Vehicle lane changing auxiliary early warning method and system based on millimeter wave radar

Abstract

The invention relates to a vehicle lane changing auxiliary early warning method and system based on a millimeter wave radar, and relates to the field of intelligent driving. The method comprises the following steps: receiving point cloud information sent by a millimeter wave radar; based on the point cloud information and the position data of the to-be-detected area, determining whether an object exists in the to-be-detected area; determining predicted collision time data corresponding to the object; a warning signal is generated based on the projected collision time data. Derivation is carried out based on the basic principle of a radar equation, a corresponding warning signal is made in combination with predicted collision time data under the condition of a preset position, and high reliability and strong anti-interference capability are achieved. When a driver carries out conscious or unconscious lane changing or merging operation, if a moving vehicle is detected in a blind spot area of the driver, the system gives an alarm to prompt a collision risk, and the probability of close-range collision is greatly reduced. Therefore, traffic accidents and dangerous lane cutting-out caused by blind areas can be avoided.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and in particular to a vehicle lane change auxiliary warning method and system based on millimeter wave radar. Background Art

[0002] As a focus of intelligent driving perception technology research, the vehicle lane change assist warning system generally perceives the surrounding environment through millimeter wave radar, ultrasonic wave, laser radar and vehicle-mounted cameras, and monitors the traffic conditions around the vehicle in real time, especially in blind spots. When the system detects potential danger, it will promptly warn the driver to help the driver avoid possible collisions. When driving in rainy, foggy or nighttime weather, the field of view of the rearview mirror is often limited, and the role of the lane change assist warning system is even more important. It can provide additional safety protection and reduce the risk of drivers changing lanes in bad weather or lighting conditions.

[0003] Lane change assist system is a driving assistance technology that aims to improve driving safety. When a vehicle is changing lanes, if a vehicle behind approaches and enters the blind spot, the system will determine whether the vehicle is at risk of collision and alert the driver through the indicator light on the rearview mirror or the vibration of the steering wheel. In addition, some advanced lane change assist systems also have interactive functions that can automatically select the best time and direction for the driver to change lanes based on road conditions and environmental information. This function not only helps to reduce driving time, but also helps save fuel and improve the overall driving experience. In related technologies, this technology is completed by the cooperation of on-board MCU and traditional sensors.

[0004] However, traditional sensors have difficulties in detecting targets, which reduces the efficiency of lane change assistance warning. Summary of the invention

[0005] This application is about a vehicle lane change auxiliary warning method and system based on millimeter wave radar, which can improve the efficiency and accuracy of lane change auxiliary warning. The technical solution is as follows: On the one hand, a vehicle lane change auxiliary warning method based on millimeter wave radar is provided, and the method is applied to a computer device in a vehicle lane change auxiliary warning system based on millimeter wave radar. The method includes: Receive point cloud information sent by millimeter-wave radar; Based on the point cloud information and the location data of the area to be detected, determine whether there is an object in the area to be detected; In response to the presence of an object in the area to be detected, determining estimated time-to-collision data corresponding to the object; A warning signal is generated based on the estimated collision time data, and the warning information is used to indicate the existence status of objects in the target blind spot area.

[0006] In an optional embodiment, receiving point cloud information sent by a millimeter wave radar includes: Preset the working cycle for receiving point cloud information; Receive point cloud information based on a work cycle.

[0007] In an optional embodiment, determining whether there is an object in the area to be detected based on the point cloud information and the position data of the area to be detected includes: Generate position data of the area to be detected based on boundary information of the area to be detected; Combine point cloud information and location data of the area to be detected to detect the existence of objects in the area to be detected; In response to the detection being passed, it is determined that there is an object in the area to be detected.

[0008] In an optional embodiment, after the position data of the area to be detected is generated based on the boundary information of the area to be detected, the method includes: determining speed information, the speed information indicating a travel speed of the vehicle; Update the boundary information of the area to be detected based on the driving speed; The position data of the area to be detected is updated based on the updated boundary information of the area to be detected.

[0009] In an optional embodiment, combining point cloud information and position data of the area to be detected to detect the existence of an object in the area to be detected includes: Perform object fitting based on point cloud information to obtain object position data and object size data; Performing object position detection based on object position data; In response to the position detection being passed, performing object presence detection based on the object size data; In response to the object size data indicating that the object size is greater than an object size threshold, a presence detection pass result is generated.

[0010] In an optional embodiment, the method further comprises: generating a presence detection fail result in response to the object size data indicating that the object size is less than an object size threshold; Discard point cloud information based on existence detection failure results.

[0011] In an optional embodiment, the object position data includes the object's current position data and the object's motion trajectory data.

[0012] In an optional embodiment, in response to the presence of an object in the area to be detected, determining the estimated collision time data corresponding to the object includes: In response to the presence of an object in the area to be detected, determining an intersection-over-union ratio between the object and the area to be detected; Based on the intersection-over-union ratio, estimated collision time data corresponding to the object is determined in combination with the object position data of the target object.

[0013] In an optional embodiment, generating a warning signal based on the estimated collision time data includes: In response to the estimated collision time data being less than a collision time threshold, sending a level one warning signal; In response to the issuance of the first level warning, receiving turn signal status data; In response to the turn signal status data indicating that the turn signal is in an on state, sending a secondary warning signal.

[0014] On the other hand, a vehicle lane change auxiliary warning system based on millimeter wave radar is provided, the system includes a millimeter wave radar and a computer device; Millimeter wave radar and computer equipment communication connection; The millimeter wave radar is used to generate point cloud information and send the point cloud information to a computer device; The computer device is used to execute any of the above vehicle lane change assistance warning methods based on millimeter wave radar.

[0015] The technical effects of each embodiment of the present application include at least: Based on the basic principle of radar equation, the system makes corresponding warning signals in combination with the estimated collision time data at the preset position, which has high reliability and strong anti-interference ability. When the driver consciously or unconsciously changes lanes or merges lanes, if a moving vehicle is detected in the driver's blind spot, the system will provide an alarm to indicate the risk of collision, greatly reducing the probability of close-range collision. This helps to avoid traffic accidents and dangerous lane cuts caused by blind spots. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A schematic structural diagram of a vehicle lane change auxiliary warning system based on millimeter wave radar provided by an exemplary embodiment of the present application is shown.

[0018] Figure 2 A schematic diagram of the division of functional blind spot warning areas in the field of intelligent driving is shown.

[0019] Figure 3A flow chart of a vehicle lane change auxiliary warning method based on millimeter-wave radar provided by an exemplary embodiment of the present application is shown.

[0020] Figure 4 A flow chart of another vehicle lane change auxiliary warning method based on millimeter wave radar provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0022] Figure 1 A schematic diagram of a vehicle lane change assistance warning system based on millimeter wave radar is shown in an exemplary embodiment of the present application. Figure 1 The system includes a millimeter wave radar 110 and a computer device 120. The millimeter wave radar 110 and the computer device 120 are communicatively connected.

[0023] In the embodiment of the present application, the millimeter wave radar is a radar product attached to the vehicle, and the detection range of the millimeter wave radar is the measured side. In the vehicle lane change scene, there are usually blind spots on both sides of the rear of the vehicle, and the detection position of the millimeter wave radar includes at least the above positions. The millimeter wave radar is used to generate point cloud information and send it to the computer device so that the computer device can generate corresponding processing results and further generate visualization results.

[0024] For an example, see Figure 2 , based on the lane change area (LCA) function blind spot warning area specified in ISO-17387, the dimensions are as follows: a) Line A 210 is parallel to the rear edge of the vehicle 200 and is 30.0 m away from the rear edge; b) Line B 220 is parallel to the rear edge of the vehicle 200 and is 3.0 m away from the rear edge; c) Line C 230 is parallel to the leading edge of the ego vehicle 200 and is located at the center of the driver's eyellipse at the 95th percentile; d) D line 240 is an extension line of the front edge of the vehicle 200; e) The E line 250 is parallel to the center line of the vehicle 200 and is tangent to the outermost edge of the left side of the vehicle 200, and the outermost edge on the left side does not include the exterior rearview mirror; f) F line 260 is on the left side of the vehicle 200, parallel to the center line of the vehicle 200 and 0.5 m away from the outermost edge of the left side of the vehicle 200; g) G line 270 is on the left side of the vehicle 200, parallel to the center line of the vehicle 200 and 3.0 m away from the outermost edge of the left side of the vehicle 200; h) H line 280 is on the left side of the vehicle 200, parallel to the center line of the vehicle 200 and 6.0 m away from the outermost edge of the left side of the vehicle 200; i) The J line 290 is parallel to the center line of the vehicle 200 and is tangent to the outermost edge of the right side of the vehicle 200, where the outermost edge does not include the exterior rearview mirror; j) K line 2100 is on the right side of the vehicle 200, parallel to the center line of the vehicle 200 and 0.5 m away from the outermost edge of the right side of the vehicle 200; k) L line 2110 is on the right side of the vehicle 200, parallel to the center line of the vehicle 200 and 3.0 m away from the outermost edge of the right side of the vehicle 200; l) M line 2120 is on the right side of the vehicle 200, parallel to the center line of the vehicle 200 and 6.0 m away from the outermost edge of the right side of the vehicle 200; m) N line 2130 is the extension line of the rear edge of the vehicle 200; n) The O line 2140 is parallel to the rear edge of the vehicle 200 and is 10.0 m away from the rear edge.

[0025] Corresponding to the above rules, the computer device executes the corresponding vehicle lane change assistance warning.

[0026] Figure 3 A flow chart of a vehicle lane change auxiliary warning method based on millimeter wave radar provided by an exemplary embodiment of the present application is shown, and the method is applied to Figure 1 Taking the computer device in the vehicle lane change auxiliary warning based on millimeter wave radar as an example, the method includes: Step 301, receiving point cloud information sent by millimeter wave radar.

[0027] This process is the process in which the computer device receives the point cloud information through the millimeter wave radar and enters a state to be processed. Optionally, the point cloud information is received periodically.

[0028] Step 302: Determine whether there is an object in the area to be detected based on the point cloud information and the position data of the area to be detected.

[0029] In the embodiment of the present application, the point cloud information and the computer device are combined according to the following Figure 2 The rules shown are preset to obtain the position data of the area to be detected to determine whether there is an object in the area to be detected. Optionally, the area to be detected is the blind spot of the vehicle.

[0030] Step 303: In response to the existence of an object in the area to be detected, estimated collision time data corresponding to the object is determined.

[0031] In the embodiment of the present application, if there is an object in the area to be detected, the estimated time to collision (Time To Collision, TTC) is calculated to obtain estimated time to collision data.

[0032] In step 304 , a warning signal is generated based on the estimated collision time data.

[0033] In the embodiment of the present application, the warning information is used to indicate the existence status of the object in the target blind area, that is, the warning information is used to indicate whether there is a collision risk.

[0034] In summary, the method provided in the embodiment of the present application is derived based on the basic principle of the radar equation. In the case of a preset position, a corresponding warning signal is made in combination with the estimated collision time data, and it has high reliability and strong anti-interference ability. When the driver consciously or unconsciously changes lanes or merges lanes, if a moving vehicle is detected in the driver's blind spot area, the system will provide an alarm to indicate the risk of collision, greatly reducing the probability of close-range collision. This helps to avoid traffic accidents and dangerous lane cuts caused by blind spots.

[0035] Figure 4 A schematic diagram of another vehicle lane change auxiliary warning method based on millimeter wave radar provided by an exemplary embodiment of the present application is shown, and the method is applied to Figure 1 Taking a computer device in the system shown in FIG. 1 as an example, the method includes: Step 401, presetting a working cycle for receiving point cloud information.

[0036] Step 402, receiving point cloud information based on a working cycle.

[0037] In the embodiment of the present application, the point cloud information is information acquired by the millimeter wave radar according to the acquisition cycle. Based on this information, the millimeter wave radar works and sends the information to a computer device for subsequent processing.

[0038] Step 403: Generate position data of the area to be detected based on the boundary information of the area to be detected.

[0039] In the embodiment of the present application, the position data of the area to be detected is Figure 2 Corresponding LCA function blind spot alarm area. It should be noted that in the embodiment of the present application, the conditions that the early warning function needs to meet are as follows: 1) The target vehicle is completely located behind Line B; 2) The target vehicle is completely to the left of the F-line; 3) Any part of the target vehicle crosses the G line to the right; 4) The relative collision time between the target vehicle and the ego vehicle is less than or equal to TTC; 5) The target is within 70m from the rear of the vehicle.

[0040] The conditions required for the right zone approaching vehicle warning are as follows: 6) The target vehicle is completely located behind Line B; 7) The target vehicle is completely on the right side of the K line; 8) Any part of the target vehicle crosses the L line to the left; 9) The relative collision time between the target vehicle and the ego vehicle is less than or equal to TTC; 10) The target is within 70m from the rear of the vehicle.

[0041] Combined with the vehicle coordinate system and Figure 2 For explanation, take the center of the rear axle of the vehicle as the origin, the longitudinal direction forward is the positive of the X axis, the horizontal direction to the left is the positive of the Y axis, and the vertical direction upward is the positive of the Z axis. According to the vehicle coordinate system, the left and right blind area boundaries are calculated. The B line, A line, G line, and F line constitute the left blind area of ​​LCA leftLcaRoi, and the B line, A line, K line, and L line constitute the left blind area of ​​LCA rightLcaRoi.

[0042] Optionally, the computer device can update the boundary of the area to be detected in combination with the current driving speed of the vehicle. This process is also a process of determining speed information; updating the boundary information of the area to be detected based on the driving speed; and updating the position data of the area to be detected based on the updated boundary information of the area to be detected. The speed information indicates the driving speed of the vehicle.

[0043] That is, in one example, the actual location is: LCA area Line B position: LineB = -3 - DISTANCEREAR; Dynamic adjustment of the position of line B in the LCA area: ExpendLineB is updated according to the actual speed of the current vehicle, and the blind spot dynamic expansion coefficient EXPENDRATIO is 0.05 m / s; LCA area Line A position: LineA = -30 - DISTANCEREAR; LCA area F, K-line position: LineF = 0.5 + EGOCARWIDTH / 2; LineK = -0.5 - EGOCARWIDTH / 2; Position of lines G and L in LCA area: LineG = 3 + EGOCARWIDTH / 2; LineL = -3 - EGOCARWIDTH / 2; In the above formula, DISTANCEREAR indicates the distance from the rear axle to the rear edge, and EGOCARWIDTH indicates the vehicle width.

[0044] Step 404: perform object fitting based on the point cloud information to obtain object position data and object size data.

[0045] Optionally, the position of the object is determined by calculating the vertex coordinates of the object in the vehicle coordinate system, and the size of the object is determined by calculating the width and length of the object in the vehicle coordinate system.

[0046] In an example, the positions posX_w and posY_w of the target in the vehicle coordinate system are obtained according to the post-processing point cloud information, and objWidth and objLength represent the width and length of the target respectively.

[0047] Step 405: perform object position detection based on the object position data.

[0048] This process is the process of matching the position coincidence between the object and the vehicle's detection area.

[0049] Step 406 , in response to the position detection being successful, performing object existence detection based on the object size data.

[0050] Step 407 : In response to the object size data indicating that the object size is greater than the object size threshold, generating a presence detection pass result.

[0051] It should be noted that if the width or length of the target is less than or equal to zero, it is set to 1 to prevent errors in subsequent calculations. That is, in response to the object size data indicating that the object size is less than the object size threshold, a presence detection failure result is generated; and the point cloud information is discarded based on the presence detection failure result.

[0052] Step 408 : In response to the existence of an object in the area to be detected, determining an intersection-over-union ratio between the object and the area to be detected.

[0053] In one example, an intersection-and-union ratio between the polygon of the target and the left blind area and / or the right blind area is determined by an intersection-and-union ratio function.

[0054] Step 409 : determining the estimated collision time data corresponding to the object based on the intersection-over-union ratio and in combination with the object position data of the target object.

[0055] Optionally, if the intersection-and-joint ratio is greater than 0 and the front end of the target enters the B line position, the TTC data is calculated.

[0056] Step 410 : In response to the estimated collision time data being less than the collision time threshold, sending a level one warning signal.

[0057] When TTC is less than the collision time threshold, it indicates that there is a high risk of collision. At this time, the computer device sends a level one warning signal, which can be used to convert into a highly recognizable risk warning, or combined with the vehicle's central control to generate control signals for other vehicle components.

[0058] Step 411, in response to the issuance of the first level warning, receiving turn signal status data.

[0059] Optionally, when the TTC is less than the collision time threshold, the computer device will further determine the driver's driving tendency.

[0060] Step 412, in response to the turn signal status data indicating that the turn signal is in an on state, sending a secondary warning signal.

[0061] When the turn signal is turned on, it means that the driver has a tendency to change lanes. At this time, there is a risk of the vehicle and objects getting close. Therefore, at this time, a low-recognition secondary warning signal is sent to alert the driver of the lane change behavior.

[0062] It should be noted that, in addition to the situation where the first-level warning signal is issued, in the embodiment of the present application, when other situations are involved, the computer device will output a safety indication signal to indicate that the current vehicle does not have the risk of lane change collision.

[0063] In summary, the method provided in the embodiment of the present application is derived based on the basic principle of the radar equation. In the case of a preset position, a corresponding warning signal is made in combination with the estimated collision time data, and it has high reliability and strong anti-interference ability. When the driver consciously or unconsciously changes lanes or merges lanes, if a moving vehicle is detected in the driver's blind spot area, the system will provide an alarm to indicate the risk of collision, greatly reducing the probability of close-range collision. This helps to avoid traffic accidents and dangerous lane cuts caused by blind spots.

[0064] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A vehicle lane change auxiliary warning method based on millimeter wave radar, characterized in that: The method is applied to a computer device in a vehicle lane change auxiliary warning system based on a millimeter wave radar, the vehicle lane change auxiliary warning system based on a millimeter wave radar comprises a computer device and a millimeter wave radar, the computer device is communicatively connected with the millimeter wave radar, and the method comprises: Receive point cloud information sent by millimeter-wave radar; Based on the point cloud information and the position data of the area to be detected, determining whether there is an object in the area to be detected; In response to the presence of an object in the area to be detected, determining estimated time-to-collision data corresponding to the object; A warning signal is generated based on the estimated collision time data, and the warning information is used to prompt the existence status of the object in the target blind spot area.

2. The method according to claim 1, characterized in that The receiving of point cloud information sent by the millimeter wave radar includes: Preset the working cycle for receiving point cloud information; The point cloud information is received based on the duty cycle.

3. The method according to claim 1, characterized in that The determining whether there is an object in the area to be detected based on the point cloud information and the position data of the area to be detected includes: Generate position data of the area to be detected based on boundary information of the area to be detected; Performing existence detection of objects in the area to be detected by combining the point cloud information and the position data of the area to be detected; In response to the detection being passed, it is determined that there is an object in the area to be detected.

4. The method according to claim 3, characterized in that After the position data of the area to be detected is generated based on the boundary information of the area to be detected, the method includes: determining speed information, the speed information indicating a travel speed of the vehicle; Updating the boundary information of the area to be detected based on the driving speed; The position data of the area to be detected is updated based on the updated boundary information of the area to be detected.

5. The method according to claim 3, characterized in that: The combining the point cloud information and the position data of the area to be detected to detect the existence of an object in the area to be detected includes: Perform object fitting based on the point cloud information to obtain object position data and object size data; Performing object position detection based on the object position data; In response to the position detection being passed, performing object existence detection based on the object size data; In response to the object size data indicating that the object size is greater than an object size threshold, a presence detection pass result is generated.

6. The method according to claim 5, characterized in that The method further comprises: In response to the object size data indicating that the object size is less than an object size threshold, generating a presence detection fail result; The point cloud information is discarded based on the existence detection failure result.

7. The method according to claim 5, characterized in that The object position data includes the object's current position data and the object's motion trajectory data.

8. The method according to claim 5, characterized in that: In response to the existence of an object in the area to be detected, determining estimated collision time data corresponding to the object includes: In response to the existence of an object in the area to be detected, determining an intersection-over-union ratio between the object and the area to be detected; Based on the intersection-over-union ratio, estimated collision time data corresponding to the object is determined in combination with the object position data of the target object.

9. The method according to claim 8, characterized in that The generating a warning signal based on the estimated collision time data comprises: In response to the estimated collision time data being less than a collision time threshold, sending a level one warning signal; In response to the issuance of the first level warning, receiving turn signal status data; In response to the turn signal lamp status data indicating that the turn signal lamp is in an on state, sending a secondary warning signal.

10. A vehicle lane change auxiliary warning system based on millimeter wave radar, characterized in that: The system includes a millimeter wave radar and a computer device; The millimeter wave radar and the computer device are communicatively connected; The millimeter wave radar is used to generate point cloud information and send the point cloud information to the computer device; The computer device is used to execute the vehicle lane change auxiliary warning method based on millimeter wave radar as described in any one of claims 1-9.

Images