EARS-Info improves multi-robot city exploration efficiency and safety
EARS-Info: Information-Aware Event-Driven Reallocation for Multi-Robot Exploration
RoboticsArtificial IntelligenceMultiagent Systems
Summary
Exploring large city areas with multiple robots can be tricky because robots need to decide where to go next to find new information and avoid wasting energy. The authors present EARS-Info, a system that helps robots intelligently choose where to move based on what new information they can get, how easy it is to get there, and planning to return safely when needed. Tests on simulated city maps show EARS-Info outperforms previous methods by finding more important places, using less energy, and avoiding problems during exploration. This makes robot teams better at mapping or searching in urban environments.
What this means in practice
- •For autonomous vehicle developers: Coordinate multiple exploration robots in urban areas to maximize finding new information while minimizing energy use and risks during missions.
- •For disaster response teams: Use multi-robot teams to safely and efficiently survey disaster-affected city zones with improved data gathering and fewer operational failures.
Authors
Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere Kyamakya
Abstract
We introduce EARS-Info, an information-aware extension of Event-Driven Ant Reallocation Search for multi-robot exploration on OpenStreetMap-derived grids. It combines marginal sensing gain, feasible relocation, return-aware routing, sensing reservations, and cached shortest paths. Across 168,000 episodes comparing 30 implementations on eight city maps, EARS-Info achieves the highest mean operational score in every evaluation panel. With eight robots and 3% communication dropout, it improves the score over EARS-Safe by 5.43%, increases weighted discovery from 88.88% to 98.46%, and reduces mean energy use by 2.62%. Score differences are positive in all eight cities ($p=0.0078125$; descriptive 95% city-bootstrap interval $[0.0159,0.0694]$), with no simulated incidents across 5,600 EARS-Info episodes. These results support the complete controller; individual component advantages remain uncertain. Generalization is limited by reused geography, one training replicate, coarse maps, and adapted comparison methods.