IR2: Implicit Rendezvous for Robotic Exploration Teams under Sparse Intermittent Connectivity

2024-09-07

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

In large-scale sparse, intermittently connected environments, multi-robot exploration suffers from inefficient information sharing, excessive detours for explicit rendezvous, and short-sighted greedy pursuit decisions. To address these challenges, this paper proposes a cooperative exploration method based on an implicit rendezvous mechanism. Our key contributions are: (1) the first deep reinforcement learning framework integrating attention mechanisms with hierarchical sparse graph modeling, which eliminates predefined rendezvous points and greedy pursuit policies to enable long-horizon coordination between disconnection-aware exploration and reconnection-enabled information sharing; and (2) the incorporation of curriculum learning to enhance training stability. Evaluated across three large-scale Gazebo simulation environments, our approach reduces total path length by 6.6–34.1% and significantly improves map consistency. The source code is publicly available.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Teamwork

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Information sharing is critical in time-sensitive and realistic multi-robot exploration, especially for smaller robotic teams in large-scale environments where connectivity may be sparse and intermittent. Existing methods often overlook such communication constraints by assuming unrealistic global connectivity. Other works account for communication constraints (by maintaining close proximity or line of sight during information exchange), but are often inefficient. For instance, preplanned rendezvous approaches typically involve unnecessary detours resulting from poorly timed rendezvous, while pursuit-based approaches often result in short-sighted decisions due to their greedy nature. We present IR2, a deep reinforcement learning approach to information sharing for multi-robot exploration. Leveraging attention-based neural networks trained via reinforcement and curriculum learning, IR2 allows robots to effectively reason about the longer-term trade-offs between disconnecting for solo exploration and reconnecting for information sharing. In addition, we propose a hierarchical graph formulation to maintain a sparse yet informative graph, enabling our approach to scale to large-scale environments. We present simulation results in three large-scale Gazebo environments, which show that our approach yields 6.6−34.1% shorter exploration paths and significantly improved mapped area consistency among robots when compared to state-of-the-art baselines. Our simulation training and testing code is available at https://github.com/marmotlab/IR2.

Problem

• Enables efficient information sharing in sparse, intermittent robot connectivity
• Optimizes trade-offs between solo exploration and reconnection for data exchange
• Scales to large environments via hierarchical graph formulation

Innovation

• Deep reinforcement learning for multi-robot exploration
• Attention-based neural networks with curriculum learning
• Hierarchical graph for scalable sparse connectivity