A narrow channel path planning method and system based on centerline

Abstract

The present invention discloses a path planning method and system for a smart mobile device to cross a narrow channel by extracting the center line of the channel. When the smart mobile device passes through a narrow channel area, firstly, a local map image near the current position of the smart mobile device is extracted, and then the center line of the connected domain where the smart mobile device is located in the local map image is extracted, and then the path planning method is used to sequentially plan the closest point S_Nearest and the shortest path from the current position S of the smart mobile device to the center line, the closest point G_Nearest and the shortest path from the target point G of the smart mobile device to the center line, and the path from S_Nearest to G_Nearest along the center line. By controlling the smart mobile device to walk along the center line as much as possible, collisions can be minimized. The present invention has strong versatility and can ensure that the smart mobile device can smoothly pass through narrow areas in various complex scenarios.

Description

Technical Field

[0001] The present invention relates to the field of mobile robots, and more specifically to a path planning method and system for an intelligent mobile device in a narrow passage. Background Art

[0002] Path planning is one of the key technologies for mobile robot applications and an important topic in the field of mobile robot research. Current path planning is mainly used in autonomous driving of mobile robots and smart cars, and plans a path from the starting point to the target point by reasonably avoiding obstacles. In practical applications, the scene is relatively complex, with obstacles and channels of various shapes. In the past, narrow channel path planning was generally achieved through random exploration, ignoring the shape and size of the robot itself. When facing different narrow channels, the problem of poor robustness will occur, and a highly adaptable path planning method is needed.

[0003] Therefore, based on the mixed obstacles in narrow passages, how to plan an optimal path for smart mobile devices to pass efficiently and safely is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that the narrow channel path planning method is not robust and inefficient in practical applications, and a narrow channel path planning method along the center line is designed.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for path planning of an intelligent mobile device in a narrow passage comprises the following steps:

[0007] Determine whether the starting point and the target point are in the same connected area. If a path can be successfully planned between the starting point and the target point on the original map, the two are in the same connected domain; or if the contour information is extracted and the parent contour index of the starting point and the target point is the same, the two are in the same connected domain.

[0008] Extract local map images near the current location of the smart mobile device and update map information in real time.

[0009] Extract the contour information of the aforementioned local map image.

[0010] All contours are traversed according to the aforementioned contour information. If the current position of the smart mobile device is within a contour and the contour has no sub-contours or the current position of the smart mobile device is outside all sub-contours of the contour, the connected domain is extracted according to the found parent contour and sub-contours.

[0011] Extract the center line of the connected domain.

[0012] Use the path planning method to obtain the nearest point S_Nearest and the nearest path from the current position of the intelligent mobile device to the center line, the nearest point G_Nearest and the nearest path from the target point to the center line, and the path from S_Nearest to G_Nearest along the center line.

[0013] Its beneficial effect is that in practical applications, the local map image near the current position of the smart mobile device can be replaced by the local obstacle map of the smart mobile device, so as to achieve the purpose of real-time map update. At the same time, extracting the local map image can effectively improve the time efficiency and achieve the purpose of real-time path planning. By extracting the center line of the channel and controlling the smart mobile device to walk along the center line, it can stay away from obstacles to the greatest extent and pass through the narrow channel smoothly.

[0014] A path planning system for an intelligent mobile device in a narrow passage includes acquiring a static global map image and a dynamic local obstacle map image, extracting a local map image, extracting a connected domain where the current position of the intelligent mobile device is located, extracting a center line of the aforementioned connected domain, path planning with a known starting point and a target point, and path planning with a known starting point and a target point on the center line.

[0015] The extraction of the centerline of the connected domain is achieved through image thinning.

[0016] Path planning with known starting and target points, and path planning with known starting and target points on the center line are both achieved through A*. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of the path planning method and system of the present invention;

[0018] Figure 2 A schematic diagram of extracting the center lines of all connected domains of a map according to the present invention;

[0019] Figure 3 After the starting point and the end point are given, the invention extracts the connected domain where the starting point and the end point are located and the center line of the connected domain, as well as an example of planning a path from the starting point to the end point;

[0020] Figure 4 Example of extracting connected regions, centerlines, and planned paths for local image extraction given a start and end point.

Claims

1. A method for path planning of an intelligent mobile device in a narrow passage, characterized in that: The following steps are involved: S1. Determine whether the current position of the smart mobile device and the target point are in the same connected domain on the original map image; S2. Extract a local map image near the current position and extract the outline of the local map image; S3. Extract the image of the connected domain where the current position is located according to the relationship between the parent contour, the child contour, and the point inside and outside the contour; S4. extracting the center line of the connected domain; S5. Use the path planning method to plan the closest point S_Nearest and the shortest path from the current position S of the smart mobile device to the center line; S6. Based on whether the target point is within the aforementioned local map image, a path planning method is used to plan the nearest point G_Nearest and the shortest path from the target point G to the center line on the local map image or the original map image; S7. Obtain a path from S_Nearest to G_Nearest on the center line using a path planning method.

2. A narrow channel intelligent mobile device path planning method according to claim 1, characterized in that: Path planning methods include: S8. Path planning method with known starting and target points; S9. Given a starting point and a target point on the center line, a path planning method is used to expand from the starting point to the center line through the neighborhood.

3. A narrow channel intelligent mobile device path planning method according to claim 1, characterized in that: S10. When the current location of the smart mobile device is updated, the local map image is re-extracted, the map is updated in real time, and the path is planned in real time.

4. A narrow channel intelligent mobile device path planning method according to claim 1, characterized in that: S11. The critical part of the narrow channel path is realized by extracting the center line; S12. Plan the closest position and path from the current position and target point to the center line.

5. A narrow channel intelligent mobile device path planning system, based on the narrow channel path planning system according to any one of claims 1 to 4, characterized in that: include: S13.. Using the path planning method to determine whether a path can be planned or whether the parent contour index is consistent, determine whether the current position of the smart mobile device and the target point are in the same connected domain; S14. Extracting a local map image near the current location of the smart mobile device. The local map can be of any shape and size and can be a static map or a dynamic obstacle map; S15. Extracting the RETR_TREE contour information of the aforementioned local map image; S15. Traverse all contours. If the current position of the smart mobile device is within a contour and the contour has no child contours, or the current position of the smart mobile device is outside all child contours of the contour, then the contour is the parent contour of the current position of the smart mobile device. Extract the image of the connected domain where the current position of the smart mobile device is located based on the parent contour and child contour information; S16. Extracting the center line of the connected domain where the current position of the smart mobile device is located on the aforementioned local map image by using an image thinning method; S17. Path planning with known starting and target points. Path planning with known starting and target points on the center line is implemented by A*. S18. Control the intelligent mobile device to walk along the planned path.

Images