BodyGuards: Escorting by Multiple Robots in Unknown Environment under Limited Communication
Zhuoli Tian, Yanze Bao, Meng Guo
AI summary
Problem
Current multi-robot exploration methods prioritize complete coverage or assume reliable communication, failing to address the challenge of safely escorting human operators to a goal in unknown, adversarial spaces under restricted connectivity.
Approach
BodyGuards integrates risk-aware dynamic path planning for the operator, a dual-mode robot strategy that alternates between frontier exploration and optimized return events, and a ring-topology protocol for intermittent inter-robot and robot-operator communication.
Key results
- Significantly reduces operator risk and mission time
- Outperforms state-of-the-art baselines in adversarial and constrained environments
- Integrates risk estimation, dynamic path planning, and multi-robot coordination into a unified framework
- Validated through extensive human-in-the-loop simulations and hardware experiments
Why it matters
Enables safe and efficient human-robot teaming for high-risk missions like disaster response and subterranean exploration where connectivity is poor.
Abstract
Multi-robot systems are increasingly deployed in high-risk missions such as reconnaissance, disaster response, and subterranean operations. Protecting a human operator while navigating unknown and adversarial environments re- mains a critical challenge, especially when the communication among the operator and robots is restricted. Unlike existing collaborative exploration methods that aim for complete cover- age, this work focuses on task-oriented exploration to minimize the navigation time of the operator to reach its goal while ensuring safety under adversarial threats. A novel escorting framework BodyGuards, is proposed to explicitly integrate seamlessly collaborative exploration, inter-robot-operator com- munication and escorting. The framework consists of three core components: (I) a dynamic movement strategy for the operator that maintains a local map with risk zones for proactive path planning; (II) a dual-mode robotic strategy combining frontier- based exploration with optimized return events to balance exploration, threat detection, and intermittent communication; and (III) multi-robot coordination protocols that jointly plan exploration and information sharing for efficient escorting. Extensive human-in-the-loop simulations and hardware ex- periments demonstrate that the method significantly reduces operator risk and mission time, outperforming baselines in adversarial and constrained environments.