Intelligent navigation point decision-making method based on urban road surface cleaning scene

Abstract

The invention discloses an intelligent navigation point decision-making method based on an urban road surface cleaning scene, and the method comprises the steps: initializing the position of a navigation point, and obtaining the position information of an operator, grid map information, road line information and vehicle pose information; checking whether effective grid map information, vehicle pose information, position information of an operator and road line information are received or not, checking whether the vehicle and the operator are on the same side of a road line or not, and checking whether a current navigation point is in a non-driving area of the grid map or not; and continuously searching a driving coordinate within a certain range along the-X direction in the local coordinate system, converting the position of the navigation point into a coordinate in the global coordinate system, and sending the position information of the navigation point through a communication architecture of the vehicle-mounted computing platform. The method has the advantage of high-reliability navigation point decision.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an intelligent navigation point decision method based on an urban road cleaning scenario. Background Art

[0002] In the cleaning operation of open roads in cities, two operators are currently required to clean the road and drive the cleaning vehicle respectively. With the development of autonomous driving technology, unmanned driving technology can be used to complete the function of driving the water storage vehicle, and the cleaning operators can complete the road cleaning work together. However, the current unmanned driving technology mostly focuses on how the vehicle goes to the predetermined navigation point, and less on how the vehicle and the operators work together efficiently in the urban road cleaning scenario.

[0003] The navigation point is the end point of a trajectory, and the selection of the navigation point should take into account the work task and the work environment. First of all, the work task is road cleaning, and the vehicle is equipped with a water pipe of limited length, so the navigation point of the decision cannot be more than the length of the water pipe away from the cleaning operator. Then, the working environment is an open road in the city, and vehicles are driving on sidewalks or non-motorized vehicle lanes. The road traffic environment is complex, so the navigation point of the decision should minimize the occupation of motor vehicle lanes and avoid collisions with surrounding obstacles. This is where this application needs to focus on improvement.

[0004] Disadvantages: Although document CN 115755925 A provides an option for setting up pedestrian following, it does not explain the specific method for selecting the vehicle navigation point during the pedestrian following process; the operation parking point in document CN 116466703 A is the parking position at the end of the operation, and it is not possible to realize midway parking and real-time updating of navigation points during the operation. At the same time, the function of the vehicle following the target person cannot be realized through the selection of navigation points; document WO 2023 / 051312 A1 cannot realize the function of the vehicle following the target person through the selection of navigation points; document EP3452788A1 cannot realize the function of the vehicle following the target person through the selection of navigation points.

[0005] This is an area where this application needs to be improved. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide an intelligent navigation point decision method based on an urban road cleaning scenario, which realizes a real-time intelligent navigation point position decision method for target personnel following during vehicle operation.

[0007] In order to solve the above technical problems, the present invention provides an intelligent navigation point decision method based on urban road cleaning scenarios, which aims to achieve navigation point selection that meets the requirements of work tasks and work environment and satisfies the continuous driving conditions of the vehicle in specific work scenarios.

[0008] The present invention involves two reference frames: 1) Local coordinate system, a rectangular coordinate system fixed to the vehicle. The vehicle's position is taken as the origin, the vehicle's forward direction is the positive direction of the X axis, and the right side perpendicular to the vehicle's direction is the positive direction of the Y axis; 2) Global coordinate system: A rectangular coordinate system fixed to the earth. The position of the local coordinate system when the program is started is the position of the global coordinate system.

[0009] The present invention provides an intelligent navigation point decision method based on an urban road cleaning scenario, and the specific steps are as follows: Step S0: Initialize the coordinates of the navigation point in the global coordinate system to ; Step S1: Obtain the location information of the operator, grid map information, roadside information and vehicle posture information. The specific steps are as follows: Step S11: obtaining the coordinates of the operator's position in the local coordinate system through the communication architecture of the vehicle-mounted computing platform; whenever valid information is received, the corresponding receiving flag is recorded as true; Step S12: obtaining a grid map consisting of grids with a fixed grid size and containing two states of drivable and non-drivable in a local coordinate system through the communication architecture of the vehicle-mounted computing platform; whenever valid information is received, the corresponding reception flag is recorded as true; The meaning of the non-drivable area in the grid map is the area containing obstacles in the environment; Step S13: The roadside line is fitted with a parametric equation, and the roadside line equation parameters in the vehicle local coordinate system are obtained through the communication architecture of the vehicle computing platform. Whenever valid information is received, the corresponding reception flag is recorded as true; Step S14: obtaining the orientation angle of the position coordinates of the vehicle in the global coordinate system through the communication architecture of the vehicle-mounted computing platform, and whenever valid information is received, marking the corresponding receiving flag as true; Step S2: Check whether valid grid map information has been received; If valid raster map information is received, the corresponding reception flag is recorded as false; If no valid grid map information is received, the process returns to step S1 to continue receiving the grid map information; Step S3: Check whether valid vehicle posture information is received; If valid vehicle posture information is received, the corresponding receiving flag is marked as false; If no valid vehicle position information is received, return to step S1 to continue receiving vehicle position information; Step S4: Check whether the location information of the valid operator has been received; If valid operator location information is received, the corresponding reception flag is marked as false; If no valid operator location information is received, the process proceeds to step S9; Step S5: Check whether valid roadside information has been received; If valid roadside information is received, the corresponding receiving flag is recorded as false; If no valid roadside information is received, jump to step S7; Step S6: Check whether the vehicle and the operator are on the same side of the roadside; If the vehicle and the operator are on the same side of the roadside, the navigation point is set at 2±0.3m directly behind the operator's body and converted into coordinates in the global coordinate system for storage; If the vehicle and the operator are not on the same side of the roadside, the navigation point is set to the left of the operator, 1.5±0.3m away from the non-drivable area on the right, and converted into coordinates in the global coordinate system for storage; Step S7: Check whether the current navigation point is in a non-drivable area of ​​the grid map; If the current navigation point is not in the non-drivable area of ​​the grid map, then the process goes to step S9; Step S8: Continue to search for a drivable coordinate within a range of 1m along the -X direction in the local coordinate system; If such coordinates are not found, a decision failure message is sent through the communication architecture of the vehicle computing platform, and the process returns to step S1 to make a new decision; Step S9: Convert the position of the navigation point into coordinates in the global coordinate system, send the navigation point position information through the communication architecture of the on-board computing platform, and then return to step S1 to make a new decision.

[0010] The superior effects of the present invention are: 1) The navigation point decision method of the present invention ensures high reliability of navigation point decision. Regardless of whether effective operator location information and roadside information can be obtained, the navigation point decision program can run normally, and at the same time, a navigation point decision result is guaranteed to be given when there are no obstacles around the vehicle; 2) The navigation point decision method of the present invention fully meets the operation requirements. On the one hand, the navigation point is selected as close to the operator as possible, and at the same time, the navigation point is also as close to the obstacle as possible to prevent the vehicle from driving into the motor vehicle lane. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings constituting a part of the present application 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 an improper limitation of the present invention. In the drawings: Figure 1 It is a workflow diagram of a specific embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0013] like Figure 1 As shown, the present invention provides an intelligent navigation point decision method based on an urban road cleaning scenario, comprising the following steps: Step S0: Initialize the coordinates of the navigation point in the global coordinate system to .

[0014] Step S1: Obtain the location information of the operator, grid map information, roadside information and vehicle posture information, specifically: Step S11: Obtain the coordinates of the operator's position in the local coordinate system through ROS topic communication, and whenever valid information is received, the corresponding reception flag is recorded as true; Step S12: obtaining a grid map consisting of grids with a fixed grid size and containing two states of drivable and non-drivable in a local coordinate system through ROS topic communication, and whenever valid information is received, the corresponding reception flag is recorded as true; The meaning of the non-drivable area in the grid map is the area containing obstacles in the environment; Step S13: The roadside line is calculated by the straight line equation Perform fitting and obtain the equation parameters of the roadside line in the vehicle's local coordinate system through ROS topic communication , whenever valid information is received, the corresponding receiving flag is recorded as true; Step S14: Obtain the vehicle's coordinates in the global coordinate system through ROS topic communication The direction angle θ is set, and whenever valid information is received, the corresponding reception flag is recorded as true.

[0015] Step S2: Check whether valid grid map information has been received; If valid raster map information is received, the corresponding reception flag is recorded as false; If no valid grid map information is received, the process returns to step S1 to continue receiving grid map information.

[0016] Step S3: Check whether valid vehicle posture information is received; If valid vehicle posture information is received, the corresponding receiving flag is marked as false; If no valid vehicle posture information is received, return to step S1 to continue receiving vehicle posture information.

[0017] Step S4: Check whether the location information of the valid operator has been received; If valid operator location information is received, the corresponding reception flag is marked as false; If no valid operator location information is received, the process proceeds to step S9.

[0018] Step S5: Check whether valid roadside information has been received; If valid roadside information is received, the corresponding receiving flag is recorded as false; If no valid roadside information is received, the process proceeds to step S7.

[0019] Step S6: Check whether the vehicle and the operator are on the same side of the roadside; If the vehicle and the operator are on the same side of the roadside, the navigation point is set at 2 m behind the operator and converted into coordinates in the global coordinate system using formula (1) for storage; (1); in: Represents the coordinates of the navigation point in the local coordinate system, Represents the coordinates of the navigation point in the global coordinate system, Represents the coordinates of the vehicle center in the global coordinate system and the heading angle of the vehicle in the global coordinate system; If the vehicle and the operator are not on the same side of the roadside, the navigation point is set to the left of the operator, 1.5 m away from the non-drivable area on the right, and converted to coordinates in the global coordinate system using formula (1) for storage.

[0020] Step S7: Check whether the current navigation point is in a non-drivable area of ​​the grid map; If the current navigation point is not in the non-drivable area of ​​the grid map, the process proceeds to step S9.

[0021] Step S8: Continue to search for a travel coordinate within a certain range along the -X direction in the local coordinate system. If no such coordinate is found, a WARN message indicating decision failure is issued through the ROS system, and return to step S1 for a new decision.

[0022] Step S9: Use formula (2) to convert the position of the navigation point into coordinates in the local coordinate system, and send the navigation point position information through the communication architecture of the vehicle computing platform; then return to step S1 to make a new decision; (2).

[0023] 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. An intelligent navigation point decision method based on urban road cleaning scenarios, comprising the following steps: Step S0: Initialize the coordinates of the navigation point in the global coordinate system to ; Step S1: Acquire the location information of the operator, grid map information, roadside information and vehicle posture information; Step S2: Check whether valid grid map information is received; If valid raster map information is received, the corresponding reception flag is recorded as false; If no valid grid map information is received, the process returns to step S1 to continue receiving the grid map information; Step S3: Check whether valid vehicle posture information is received; If valid vehicle posture information is received, the corresponding receiving flag is marked as false; If no valid vehicle position information is received, return to step S1 to continue receiving vehicle position information; Step S4: Check whether the location information of the valid operator has been received; If valid operator location information is received, the corresponding reception flag is marked as false; If no valid operator location information is received, the process proceeds to step S9; Step S5: Check whether valid roadside information has been received; If valid roadside information is received, the corresponding receiving flag is recorded as false; If no valid roadside information is received, jump to step S7; Step S6: Check whether the vehicle and the operator are on the same side of the roadside; If the vehicle and the operator are on the same side of the roadside, the navigation point is set at 2±0.3 behind the operator's body and converted into coordinates in the global coordinate system for storage; If the vehicle and the operator are not on the same side of the roadside, the navigation point is set to the left of the operator, 1.5±0.3m away from the non-drivable area on the right, and converted into coordinates in the global coordinate system for storage; Step S7: Check whether the current navigation point is in a non-drivable area of ​​the grid map; If the current navigation point is not in the non-drivable area of ​​the grid map, then the process goes to step S9; Step S8: Continue to search for a travel coordinate within a certain range along the -X direction in the local coordinate system; If such coordinates are not found, a decision failure message is sent through the communication architecture of the vehicle computing platform, and the process returns to step S1 to make a new decision; Step S9: Convert the position of the navigation point into coordinates in the global coordinate system, send the navigation point position information through the communication architecture of the on-board computing platform, and then return to step S1 to make a new decision.

2. The intelligent navigation point decision method based on the urban road cleaning scenario according to claim 1 is characterized by: The step S1 comprises the following specific steps: Step S11: obtaining the coordinates of the operator's position in the local coordinate system through the communication architecture of the vehicle-mounted computing platform, and whenever valid information is received, marking the corresponding receiving flag as true; Step S12: obtaining a grid map consisting of grids with a fixed grid size and containing two states of drivable and non-drivable in a local coordinate system through the communication architecture of the vehicle-mounted computing platform; whenever valid information is received, the corresponding reception flag is recorded as true; Step S13: The roadside line is fitted with a parametric equation, and the roadside line equation parameters in the vehicle local coordinate system are obtained through the communication architecture of the vehicle computing platform. Whenever valid information is received, the corresponding reception flag is recorded as true; Step S14: The orientation angle of the position coordinates of the vehicle in the global coordinate system is obtained through the communication architecture of the vehicle-mounted computing platform. Whenever valid information is received, the corresponding receiving flag is recorded as true.

3. A computer system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the navigation point decision method according to any one of claims 1-2.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the navigation point decision method described in any one of claims 1-2 are implemented.

5. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the navigation point decision method described in any one of claims 1-2 are implemented.

Images