Hilbert-Augmented Reinforcement Learning for Scalable Multi-Robot Coverage and Exploration

2026-02-22

AI Summary

This work addresses the challenges of high redundancy, low efficiency, and poor scalability in multi-robot cooperative coverage and exploration under sparse reward settings. The authors propose a decentralized reinforcement learning framework that integrates a Hilbert space-filling curve as a geometric prior to guide structured exploration trajectories, thereby substantially reducing action redundancy. A curvature-constrained SE(2) trajectory generation interface is also introduced to ensure compatibility with resource-limited physical robots. Experimental results demonstrate that the proposed method significantly improves coverage efficiency and accelerates convergence compared to baseline approaches in grid-based coverage tasks. Furthermore, the approach has been successfully deployed on Boston Dynamics Spot robots, validating its reliability and scalability in real-world indoor environments.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

We present a coverage framework that integrates Hilbert space-filling priors into decentralized multi-robot learning and execution. We augment DQN and PPO with Hilbert-based spatial indices to structure exploration and reduce redundancy in sparse-reward environments, and we evaluate scalability in multi-robot grid coverage. We further describe a waypoint interface that converts Hilbert orderings into curvature-bounded, time-parameterized SE(2) trajectories (planar (x, y, θ)), enabling onboard feasibility on resource-constrained robots. Experiments show improvements in coverage efficiency, redundancy, and convergence speed over DQN/PPO baselines. In addition, we validate the approach on a Boston Dynamics Spot legged robot, executing the generated trajectories in indoor environments and observing reliable coverage with low redundancy. These results indicate that geometric priors improve autonomy and scalability for swarm and legged robotics.

Problem

• multi-robot coverage
• sparse-reward environments
• scalability
• redundancy reduction
• autonomous exploration

Innovation

• Hilbert space-filling curve
• multi-robot reinforcement learning
• coverage and exploration
• curvature-bounded trajectory
• scalable autonomy