A Visitation Grid for Complete Coverage Foraging in Robot Swarms

2026-05-20

AI Summary

This work addresses the challenge of efficiently achieving complete coverage for sparse resource collection by robotic swarms in large, unknown environments—particularly the low efficiency observed during the final phase when only scattered resources remain. The authors propose a visitation-grid-based stochastic foraging strategy that leverages a lightweight central server to maintain regional visit counts. By integrating global visitation density estimation with local random selection, robots are guided toward neighboring regions with the fewest prior visits. The approach employs a grid-based environmental representation, a probabilistic region selection mechanism, and a distributed coordination algorithm designed for limited computational and memory resources, enabling scalable and efficient coverage. Compared to the classical CPFA algorithm, the proposed method reduces total collection time by up to 33% and improves late-stage efficiency by over 48%, significantly enhancing system robustness, flexibility, and scalability.

Abstract

The complete collection of sparse resources in large, unknown environments remains a challenging problem for autonomous robot swarms. Previous studies have shown that a substantial portion of total mission time is consumed during the final stage of collection, where only a small fraction of randomly scattered resources remain. Consequently, many existing swarm foraging algorithms (search and collection) focus on collecting most resources within a limited time window, rather than improving end-stage efficiency for collecting all resources. We propose a grid-based stochastic foraging strategy that explicitly reduces redundant visits and accelerates late-stage collection. The unknown search area is partitioned into a grid map, which is maintained by a lightweight central server. To maintain scalability, both robots and the server operate within limited memory and computational constraints. The server updates the grid-level visitation counts based on robot-reported locations, producing a global estimate of the exploration density. For each new foraging trip, a robot selects its next search area from a local 3 X 3 neighborhood of grids probabilistically with the lowest visitation count, thus biasing exploration toward under-visited regions while maintaining stochasticity. Extensive simulation experiments demonstrate that the proposed strategy consistently outperforms the canonical centrally placed baseline foraging algorithm (CPFA). Compared to CPFA, the proposed method reduces the total collection time by up to 33% and improves collection efficiency by more than 48% during the final stage of the mission. These results indicate that the proposed strategy is robust, flexible, and scalable for near-complete and complete resource collection in robot swarms and can serve as a general enhancement for stochastic swarm foraging methods under limited onboard resources.

Problem

• robot swarms
• complete coverage
• foraging
• sparse resources
• unknown environments

Innovation

• visitation grid
• stochastic foraging
• robot swarms
• complete coverage
• scalable coordination