Mind the Gaps: Multi-Robot Feedback-Driven Ergodic Coverage in Unknown Environments

2026-05-20

AI Summary

This work proposes an adaptive coverage strategy for multi-robot systems operating in unknown environments, where traditional approaches often rely on prior information and struggle to sample efficiently. By leveraging real-time feedback, the method employs online learning to construct a parameterized environmental model, dynamically estimating the spatial distribution of information and guiding robots to collaboratively optimize their traversal trajectories with emphasis on high-value regions. The approach tightly integrates online model updating with coverage control, enabling significant improvements in coverage efficiency and resource utilization without requiring any prior knowledge of the environment. Extensive simulations demonstrate its superior performance over existing methods in fully unknown scenarios.

Abstract

In this work, we address the problem of multi-robot adaptive coverage, where teams of robots perform dynamic sampling by continuously adjusting their positions to collect data in an environment. This task can be challenging, particularly when robots must be efficiently allocated to new sampling locations over time. Ergodic search methods optimize robot trajectories by ensuring that the robots' time-averaged spatial distribution aligns with the spatial distribution of environmental information. While these methods promote effective exploration provided a target distribution, they often fail to account for unknown prior distributions of the environment. To overcome this limitation, we propose an adaptive coverage strategy that utilizes real-time feedback from an environmental model to adjust robot sampling behavior in response to unknown conditions. Our approach enhances traditional ergodic trajectory optimization by constructing a target spatial information distribution based on parametric models of the environment, which are updated online. This strategy assumes that the environment is either static or changes slowly compared to the robot's motion. Our framework allows robots to dynamically prioritize regions of high interest, improving coverage efficiency, synthesizing effective control policies for individual agents, and optimizing resource use in settings with unknown prior distributions. We validate our approach through simulations, demonstrating its effectiveness in enhancing coverage and resource allocation.

Problem

• multi-robot coverage
• ergodic control
• unknown environments
• adaptive sampling
• spatial information distribution

Innovation

• adaptive coverage
• ergodic control
• multi-robot systems
• real-time feedback
• unknown environments