Topological Map Construction Based on Region Dynamic Growing and Map Representation Method

Abstract

In the human–machine interactive scene of the service robot, obstacle information and destination information are both required, and both kinds of information need to be saved and used at the same time. In order to solve this problem, this paper proposes a topological map construction pipeline based on regional dynamic growth and a map representation method based on the conical space model. Based on the metric map, the construction pipeline can initialize the region growth point on the trajectory of the mobile robot. Next, the topological region is divided by the region dynamic growth algorithm, the map structure is simplified by the minimum spanning tree, and the similar region is merged by the region merging algorithm. After that, the parameter TM (topological information in the map) and the parameter OM (occupied information in the map) are used to represent the topological information and the occupied information. Finally, a topological map represented by the colored picture is saved by converting to color information. It is highlighted that the topological map construction pipeline is not limited by the structure of the environment, and can be automatically adjusted according to the actual environment structure. What’s more, the topological map representation method can save two kinds of map information at the same time, which simplifies the map representation structure. The experimental results show that the map construction method is flexible, and that resources such as calculation and storage are less consumed. The map representation method is convenient to use and improves the efficiency of the map in preservation.

A Hierarchical Path Planning Approach with Multi-SARSA Based on Topological Map

“…Use the region growth method in Wang et al [ 24 ] to construct the topological map, whose main process is the following: After the grid map is obtained, because the trajectory where the robot moves must be free, the growth point is randomly selected on the driving trajectory; “Then grows dynamically according to the parameters until the regional characteristics meet the requirements, the growth will stop. After the growth of each region is completed, it will be segmented from the grid map, and the color identification of the RGB topological will be established” [ 24 ]. The gravity center of the topological areas will be set as topological nodes while the neighborhood is scanned [ 24 ].…”

TSM: Topological Scene Map for Representation in Indoor Environment Understanding

“…Although the fusion of these two maps achieves obstacle avoidance navigation, the cost of storing the map is extremely. A concise process of topological map construction and effective topological representation are pro- posed in [5] to resolve the problem. While creating a topological map, it is necessary to determine which topological node each region of the environment belongs to.…”

“…These coarsegrained representations are the topological descriptions of the environment. The topological map has been widely used in the navigation of robots [2]- [5], and the recent rapid development of deep learning algorithms provides a new perspective for the application of topological map [6]- [8].…”

Special Feature on Advanced Mobile Robotics

“…Mobile service robot needs to handle the human-machine interactive scene, and Wang et al [17] proposed a topological map construction pipeline with regional dynamic growth algorithm; the map has a representation of topological information as well as occupied information. Autonomous service robots in an indoor complex environment need to find paths with obstacles and also interact with patients.…”