavior recognition. The residual neural network (Residual Network, referred to as ResNet) is a deep neural network architecture. The core idea of ​​this network model is to solve the gradient disappearance and gradient explosion problems in deep neural network training by introducing residual blocks, so that deeper networks can be more easily trained and optimized.

[0029] The residual block is the core component of the ResNet model. It directly connects the input to the output through a shortcut connection, implementing a residual learning method. Each residual block usually consists of two or three convolutional layers, batch normalization, and an activation function (such as ReLU).

[0030] The residual block can be expressed as: Input: x ; Output: H ( x )= F ( x )+ x ,in, F ( x ) represents residual mapping, which is the part of network learning; x It represents identity mapping, that is, directly adding the input to the output. This design makes it easier for the network to learn the identity mapping during training, thereby solving the gradient problem in deep network training.

[0031] The residual neural network model is improved by not using the normalization layer anywhere in the residual block of the residual neural network model. Specifically, The residual block of the form Indicates The input of the residual block is Indicates The function calculated by the residual branch, scalar Specifies the rate of increase of the variance after each residual block, a scalar By predicting the The standard deviation of the residual block input is determined by ,and This not only shortens the gradient calculation time, but also ensures that the deviation value during training is smaller to a greater extent.

[0032] In this implementation, the recognition of objects around the vehicle based on the received point cloud data can be implemented using an existing deep learning network, such as a convolutional neural network. Optionally, in some other implementations, the following methods can also be used: Assume that the scanned point cloud S contains n three-dimensional space points. The steps are as follows: 1) Set the parameter α and the angle threshold β; 2) Select a point P1 from the point set S, and form a subset S1 with all points whose distance to it is less than 2α; 3) Pick any two points P2 and P3 in S1, and find out whether there is a ball that passes through P1, P2, and P3 at the same time and has a radius of α, and satisfies the angle threshold β. If so, record the coordinates of the center of the ball as O; if not, reselect points P2 and P3; 4) Traverse the point set S1 and calculate the distance from the center O to all points in S1 except P1, P2, and P3, recorded as set d. If any distance value in d is greater than the value of radius α, the triangle formed by P1, P2, and P3 is recorded as a boundary triangle; otherwise, the triangle formed by P1, P2, and P3 is considered not a boundary triangle; 5) Select the next set of points in S1 as P2 and P3, and repeat steps 3) and 4) until all possible combinations of P2 and P3 in S1 are traversed; 6) Select the next point in S as P1 and repeat steps 2) to 5) until all points in S are traversed; 7) Traverse all boundary triangles and record the number m of contour triangles formed by each vertex. If the m values ​​of the three vertices of a boundary triangle are all less than 3, delete the boundary triangle; extract the vertices of all boundary triangles to form a point set S2, and the output point set S2 is the contour point cloud of the object to be identified; 8) Perform radius filtering on the obtained contour point cloud of the object to be identified, remove discrete points, and obtain the final contour point cloud of the object to be identified. Match the contour point cloud of the object to be identified with the contour point cloud of the pre-stored typical object to obtain the final type of the object to be identified.

[0033] In this implementation, more specifically, the anomalies that require steering control include: the vehicle ahead suddenly decelerates and the speed at which the relative distance decreases is greater than a set threshold, or a pedestrian appears ahead and the relative distance is less than the braking distance, or the speed at which the distance between vehicles on both sides decreases is greater than a set value.

[0034] In the present implementation, preferably, the driver status is abnormal, including: the driver is detected yawning N times in a set time, or the driver's hands are detected off the steering wheel N times in a set time, or the driver is detected checking the mobile phone N times in a set time, or the driver is detected with an anxious expression N times in a set time, where N is greater than or equal to 3; it is understandable that more abnormal operating conditions can also be set as needed, and the conditions after excluding the abnormal conditions are determined to be normal.

[0035] In the present implementation, preferably, the intelligent steering control actively intervenes after the alarm, and also includes: a set time difference between the alarm and the active intervention (for example, 0.5s), and in the time period between the alarm and the active intervention, according to the driver's interruption voice command, the active intervention of the steering control is terminated, such as giving the command "Xiao*, terminate active steering control"; it should be pointed out that when encountering an abnormal event for which the driver's reaction time cannot be given, the intelligent steering active intervention does not need to give a set time between the alarm and the active intervention, that is, the alarm and active intervention occur at the same time.

[0036] In this implementation, preferably, the number of active interventions is counted within a set time period, and when the number is greater than a set threshold (e.g., three times), it is determined that the driver relies on active intervention at this time, and no further determination is made at this time to directly enter the active intervention mode; The number of interrupted voice commands is counted within a set time period. When the number is greater than a set threshold (for example, three), it is determined that the driver is relying on self-driving at this time. No judgment will be made in the subsequent set time period and the active intervention mode will not be entered.

[0037] In some other implementations, a new energy vehicle steering control method is also proposed, which can be applied to a computer terminal or a computer-readable storage medium, and includes the following process: S1: Identify objects around the vehicle based on the collected point cloud data to obtain the surrounding object identification results, determine the relative distance and relative speed between each object identification result and the vehicle in real time, and make an abnormality judgment based on the relative distance and relative speed. When an abnormality requiring steering control occurs, execute the steering control judgment step; S2: The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

[0038] For the specific process, please refer to the working process of the system in this implementation method, which will not be repeated here.

[0039] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A steering control system for new energy vehicles, It is characterized in that It includes: a vehicle-mounted control terminal, a vehicle-mounted laser radar device and a vehicle-mounted image acquisition device, wherein the vehicle-mounted control terminal is communicatively connected with the vehicle-mounted laser radar device and the vehicle-mounted image acquisition device respectively; The vehicle-mounted laser radar device is used to collect point cloud data around the vehicle in real time and send it to the vehicle-mounted control terminal. The vehicle-mounted image acquisition device collects the image of the driver in the vehicle in real time and sends it to the vehicle-mounted control terminal; The vehicle control terminal is configured to perform the following process: Identify objects around the vehicle based on the collected point cloud data to obtain identification results of the surrounding objects, determine the relative distance and relative speed between each object identification result and the vehicle in real time, make abnormality judgment based on the relative distance and relative speed, and execute the steering control judgment step when an abnormality requiring steering control occurs; The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

2. The new energy vehicle steering control system according to claim 1, characterized in that: Abnormalities that require steering control include: the vehicle ahead suddenly decelerates and the speed at which the relative distance decreases is greater than the set threshold, or a pedestrian appears ahead and the relative distance is less than the braking distance, or the speed at which the distance between the vehicles on both sides decreases is greater than the set value.

3. The new energy vehicle steering control system according to claim 1, characterized in that: The driver status is abnormal, including: the driver is detected yawning N times in a set time, or the driver's hands are detected off the steering wheel N times in a set time, or the driver is detected checking the mobile phone N times in a set time, or the driver has an anxious expression N times in a set time, where N is greater than or equal to 3.

4. The new energy vehicle steering control system according to claim 1, characterized in that: The intelligent steering control actively intervenes after the alarm, and also includes: setting the difference time between the alarm and the active intervention, and terminating the active intervention of the steering control according to the driver's interruption voice command during the time period between the alarm and the active intervention.

5. The new energy vehicle steering control system according to any one of claims 1 to 4, characterized in that: Counting the number of active interventions within a set time period, and when the number is greater than a set threshold, determining that the driver relies on active intervention at this time, and then directly entering the active intervention mode without further determination; The number of interrupted voice commands is counted within a set time period. When the number is greater than a set threshold, it is determined that the driver is relying on self-driving at this time. No judgment will be made in the subsequent set time period and the active intervention mode will not be entered.

6. A steering control method for a new energy vehicle, characterized in that: The process includes: Identify objects around the vehicle based on the collected point cloud data to obtain identification results of the surrounding objects, determine the relative distance and relative speed between each object identification result and the vehicle in real time, make abnormality judgment based on the relative distance and relative speed, and execute the steering control judgment step when an abnormality requiring steering control occurs; The steering control determination step comprises: When the middle position of both sides of the steering wheel is held and the holding force is greater than the set threshold, it is judged that the driver's control of the vehicle steering wheel is normal at this time, and the force is determined to be the first level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control does not intervene. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes or actively intervenes after an alarm; When the middle position of both sides of the steering wheel is held and the holding force is less than the set threshold, it is judged that the driver's control over the vehicle steering wheel is general at this time, and the force is determined to be the second level. When the driver's state obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's state obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes; When the bottom position of the steering wheel is held and the holding force is less than the set threshold, the force is determined to be at the third level. When the driver's status obtained according to the image data at this time is normal, the intelligent steering control actively intervenes after an alarm. When the driver's status obtained according to the image data at this time is abnormal, the intelligent steering control directly intervenes.

7. The steering control method for a new energy vehicle as claimed in claim 6, characterized in that: Abnormalities that require steering control include: the vehicle ahead suddenly decelerates and the speed at which the relative distance decreases is greater than the set threshold, or a pedestrian appears ahead and the relative distance is less than the braking distance, or the speed at which the distance between the vehicles on both sides decreases is greater than the set value.

8. The steering control method for a new energy vehicle as claimed in claim 6, characterized in that: The driver status is abnormal, including: the driver is detected yawning N times in a set time, or the driver's hands are detected off the steering wheel N times in a set time, or the driver is detected checking the mobile phone N times in a set time, or the driver has an anxious expression N times in a set time, where N is greater than or equal to 3.

9. The steering control method for a new energy vehicle as claimed in claim 6, characterized in that: The intelligent steering control actively intervenes after the alarm, and also includes: setting the difference time between the alarm and the active intervention, and terminating the active intervention of the steering control according to the driver's interruption voice command during the time period between the alarm and the active intervention.

10. The steering control method for a new energy vehicle according to any one of claims 6 to 9, characterized in that: Counting the number of active interventions within a set time period, and when the number is greater than a set threshold, determining that the driver relies on active intervention at this time, and then directly entering the active intervention mode without further determination; The number of interrupted voice commands is counted within a set time period. When the number is greater than a set threshold, it is determined that the driver is relying on self-driving at this time. No judgment will be made in the subsequent set time period and the active intervention mode will not be entered.

Images