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

TL;DR

IR2 is a deep reinforcement learning method that enables multi-robot teams to efficiently share information during exploration in environments with sparse and intermittent connectivity, outperforming existing approaches.

Contribution

The paper introduces IR2, a novel RL-based approach with attention mechanisms and hierarchical graph modeling for scalable, efficient multi-robot exploration under realistic communication constraints.

Findings

IR2 achieves 6.6-34.1% shorter exploration paths than baselines.

The approach scales to large environments via hierarchical graph formulation.

IR2 successfully deployed on hardware, demonstrating practical applicability.

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 when compared to state-of-the-art baselines, and lastly deploy our learned policy on hardware. Our simulation training and testing code is available at https://ir2-explore.github.io.