Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CAP: A Connectivity-Aware Hierarchical Coverage Path Planning Algorithm for Unknown Environments using Coverage Guidance Graph

Zongyuan Shen, Burhanuddin Shirose, Prasanna Sriganesh, Matthew Travers

TL;DR

CAP tackles online coverage of unknown environments by maintaining an incremental online map and building a coverage guidance graph that encodes global topology. It uses a hierarchical planner that switches between greedy exploration for exploring subareas and a TSP-based global tour for explored regions, yielding improved global coverage efficiency and reduced local coverage time. In both high-fidelity simulations and real-world experiments, CAP outperforms five baselines in coverage time, path length, and path overlap, demonstrating practical gains for autonomous exploration. The approach offers a scalable framework for online CPP with potential extensions to multi-robot and dynamic scenarios.

Abstract

Efficient coverage of unknown environments requires robots to adapt their paths in real time based on on-board sensor data. In this paper, we introduce CAP, a connectivity-aware hierarchical coverage path planning algorithm for efficient coverage of unknown environments. During online operation, CAP incrementally constructs a coverage guidance graph to capture essential information about the environment. Based on the updated graph, the hierarchical planner determines an efficient path to maximize global coverage efficiency and minimize local coverage time. The performance of CAP is evaluated and compared with five baseline algorithms through high-fidelity simulations as well as robot experiments. Our results show that CAP yields significant improvements in coverage time, path length, and path overlap ratio.

CAP: A Connectivity-Aware Hierarchical Coverage Path Planning Algorithm for Unknown Environments using Coverage Guidance Graph

TL;DR

CAP tackles online coverage of unknown environments by maintaining an incremental online map and building a coverage guidance graph that encodes global topology. It uses a hierarchical planner that switches between greedy exploration for exploring subareas and a TSP-based global tour for explored regions, yielding improved global coverage efficiency and reduced local coverage time. In both high-fidelity simulations and real-world experiments, CAP outperforms five baselines in coverage time, path length, and path overlap, demonstrating practical gains for autonomous exploration. The approach offers a scalable framework for online CPP with potential extensions to multi-robot and dynamic scenarios.

Abstract

Efficient coverage of unknown environments requires robots to adapt their paths in real time based on on-board sensor data. In this paper, we introduce CAP, a connectivity-aware hierarchical coverage path planning algorithm for efficient coverage of unknown environments. During online operation, CAP incrementally constructs a coverage guidance graph to capture essential information about the environment. Based on the updated graph, the hierarchical planner determines an efficient path to maximize global coverage efficiency and minimize local coverage time. The performance of CAP is evaluated and compared with five baseline algorithms through high-fidelity simulations as well as robot experiments. Our results show that CAP yields significant improvements in coverage time, path length, and path overlap ratio.

Paper Structure

This paper contains 14 sections, 4 equations, 7 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. CAP Algorithm
  4. Identification of Disconnected Subareas
  5. Incremental Construction of Coverage Guidance Graph
  6. Global Coverage Tour Planning
  7. Local Coverage Path Planning
  8. Coverage of Exploring Node
  9. Coverage of Explored Node
  10. Time Complexity Analysis
  11. Results and Discussion
  12. Simulation Validations
  13. Real-World Experiments
  14. Conclusions and Future Work

Figures (7)

  • Figure 1: Example of coverage paths generated by different methods.
  • Figure 2: Illustration of the CAP algorithm: a)-b) identification of disconnected subareas, c) incremental construction of coverage guidance graph, and c)-d) computation of hierarchical coverage path.
  • Figure 3: Car-like robot in gazebo scene used for simulation experiments (top row). Spot robot in a large warehouse with configurable obstacles used for real-world experiments (bottom row).
  • Figure 4: Performance comparison of CAP with the baseline algorithms in simulations.
  • Figure 5: Coverage paths generated by different algorithms in experiment 1.
  • ...and 2 more figures

Theorems & Definitions (5)

  • Definition III.1: Tiling
  • Definition III.2: Complete Coverage
  • Definition III.3: Exploring Area
  • Definition III.4: Disconnected Subareas
  • Definition III.5: Coverage Guidance Graph