Unlock instant, AI-driven research and patent intelligence for your innovation.

An Indoor Path Planning Method Based on Obstacle Semantic Information

A technology of semantic information and path planning, applied in two-dimensional position/course control, vehicle position/route/altitude control, instruments, etc., can solve problems such as weak positioning ability and poor safety, achieve high accuracy and improve accuracy The effect of high accuracy, security and fault tolerance

Active Publication Date: 2022-07-29
TONGJI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The core of indoor robot navigation is to plan a collision-free path from the starting point to the target point in a complex environment, avoiding different types of obstacles, and weak positioning ability
However, the indoor path planning and optimization methods proposed in the prior art are mainly dedicated to keeping a certain distance between the robot and obstacles, and performing path planning by establishing an environmental hazard map, in which the hazard decreases with the increase of the distance from the obstacle. However, the design of this risk level is usually fixed, and the consequences caused by the collision of different types of obstacles are very different. Therefore, the method of path planning by establishing an environmental risk level map has limitations for indoor path planning. poor sex

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Indoor Path Planning Method Based on Obstacle Semantic Information
  • An Indoor Path Planning Method Based on Obstacle Semantic Information
  • An Indoor Path Planning Method Based on Obstacle Semantic Information

Examples

Experimental program
Comparison scheme
Effect test

example 1 and example 2

[0093] Example 1 The indoor path planning method proposed in this embodiment is applied to perform path planning in a room, figure 2 for the interior 3D map of the room, image 3 for the semantic map of the room, Figure 4 The three-dimensional map of the danger level of Example 1, the danger level is divided into 1 to 6, Figure 5 for Figure 4 The two-dimensional grid map generated by the vertical projection of the part below the height of the robot, Image 6 for the basis of Figure 5 The cost map produced by grayscale represents the passing cost of the grid around the obstacle;

example 2

[0094] Example 2 The indoor path planning method proposed in this embodiment is applied to carry out path planning in a house, Figure 7 for indoor 3D maps of houses, Figure 8 for the basis of Figure 7 the generated semantic map, Figure 9 For the price map of the house, Figure 10 A schematic diagram of the planned path for the cost map, such as Figure 11 , the cost algorithm proposed in the prior art divides the indoor environment into corridors and rooms. The passage costs of corridors and rooms are different, and a path with the smallest traversal cost is planned. obstacles to avoid robot collisions, while the planned paths generated by the cost algorithm and A* algorithm proposed in the prior art cannot be biased towards or away from different types of obstacles.

[0095] This embodiment proposes an indoor path planning method based on the semantic information of obstacles, constructs a semantic map, identifies different types of obstacles through the semantic info...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an indoor path planning method based on the semantic information of obstacles, which specifically includes: obtaining an indoor three-dimensional map, obtaining the semantic information of the indoor obstacles according to the indoor three-dimensional map; obtaining the obstacles by evaluating the classification decision tree according to the semantic information of the obstacles According to the danger level of the object, generate a three-dimensional map of the danger level according to the indoor three-dimensional map and the danger level of the obstacles; perform a vertical projection on the part of the three-dimensional danger level map whose height is lower than the height of the robot to generate a two-dimensional grid map; The traffic cost of each grid in the 2D grid map is used to generate a cost map; the initial grid and the end grid are selected on the 2D grid map, and a line from the initial grid to the end grid is generated on the cost map through the evaluation function. The planned path with the smallest total traffic cost, and the robot walks indoors according to the planned path. Compared with the prior art, the present invention has the advantages of high accuracy, good security and high fault tolerance.

Description

technical field [0001] The invention relates to the field of indoor robot global path planning, in particular to an indoor path planning method based on obstacle semantic information. Background technique [0002] The navigation ability of a mobile robot is a key issue that determines its autonomous ability, and it has been a hot topic in the field of robotics. Global path planning is the core component of robot navigation and an important factor affecting the autonomous driving performance of robots. It refers to planning the optimal path between a given starting point and a target point in a known map. In recent years, with the continuous development of the application of robots in indoor scenes, planning the optimal path of indoor robots has also become a key issue in the field of robot navigation. Compared with structured roads in outdoor environments, robot path planning in indoor scenes is more complex and contains more uncertain factors. This complexity is reflected...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05D1/02
CPCG05D1/0214G05D1/0221
Inventor 张皓孙霄翔王祝萍张长柱黄超
Owner TONGJI UNIV