Sanitation vehicle control method and device based on AEBS fusion

Abstract

The invention discloses a sanitation vehicle control method and device based on AEBS fusion, and the method comprises the steps: when a working vehicle works on a road surface where pedestrians or non-motor vehicles run in parallel (water sprinkling), a detection device configured by an AEB system intelligently monitors the moving trend of obstacles (including pedestrians, non-motor vehicles and the like) on the road surface, and system perception and a whole vehicle operation control system are fused, so that the vehicle operation control is realized. And the sprinkling range and the water quantity are automatically controlled, so that sewage is prevented from being splashed on pedestrians or non-motor vehicles, and complaints and unnecessary civil disputes are reduced. The environmental sanitation vehicle control method based on AEBS fusion comprises the steps that area calibration is conducted on the front portion of a vehicle body through a binocular camera, step division is conducted on the calibrated area, and a first division result is obtained; performing area calibration on the two sides of the vehicle body through radar detection, and performing step division on the calibrated areas to obtain a second division result; and detecting the calibrated area based on the first division result and the second division result, and performing work control on a sanitation vehicle control system according to a detection result.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and particularly to a control method and device for a sanitation vehicle based on AEBS fusion. Background Art

[0002] With the development of computer vision technology, through following the vehicle to observe the operation of the sprinkler truck on-site, it is found that the current high-pressure water cannon equipped in front of the sprinkler truck mainly controls the water output and the range adjustment in all directions through a high-definition control panel and a water pump controller, and the equipment is controlled by a solid-line connection method.

[0003] At present, the real-time control scheme of the high-pressure water cannon is still not used ideally, and the main reasons are as follows: when the driver's attention is not concentrated, the movement trajectories of pedestrians and vehicles cannot be captured in advance, and the current water output and direction may cause sewage to splash on pedestrians, resulting in civil disputes; at present, the water control method of the water cannon is relatively clumsy, the left and right turning distances are fixed, and there is a delay time between the input command of the control panel and the execution command of the water cannon.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The main purpose of the present invention is to disclose a control method and device for a sanitation vehicle based on AEBS fusion, which is used to solve the problems in the prior art that when the driver's attention is not concentrated, the movement trajectories of pedestrians and vehicles cannot be captured in advance, and the current water output and direction may cause sewage to splash on pedestrians, resulting in civil disputes; at present, the water control method of the water cannon is relatively clumsy, the left and right turning distances are fixed, and there is a delay time between the input command of the control panel and the execution command of the water cannon.

[0006] To achieve the above object, according to one aspect of the present invention, a control method for a sanitation vehicle based on AEBS fusion is provided, and the following technical solutions are adopted: Perform area calibration on the front of the vehicle body through a binocular camera, and perform stepped division on the calibrated area to obtain a first division result; perform area calibration on both sides of the vehicle body through radar detection, and perform stepped division on the calibrated area to obtain a second division result; based on the first division result and the second division result, detect the calibrated area, and according to the detection result, control the operation of the sanitation vehicle control system.

[0007] Further, both the first division result and the second division result are: dividing the calibrated area into a warning area and a necessary interception area according to the range. The detection of the calibrated area based on the first division result and the second division result, and the work control of the sanitation vehicle control system according to the detection result include: detecting obstacles in front, judging whether the obstacles in front are in the necessary interception area according to the detection result, if so, taking a three-level sound and light warning, and at the same time intercepting the water output for 5 seconds, and performing re-detection after 3 seconds of interception. According to the detection result, determine whether to continue intercepting the water output. If so, continue to intercept the next 5-second water output. If not, restore the range.

[0008] Further, the detection of the calibrated area based on the first division result and the second division result, and the work control of the sanitation vehicle control system according to the detection result also include: detecting obstacles in front, judging whether the obstacles in front are in the warning area according to the detection result, if so, performing a first-level sound and light warning; when the obstacle has a tendency to enter the range, the system adjusts the water range and performs a second-level sound and light warning.

[0009] Further, the detection of the calibrated area based on the first division result and the second division result, and the work control of the sanitation vehicle control system according to the detection result also include: detecting obstacles on both sides of the vehicle body, judging the comprehensive running posture of the obstacles according to the detection result, and judging whether the obstacle has a tendency to enter the necessary interception area in a way assisted by a BSD camera. If so, execute an emergency interception decision.

[0010] According to another aspect of the present invention, a sanitation vehicle control device based on AEBS fusion is provided, and the following technical solutions are adopted: A first calibration module for calibrating the area in front of the vehicle body through a binocular camera, and performing a stepped division on the calibrated area to obtain a first division result; a second calibration module for calibrating the area on both sides of the vehicle body through radar detection, and performing a stepped division on the calibrated area to obtain a second division result; a detection module for detecting the calibrated area based on the first division result and the second division result, and controlling the work of the sanitation vehicle control system according to the detection result.

[0011] Further, the detection module includes: a detection sub-module for detecting obstacles in front, judging whether the obstacles in front are in the necessary interception area according to the detection result, if so, taking a three-level sound and light warning, and at the same time intercepting the water output for 5 seconds, and performing re-detection after 3 seconds of interception. According to the detection result, determine whether to continue intercepting the water output. If so, continue to intercept the next 5-second water output. If not, restore the range.

[0012] Further, the detection module further includes: a warning module for detecting obstacles ahead, determining whether the obstacles ahead are in the warning area according to the detection results, and if so, giving a first-level audible and visual warning. An adjustment module for adjusting the water range of the system and giving a second-level audible and visual warning when the obstacle has a tendency to enter the range.

[0013] Further, the detection module further includes: a judgment module for detecting obstacles on both sides of the vehicle body, judging the comprehensive running posture of the obstacles according to the detection results, and judging whether the obstacles have a tendency to enter the necessary interception area in a way assisted by the BSD camera as vision, and if so, executing an emergency interception decision.

[0014] In addition, the present invention provides a sanitation vehicle, which is characterized by including the above-mentioned sanitation vehicle control device.

[0015] By setting the sanitation vehicle control component, the present invention has accurate recognition ability for different types of obstacles: the obstacle recognition of the binocular stereo camera can be aimed at all types of obstacles. The binocular stereo camera performs image recognition on known types (such as vehicles, pedestrians, etc.), and then estimates the distance between the camera and the obstacle through the size of the target object in the image, and can also effectively sense and measure other non-standard obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0017] Figure 1 It is a flowchart of a sanitation vehicle control method based on AEBS fusion according to an embodiment of the present invention; Figure 2 It is a specific flowchart of a sanitation vehicle control method based on AEBS fusion according to an embodiment of the present invention; Figure 3 It is a logic flowchart of a traditional manual control surface template; Figure 4 It is a structure diagram of a sanitation vehicle control device based on AEBS fusion according to an embodiment of the present invention; Figure 5 It is a traditional manual control surface template (spraying water on both sides) and a traditional manual control surface template (forward water cannon). DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways defined and covered by the claims.

[0019] Figure 1 It is a flowchart of a control method for a sanitation vehicle based on AEBS fusion according to an embodiment of the present invention.

[0020] See Figure 1 As shown, a control method for a sanitation vehicle based on AEBS fusion includes: S101: Calibrate the area in front of the vehicle body through a binocular camera, and perform stepped division on the calibrated area to obtain the first division result; S102: Calibrate the areas on both sides of the vehicle body through radar detection, and perform stepped division on the calibrated areas to obtain the second division result; S103: Detect the calibrated area based on the first division result and the second division result, and control the operation of the sanitation vehicle control system according to the detection result.

[0021] Specifically, I. Interception area calibration: S101 Forward interception area calibration: Conduct distance survey through the binocular camera calibration software, and perform stepped division of the area based on the maximum range of the water cannon being 8 meters combined with the distance surveyed by the binoculars. When the system intelligently controls the water cannon, it gradually decreases according to the stepped area, achieving the effect of shortening the range.

[0022] Both-side interception area calibration: Set a stepped warning area through radar detection area. By analyzing whether there is a phenomenon of pedestrians and non-motor vehicles entering the interception area in terms of their movement trends, gradually decrease the stepped area with a maximum distance of 3 meters on both sides, achieving the effect of shortening the range.

[0023] S102: Execution strategy: Judge the distance of the forward obstacle through the stereo vision of the binocular camera, and judge whether it is within the necessary interception area according to the detected distance; 1. Necessary interception area: When the system judges that there is an obstacle in the necessary interception area, it adopts a three-level audible and visual alarm method to remind the driver that "there is an obstacle within the range, and the range should be adjusted appropriately". At the same time, briefly intercept the water output for 5 seconds. After intercepting for 3 seconds, detect again whether the current range has been adjusted to the effect of no longer infringing on the obstacle; if it has been adjusted, continue to output according to the adjusted effect; if not, enter the next 5-second interval period, and continuously remind the driver to adjust the current water cannon range.

[0024] 2. Non-necessary interception area: When the binocular camera detects a dynamic obstacle at a distance of 2 meters outside the current range, give a first-level audible and visual warning to remind the driver that "there is a moving obstacle"; When there is a tendency for an obstacle to enter the range, the system appropriately adjusts the water range and gives a secondary audible and visual warning to remind the driver that "the obstacle is about to enter the range".

[0025] S103 determines the comprehensive operating attitude (such as moving speed, distance, and direction) of the obstacle through sensors on both sides, and uses the BSD camera as a visual aid to determine whether there is a tendency for the obstacle to enter the interception area, and further determines whether an emergency interception decision needs to be executed.

[0026] Furthermore, the present invention provides an extended solution based on a sanitation vehicle control method based on AEBS fusion, as follows: For a fixed monocular camera and an object, since the monocular camera cannot directly measure depth information, monocular depth estimation is to first identify and then measure the distance. First, it is identified through image matching, and then the distance is estimated according to the size of the target in the database. Since comparisons with the established sample database are required in both the identification and estimation stages, it lacks self-learning capabilities, and the perception results are restricted by the database, and usually unlabeled targets are ignored, which leads to the problem of not being able to identify uncommon targets. For lidar and far-infrared thermal imaging cameras, the comprehensive procurement, maintenance, and operation costs in the finished product market are quite high, and they do not have the conditions for batch implementation.

[0027] As Figure 2 shown Figure 2 is the specific implementation logic flow of a sanitation vehicle control method based on AEBS fusion in this embodiment: 210, Determine the position of the mud block on the road surface; 220, The driver controls the water cannon in the corresponding direction for cleaning; 230, Subjectively judge whether there is a phenomenon of splashing pedestrians with the current water cannon range and output; 240 Autonomously adjust the range and output; 250, Output according to the current control effect; 260, End.

[0028] The specific implementation is as follows: Step 210: First, the system will determine the position of the mud block on the road surface. This is usually achieved through a certain sensor or camera to detect whether there is a mud block on the road surface that needs to be cleaned. Step 220: Once the mud block is detected, the driver will control the water cannon in the corresponding direction for cleaning. This means that the driver will adjust the spraying direction of the water cannon according to the position of the mud block to ensure that the mud block can be accurately removed. Step 230: During the cleaning process, the driver needs to subjectively judge whether there is a phenomenon of splashing pedestrians with the current water cannon range and output. This is a crucial safety step because if the range and output of the water cannon are set improperly, it may splash on pedestrians, causing unnecessary trouble or harm.

[0029] Step 240 (if the judgment in Step 230 is "true"): If the driver discovers that there is indeed a risk of splashing pedestrians with the current water cannon's range or output volume, they will independently adjust the range and output volume to reduce this risk. Note: Here, "true" means that if the judgment result of Step 230 is true (i.e., there is a risk of splashing pedestrians), then the adjustment operation in Step 240 is executed. Step 250: Regardless of whether the range and output volume have been adjusted, the driver will output based on the current control effect (i.e., evaluate the cleaning effect). This is usually achieved by observing the road surface cleaning situation or receiving feedback from the system. Step 260: Finally, the entire process ends. This may mean that the cleaning task has been completed, or the system is ready to enter the next cleaning cycle.

[0030] In comparison with Figure 3 , the traditional process, it reduces the behavioral deviations caused by human subjective factors; Figure 4 The figure is a structural diagram of a sanitation vehicle control device based on AEBS fusion according to an embodiment of the present invention.

[0031] Participate in Figure 4 As shown, a sanitation vehicle control device based on AEBS fusion includes: a first calibration module 41, configured to perform area calibration on the front of the vehicle body through a binocular camera, and perform stepped division on the calibrated area to obtain a first division result; a second calibration module 42, configured to perform area calibration on both sides of the vehicle body through radar detection, and perform stepped division on the calibrated area to obtain a second division result; a detection module 43, configured to detect the calibrated area based on the first division result and the second division result, and perform work control on the sanitation vehicle control system according to the detection result.

[0032] The sanitation vehicle provided by the present invention includes the above-mentioned sanitation vehicle control based on AEBS fusion.

[0033] Compared with the real-time control of traditional high-pressure water cannons, as Figure 5 shown, when the operation vehicle is operating on a road surface where there are pedestrians or non-motor vehicles traveling in parallel (spraying water), the present invention can, through the detection device configured in the AEB system mentioned in the above implementation manner, intelligently monitor the movement trend of obstacles (including pedestrians, non-motor vehicles, etc.) on the road surface, and the system perception is fused with the vehicle operation control system to automatically control the sprinkling range and water volume, thereby avoiding sewage from splashing on pedestrians or non-motor vehicles and reducing complaints and unnecessary civil disputes.

[0034] Only some exemplary embodiments of the present embodiment have been described by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A sanitation vehicle control method based on AEBS fusion, characterized in that: include: The area in front of the vehicle body is calibrated by a binocular camera, and the calibrated area is divided into steps to obtain a first division result; Calibrate the areas on both sides of the vehicle body through radar detection, and divide the calibrated areas into steps to obtain a second division result; The calibrated area is detected based on the first division result and the second division result, and the sanitation vehicle control system is controlled according to the detection result.

2. The sanitation vehicle control method according to claim 1, characterized in that: The first division result and the second division result are both: The calibrated area is divided into a warning area and a necessary interception area according to the range.

3. The sanitation vehicle control method according to claim 2, characterized in that: The detecting of the calibrated area based on the first division result and the second division result, and controlling the operation of the sanitation vehicle control system according to the detection result includes: Obstacle detection is performed ahead, and it is determined whether the obstacle ahead is in the necessary interception area based on the detection result. If so, a three-level sound and light warning is taken, and the water output is intercepted for 5 seconds. Another test is performed 3 seconds after the interception. Based on the detection result, it is determined whether to continue to intercept the water output. If so, the water output will continue to be intercepted for the next 5 seconds. If not, the range is restored.

4. The sanitation vehicle control method according to claim 3, characterized in that: The detecting of the calibrated area based on the first division result and the second division result, and controlling the operation of the sanitation vehicle control system according to the detection result also includes: Detect obstacles ahead and determine whether the obstacles ahead are in the warning area based on the detection results. If so, issue a first-level sound and light warning. When there is a tendency for an obstacle to enter the range, the system adjusts the water volume and range and issues a secondary sound and light warning.

5. The sanitation vehicle control method according to claim 4, characterized in that: The detecting of the calibrated area based on the first division result and the second division result, and controlling the operation of the sanitation vehicle control system according to the detection result also includes: Obstacle detection is performed on both sides of the vehicle body, and the comprehensive operating posture of the obstacle is determined based on the detection results. The BSD camera is used as a visual aid to determine whether the obstacle has a tendency to enter the necessary interception area. If so, an emergency interception decision is made.

6. A sanitation vehicle control device based on AEBS fusion, characterized in that: include: A first calibration module is used to calibrate the area in front of the vehicle body through a binocular camera, and to perform step-wise division on the calibrated area to obtain a first division result; A second calibration module is used to calibrate the areas on both sides of the vehicle body through radar detection, and to divide the calibrated areas into steps to obtain a second division result; The detection module is used to detect the calibrated area based on the first division result and the second division result, and control the operation of the sanitation vehicle control system according to the detection result.

7. The sanitation vehicle control device according to claim 6, characterized in that: The detection module includes: The detection submodule detects obstacles ahead and determines whether the obstacles ahead are in the necessary interception area based on the detection results. If so, a three-level sound and light warning is taken, and the water output is intercepted for 5 seconds. After 3 seconds of interception, another test is performed. Based on the detection results, it is determined whether to continue intercepting the water output. If so, the water output will continue to be intercepted for the next 5 seconds. If not, the range is restored.

8. The sanitation vehicle control device according to claim 7, characterized in that: The detection module also includes: The warning module is used to detect obstacles ahead and determine whether the obstacles ahead are in the warning area based on the detection results. If so, a first-level sound and light warning is issued; The adjustment module is used to adjust the water range and issue a second-level sound and light warning when an obstacle tends to enter the range.

9. The sanitation vehicle control device according to claim 8, characterized in that: The detection module also includes: The judgment module is used to detect obstacles on both sides of the vehicle body, determine the comprehensive operating posture of the obstacle based on the detection results, and use the BSD camera as a visual aid to determine whether the obstacle has a tendency to enter the necessary interception area. If so, an emergency interception decision is executed.

10. A sanitation vehicle, characterized in that: Including the sanitation vehicle control device as described in any one of claims 6-9.

Images