Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Region Aware Autonomous Exploration for Multi-Type Map Construction in Unknown Indoor Environments

Jianfang Mao

TL;DR

This work proposes a novel semantic region aware autonomous exploration method that enables the mobile robot to fully explore the current semantic region before moving to the next region, contributing to avoid excessively-repeated explorations and accelerate the exploration speed.

Abstract

Mainstream autonomous exploration methods usually perform excessively-repeated explorations for the same region, leading to long exploration time and exploration trajectory in complex scenes. To handle this issue, we propose a novel semantic region aware autonomous exploration method, the core idea of which is considering the information of semantic regions to optimize the autonomous navigation strategy. Our method enables the mobile robot to fully explore the current semantic region before moving to the next region, contributing to avoid excessively-repeated explorations and accelerate the exploration speed. In addition, compared with existing au?tonomous exploration methods that usually construct the single-type map, our method allows to construct four types of maps including point cloud map, occupancy grid map, topological map, and semantic map. The experiment results demonstrate that our method achieves the highest 50.7% exploration time reduction and 48.1% exploration trajectory length reduction while maintaining >98% exploration rate when comparing with the classical RRT (Rapid-exploration Random Tree) based autonomous exploration method.

Semantic Region Aware Autonomous Exploration for Multi-Type Map Construction in Unknown Indoor Environments

TL;DR

This work proposes a novel semantic region aware autonomous exploration method that enables the mobile robot to fully explore the current semantic region before moving to the next region, contributing to avoid excessively-repeated explorations and accelerate the exploration speed.

Abstract

Mainstream autonomous exploration methods usually perform excessively-repeated explorations for the same region, leading to long exploration time and exploration trajectory in complex scenes. To handle this issue, we propose a novel semantic region aware autonomous exploration method, the core idea of which is considering the information of semantic regions to optimize the autonomous navigation strategy. Our method enables the mobile robot to fully explore the current semantic region before moving to the next region, contributing to avoid excessively-repeated explorations and accelerate the exploration speed. In addition, compared with existing au?tonomous exploration methods that usually construct the single-type map, our method allows to construct four types of maps including point cloud map, occupancy grid map, topological map, and semantic map. The experiment results demonstrate that our method achieves the highest 50.7% exploration time reduction and 48.1% exploration trajectory length reduction while maintaining >98% exploration rate when comparing with the classical RRT (Rapid-exploration Random Tree) based autonomous exploration method.
Paper Structure (21 sections, 5 equations, 7 figures, 3 tables, 1 algorithm)

This paper contains 21 sections, 5 equations, 7 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Autonomous Exploration Strategy
  4. Hybrid Mapping System
  5. Method
  6. Preliminaries: RRT-Based Exploration
  7. Overview
  8. Semantic Region Aware Autonomous Navigation
  9. Semantic region aware frontier point generation mechanism
  10. Semantic region aware frontier point evaluation function
  11. Multi-Type Map Construction
  12. Experiment
  13. Settings
  14. Simulation environments and robot
  15. Metrics
  16. ...and 6 more sections

Figures (7)

  • Figure 1: Four types of maps constructed by our semantic region aware autonomous exploration method. (1) 2D occupancy grid map, (2) topological map, (3) 3D point cloud map, and (4) semantic map.
  • Figure 2: The overview of our method. The semantic region aware parts are shaded in green.
  • Figure 3: Comparison of original frontier point generation (left) and semantic region aware frontier point generation (right).
  • Figure 4: Simulation environment and simulation robot.
  • Figure 5: Growing trend of exploration rate corresponding to the increasing exploration trajectory length.
  • ...and 2 more figures