Autonomous Navigation Of Quadrupeds Using Coverage Path Planning

2025-04-24

AI Summary

This paper addresses the challenge of autonomous full-coverage scanning navigation for quadruped robots in unstructured environments. We propose a coverage path planning method based on morphological skeletonization. First, a 2D occupancy grid map is constructed via SLAM; then, its morphological skeleton is extracted to generate a sparse sequence of interest points. Subsequently, pixel-level path planning is integrated with the Nav2 framework, coordinated by a finite-state machine to synergize global navigation and local scanning. To our knowledge, this is the first work to introduce morphological skeletonization into coverage path planning for quadruped robots, simultaneously ensuring path feasibility and computational efficiency. Experimental evaluation across five test scenarios demonstrates successful navigation to 86.5% of target points. Map processing and path planning incur average computational costs of 2.52 ms and 1.7 ms per pixel, respectively.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper proposes a novel method of coverage path planning for the purpose of scanning an unstructured environment autonomously. The method uses the morphological skeleton of the prior 2D navigation map via SLAM to generate a sequence of points of interest (POIs). This sequence is then ordered to create an optimal path given the robot's current position. To control the high-level operation, a finite state machine is used to switch between two modes: navigating towards a POI using Nav2, and scanning the local surrounding. We validate the method in a leveled indoor obstacle-free non-convex environment on time efficiency and reachability over five trials. The map reader and the path planner can quickly process maps of width and height ranging between [196,225] pixels and [185,231] pixels in 2.52 ms/pixel and 1.7 ms/pixel, respectively, where their computation time increases with 22.0 ns/pixel and 8.17 $mu$s/pixel, respectively. The robot managed to reach 86.5% of all waypoints over all five runs. The proposed method suffers from drift occurring in the 2D navigation map.

Problem

• Autonomous scanning of unstructured environments using quadruped robots
• Generating optimal paths via SLAM-based morphological skeleton POIs
• Balancing navigation and local scanning with a finite state machine

Innovation

• Uses SLAM-derived morphological skeleton for POI generation
• Employs finite state machine for mode switching control
• Optimizes path planning based on current robot position