Complex mountain road sensing method and system for vehicle

Abstract

The invention discloses a complex mountain road sensing method and system for a vehicle. The method comprises the following steps: receiving lane line acquisition information of a complex mountain road in front of the vehicle by a binocular camera and environment acquisition information of the front of the vehicle by a 4D millimeter wave radar; determining the curvature of the lane by combining the lane line acquisition information and the environment acquisition information; judging whether the vehicle needs to steer according to the curvature; if yes, calculating a steering angle; and transmitting the vehicle steering information. According to the invention, the influence of weak light of the mountain road environment on the binocular camera is made up by using the three-dimensional detection result of the 4D millimeter-wave radar on the overall environment of the complex mountain road, so that the position and the bending condition of the lane are accurately identified, and the driving safety of the complex mountain road is improved.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and more specifically, to a complex mountain road perception method and system for a vehicle. Background Art

[0002] Mountain roads are winding and complex, with many obstacles on both sides of the lanes. Falling rocks, rocks protruding from one side of the mountain, road collapses, etc. often occur, and the road conditions in the mountains are dangerous (one side is the mountain, and the other side is the cliff). These cause many inconveniences to drivers when driving vehicles in the mountains and are very prone to danger.

[0003] In order to cope with the driving difficulties on complex mountain roads, the current mainstream method is to install a camera on the car to determine the curvature of the road to assist the driver in driving safely; by adding millimeter-wave radar to detect obstacles or road collapse, etc., to assist the driver in avoiding obstacles.

[0004] Although installing cameras can help drivers identify winding roads to a certain extent, the light on mountain roads will be greatly weakened due to the influence of mountains. Cameras are sensitive to light. In low light conditions, the accuracy of camera target recognition is greatly reduced. Therefore, using cameras to assist drivers in driving on mountain roads is not very effective.

[0005] In addition, since millimeter-wave radar mainly detects moving objects, and fallen rocks on mountain roads and protruding rocks on the mountain are stationary, ordinary millimeter-wave radars may miss detections and make false detections, resulting in the vehicle's failure to respond to braking or false triggering of braking. Summary of the invention

[0006] The present application provides a method and system for sensing complex mountain roads for a vehicle, which utilizes the stereoscopic detection results of the overall environment of complex mountain roads by 4D millimeter-wave radar to compensate for the impact of weak ambient light on the mountain roads on the binocular camera, thereby accurately identifying the position of the lane and its curvature, and improving driving safety on complex mountain roads.

[0007] The present application provides a complex mountain road perception method for a vehicle, comprising:

[0008] Receive lane line information collected by binocular cameras on complex mountain roads ahead of the vehicle and environment information collected by 4D millimeter-wave radar ahead of the vehicle;

[0009] Determine the curvature of the lane by combining lane line information and environment information;

[0010] Determine whether the vehicle needs to turn based on the curvature;

[0011] If so, calculate the steering angle;

[0012] Send vehicle steering information.

[0013] Preferably, the complex mountain road perception method of the vehicle further includes:

[0014] Obtain the outline information of the protruding rocks on both sides of the mountain from the environmental collection information;

[0015] Calculate the sum of the width of the protruding rock protruding from the road surface and the width of the vehicle;

[0016] Determine whether the sum is greater than or equal to the width of the road surface;

[0017] If so, vehicle braking information is issued.

[0018] Preferably, the complex mountain road perception method of the vehicle further includes:

[0019] Acquire the road undulation area in front of the vehicle from the environment collection information;

[0020] Determine whether the highest point of the road undulation area is greater than the chassis height of the vehicle;

[0021] If so, vehicle braking information is issued.

[0022] Preferably, if the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height, vehicle deceleration information is issued.

[0023] Preferably, a pothole road area in front of the vehicle is obtained from the environmental collection information;

[0024] Determining whether the length of the pothole area is less than the length of the vehicle, and the depth of the pothole area is less than the chassis height of the vehicle;

[0025] If not, a vehicle braking message is issued.

[0026] Preferably, while controlling the braking or deceleration of the vehicle, the information collected by the rear corner millimeter wave radar and the rear-view camera of the vehicle on the rear vehicle is received;

[0027] Determine whether there is a risk of collision with the vehicle behind when the vehicle brakes or decelerates;

[0028] If so, the vehicle steering information is issued, and braking information or deceleration information is issued after the collision risk is eliminated.

[0029] The present application also provides a complex mountain road perception system for a vehicle, comprising a receiving module, an information processing module, a steering judgment module and a sending module;

[0030] The receiving module is used to receive lane line information collected by the binocular camera on the complex mountain road in front of the vehicle and environment information collected by the 4D millimeter wave radar in front of the vehicle;

[0031] The information processing module is used to determine the curvature of the lane by combining the lane line collected information and the environment collected information;

[0032] The steering judgment module is used to judge whether the vehicle needs to turn based on the curvature; if turning is required, the steering angle is calculated;

[0033] The sending module is used to send vehicle steering information.

[0034] Preferably, the information processing module is also used to obtain the contour information of the protruding rocks on the mountains on both sides from the environmental collection information, and calculate the sum of the width of the protruding rocks protruding from the road surface and the width of the vehicle;

[0035] The complex mountain road perception system also includes a braking judgment module, which is used to determine that the vehicle needs to brake when the width of the road is greater than or equal to the width of the road.

[0036] Preferably, the complex mountain road perception system of the vehicle also includes a deceleration judgment module, which is used to determine that the vehicle needs to decelerate when the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height.

[0037] Preferably, the information processing module is also used to obtain the pothole road area in front of the vehicle from the environmental collection information;

[0038] The braking judgment module is used to determine that the vehicle needs to brake when the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is less than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is less than the chassis height of the vehicle.

[0039] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0041] Figure 1 A flow chart of a complex mountain road perception method for a vehicle provided in this application;

[0042] Figure 2 This is a structural diagram of the complex mountain road perception system for the vehicle provided in this application. DETAILED DESCRIPTION

[0043] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0044] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] The present application provides a method and system for sensing complex mountain roads for vehicles, which uses the stereoscopic detection results of the overall environment of complex mountain roads by 4D millimeter-wave radar to compensate for the impact of weak ambient light on the mountain road on the binocular camera, thereby accurately identifying the location of the lane and its curvature, and improving driving safety on complex mountain roads. In addition, the present application uses the information collected by the 4D millimeter-wave radar to make corresponding control strategies when there are protruding rocks on both sides of the mountain, and there are undulating areas and potholes on the road surface, reducing the phenomenon of vehicles falsely triggering or not triggering related functions due to missed or false detection, and further improving driving safety.

[0048] It should be noted that in this application, the domain controller processes the information collected by the perception system (including binocular cameras, 4D millimeter-wave radars, rear-angle millimeter-wave radars, and rear-view cameras, etc.) and obtains driving decisions. When driving on complex mountain roads, in emergency situations (for example, the driver's driving intention is inconsistent with the driving decision of the domain controller, there are protruding rocks on the mountain, there are undulating or potholes on the road surface, etc.), the automatic driving system automatically takes over the vehicle for automatic driving and informs the driver through the dashboard. Based on this idea, in this application, in an emergency, the automatic driving system will issue corresponding instructions to the chassis through the body controller based on the driving decision to realize the automatic driving of the vehicle.

[0049] like Figure 1 As shown, the complex mountain road perception method for a vehicle provided by the present application is applicable to a domain controller, including:

[0050] S110: receiving lane line information of the complex mountain road ahead of the vehicle collected by the binocular camera and environment information ahead of the vehicle collected by the 4D millimeter wave radar.

[0051] 4D millimeter-wave radar can not only identify the distance, relative speed, and direction information between the target and the launch point, but also has three-dimensional detection capabilities and edge contour recognition capabilities to filter out false alarms, reduce noise, and provide more accurate information about the target object.

[0052] S120: Determine the curvature of the lane by combining the lane line collected information and the environment collected information.

[0053] S130: Determine whether the vehicle needs to turn based on the curvature. If yes, execute S140; otherwise, execute S1170.

[0054] S140: Calculate the steering angle.

[0055] S150: Sending vehicle steering information to the automatic driving system.

[0056] Preferably, while executing S120, the following steps are also executed:

[0057] S160: Obtaining contour information of protruding rocks on both sides of the mountain from the environmental collection information.

[0058] S170: Calculate the sum of the width of the protruding rock protruding from the road surface and the width of the vehicle.

[0059] S180: Determine whether the sum is greater than or equal to the width of the road surface. If so, determine that the vehicle needs to brake and execute S190; otherwise, execute S1100.

[0060] S190: Send vehicle braking information to the automatic driving system.

[0061] S1100: Determine whether there is a risk of collision with a protruding rock when the vehicle is traveling along the current local path. If yes, execute S140-S150; otherwise, execute S1170.

[0062] In this case, in S140, the steering angle θ=arctanX / Y (where X is the distance between the vehicle body on the side close to the protruding rock and the protruding rock, and Y is the distance between the front end of the vehicle and the protruding rock).

[0063] Preferably, while executing S120, the following steps are also executed:

[0064] S1110: Acquire the road undulation area in front of the vehicle from the environment collection information.

[0065] S1120: Determine whether the highest point of the road undulation area is greater than the chassis height of the vehicle. If so, determine that the vehicle needs to brake and execute S190; otherwise, execute S1130.

[0066] S1130: Determine whether the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height. If so, determine that the vehicle body needs to be decelerated and execute S1140; otherwise, execute S1170.

[0067] S1140: Send vehicle deceleration information to the automatic driving system.

[0068] Preferably, while executing S120, the following steps are also executed:

[0069] S1150: Acquire a pothole road area in front of the vehicle from the environment collection information.

[0070] S1160: Determine whether the length of the pothole area is less than the length of the vehicle, and the depth of the pothole area is less than the chassis height of the vehicle. If so, execute S1170; otherwise, that is, the length of the pothole area is greater than the length of the vehicle, and the depth of the pothole area is greater than the chassis height of the vehicle, or the length of the pothole area is less than the length of the vehicle, and the depth of the pothole area is greater than the chassis height of the vehicle, or the length of the pothole area is greater than the length of the vehicle, and the depth of the pothole area is less than the chassis height of the vehicle, then it is determined that the vehicle needs to brake, and execute S190.

[0071] S1170: Send normal driving information to the automatic driving system.

[0072] Preferably, the automatic driving system also reminds the following vehicles through the taillights and the driver through the instrument panel while controlling the driving of the vehicle.

[0073] Specifically, while the autonomous driving system controls the vehicle to brake, it also controls the vehicle's taillights to flash at a first frequency to remind the vehicle behind that the vehicle needs to brake, and reminds the driver through the dashboard (with text and / or voice prompts) that the braking function is being performed. While the autonomous driving system controls the vehicle to decelerate, it controls the vehicle's taillights to flash at a second frequency to remind the vehicle behind that the vehicle needs to decelerate, and reminds the driver through the dashboard that the deceleration function is being performed. The second frequency is lower than the first frequency. While the autonomous driving system controls the vehicle to turn, it reminds the vehicle behind by turning on the turn signal.

[0074] Preferably, the automatic driving system, while controlling the driving of its own vehicle, also determines the driving conditions of the vehicle behind through the perception system at the rear of the vehicle and takes corresponding collision avoidance measures.

[0075] Specifically, while the autonomous driving system controls the vehicle to brake or decelerate, it receives information collected by the vehicle's rear-corner millimeter-wave radar and rear-view camera about the rear vehicle, and determines the speed of the rear vehicle and the distance between the rear vehicle and the vehicle, and determines whether there is a risk of collision with the rear vehicle when the vehicle brakes or decelerates. If so, the domain controller sends the vehicle steering information to the autonomous driving system, and sends braking information or deceleration information to the autonomous driving system after the collision risk is eliminated. While the autonomous driving system controls the vehicle to turn, it receives information collected by the vehicle's rear-corner millimeter-wave radar and rear-view camera about the rear vehicle, and determines whether there is a risk of collision with the rear vehicle when the vehicle turns. If so, the domain controller sends the vehicle braking information to the autonomous driving system, and sends steering information to the autonomous driving system after the collision risk is eliminated.

[0076] Based on the above, the present application also provides a complex mountain road perception system for a vehicle. Figure 2 As shown, the complex mountain road perception system includes a receiving module 210 , an information processing module 220 , a steering judgment module 230 and a sending module 240 .

[0077] The receiving module 210 is used to receive lane line information collected by the binocular camera on the complex mountain road in front of the vehicle and environment information collected by the 4D millimeter wave radar in front of the vehicle.

[0078] The information processing module 220 is used to determine the curvature of the lane by combining the lane line collected information and the environment collected information.

[0079] The steering determination module 230 is used to determine whether the vehicle needs to turn according to the curvature, and if turning is required, calculate the steering angle.

[0080] The sending module 240 is used to control the vehicle to turn.

[0081] Preferably, the information processing module 220 is also used to obtain the contour information of the protruding rocks on the mountains on both sides from the environmental collection information, and calculate the sum of the width of the protruding rocks protruding from the road surface and the width of the vehicle.

[0082] The complex mountain road perception system further includes a braking judgment module 250, which is used to determine that the vehicle needs to brake when the sum is greater than or equal to the width of the road surface.

[0083] Preferably, the turning judgment module 230 is further used for determining that the vehicle needs to turn when the vehicle is at risk of colliding with a protruding rock when traveling along the current local path and when the vehicle is less than the width of the road surface.

[0084] Preferably, the information processing module 220 is further used to obtain the road undulation area in front of the vehicle from the environmental collection information.

[0085] The braking determination module 250 is further configured to determine that the vehicle needs braking when the highest point of the road undulation area is greater than the chassis height of the vehicle.

[0086] Preferably, the complex mountain road perception system of the vehicle also includes a deceleration judgment module 260, which is used to determine that the vehicle needs to decelerate when the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height.

[0087] Preferably, the information processing module 220 is used to obtain the pothole road area in front of the vehicle from the environmental collection information.

[0088] The braking judgment module 250 is used to determine that the vehicle needs to brake when the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is less than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is less than the chassis height of the vehicle.

[0089] Preferably, the sending module 240 is also used to control the vehicle's taillights to flash at a first frequency while controlling the vehicle's braking, and to remind the driver through the instrument panel that the braking function is being performed; while controlling the vehicle's deceleration, the sending module 240 is also used to control the vehicle's taillights to flash at a second frequency, and to remind the driver through the instrument panel that the deceleration function is being performed.

[0090] Preferably, the receiving module 210 is also used to receive information collected by the vehicle's rear corner millimeter wave radar and rear-view camera on the rear vehicle.

[0091] The complex mountain road perception system also includes a collision judgment module 270, which is used to judge whether there is a risk of collision with the following vehicle when the vehicle is turning, braking or decelerating.

[0092] The sending module 240 is also used to take collision avoidance measures when there is a collision risk, and perform steering, braking or deceleration after the collision risk is eliminated.

[0093] The present application reduces the probability of a binocular camera failing to identify lane lines or misidentifying lane lines due to insufficient light, thereby effectively assisting the driver in driving on winding roads; and the present application increases the recognition of obstacles, road undulations, and collapsed areas on mountain roads, thereby preventing false triggering, effectively helping the driver to judge the above factors, and assisting the driver in driving safely.

[0094] Although some specific embodiments of the present application have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present application. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. A complex mountain road perception method for a vehicle, characterized in that: include: Receive lane line information collected by binocular cameras on complex mountain roads ahead of the vehicle and environment information collected by 4D millimeter-wave radar ahead of the vehicle; Determine the curvature of the lane by combining the lane line collected information and the environment collected information; determining whether the vehicle needs to turn according to the curvature; If so, calculate the steering angle; Send vehicle steering information.

2. The complex mountain road perception method for a vehicle according to claim 1, characterized in that: Also includes: Acquire the outline information of the protruding rocks on the mountains on both sides from the environmental collection information; Calculate the sum of the width of the protruding rock protruding from the road surface and the width of the vehicle; Determining whether the sum is greater than or equal to the width of the road surface; If so, vehicle braking information is issued.

3. The complex mountain road perception method for a vehicle according to claim 1, characterized in that: Also includes: Acquire the road surface undulation area in front of the vehicle from the environment collection information; Determining whether the highest point of the road undulation area is greater than the chassis height of the vehicle; If so, vehicle braking information is issued.

4. The complex mountain road perception method for a vehicle according to claim 3, characterized in that: If the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height, vehicle deceleration information is issued.

5. The complex mountain road perception method for a vehicle according to claim 1, characterized in that: Acquire a pothole road area in front of the vehicle from the environmental collection information; Determining whether the length of the pothole road area is less than the length of the vehicle, and the depth of the pothole road area is less than the chassis height of the vehicle; If not, a vehicle braking message is issued.

6. The complex mountain road perception method for a vehicle according to any one of claims 2 to 5, characterized in that: While controlling the vehicle's braking or deceleration, it receives information collected by the vehicle's rear corner millimeter wave radar and rear-view camera about the vehicle behind; Determine whether there is a risk of collision with the vehicle behind when the vehicle brakes or decelerates; If so, the vehicle steering information is issued, and braking information or deceleration information is issued after the collision risk is eliminated.

7. A complex mountain road perception system for a vehicle, characterized in that: It includes a receiving module, an information processing module, a steering judgment module and a sending module; The receiving module is used to receive lane line information collected by the binocular camera on the complex mountain road in front of the vehicle and environment information collected by the 4D millimeter wave radar in front of the vehicle; The information processing module is used to determine the curvature of the lane by combining the lane line collected information and the environment collected information; The steering judgment module is used to judge whether the vehicle needs to turn according to the curvature; If steering is required, calculate the steering angle; The sending module is used to send vehicle steering information.

8. The complex mountain road perception system for a vehicle according to claim 7, characterized in that: The information processing module is also used to obtain the contour information of the protruding rocks on the mountains on both sides from the environmental collection information, and calculate the sum of the width of the protruding rocks protruding from the road surface and the width of the vehicle; The complex mountain road perception system also includes a braking judgment module, which is used to determine that the vehicle needs to brake when the sum is greater than or equal to the width of the road surface.

9. The complex mountain road perception system for a vehicle according to claim 8, characterized in that: It also includes a deceleration judgment module, which is used to determine that the vehicle needs to decelerate when the highest point of the road undulation area is greater than half of the chassis height of the vehicle and less than the chassis height.

10. The complex mountain road perception system for a vehicle according to claim 8, characterized in that: The information processing module is also used to obtain a pothole road area in front of the vehicle from the environmental collection information; The braking judgment module is used to determine that the vehicle needs to brake when the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is less than the length of the vehicle and the depth of the pothole road area is greater than the chassis height of the vehicle, or the length of the pothole road area is greater than the length of the vehicle and the depth of the pothole road area is less than the chassis height of the vehicle.

Images