Efficient, Decentralized, and Collaborative Multi-Robot Exploration using Optimal Transport Theory

2020-09-29

An Optimal Transport (OT)-based decentralized collaborative multi-robot exploration strategy is proposed in this paper. This method is to achieve an efficient exploration with a predefined priority in the given domain. In this context, the efficiency indicates how a team of robots (agents) cover the domain reflecting the corresponding priority map (or degrees of importance) in the domain. The decentralized exploration implies that each agent carries out their exploration task independently in the absence of any supervisory agent/computer. When an agent encounters another agent within a communication range, each agent receives the information about which areas are already covered by other agents, yielding a collaborative exploration. The OT theory is employed to quantify the difference between the distribution formed by the robot trajectories and the given reference spatial distribution indicating the priority. A computationally feasible way is developed to measure the performance of the proposed exploration scheme. Further, the formal algorithm is provided for the efficient, decentralized, and collaborative exploration plan. Simulation results are presented to validate the proposed methods.

📄 PDF Abstract BibTeX arXiv:2009.14434

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient Exploration

Multi-Robot Decentralized Collaborative SLAM in Planetary Analogue Environments: Dataset, Challenges, and Lessons Learned

2026-01-28 · Pierre-Yves Lajoie, Karthik Soma, Haechan Mark Bong, Alice Lemieux-Bourque 외 arxiv

Decentralized collaborative simultaneous localization and mapping (C-SLAM) is essential to enable multirobot missions in unknown environments without relying on preexisting localization and communication infrastructure. …

Decentralized Heterogeneous Multi-Robot Collaborative Exploration for Indoor and Outdoor 3D Environments

2026-04-26 · Yuxiang Li, Kun Chen, Jiancheng Wang, Shihao Fang 외 arxiv

Heterogeneous multi-robot systems feature significant adaptability for complex environments. However, effective collaboration that fully exploits the robots' potential remains a core challenge. This paper proposes a dece…

HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization

2026-03-04 · Hao Zhang, Yaru Niu, Yikai Wang, Ding Zhao 외 arxiv

To improve generalization and resilience in human-robot collaboration (HRC), robots must contend with diverse combinations of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, i…

Multi-agent Reinforcement Learning

Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning

2019-06-05 · Wendelin Böhmer, Tabish Rashid, Shimon Whiteson

This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how …

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Efficient Multi-robot Exploration via Multi-head Attention-based Cooperation Strategy

2019-11-05 · Shuqi Liu, Zhaoxia Wu

The goal of coordinated multi-robot exploration tasks is to employ a team of autonomous robots to explore an unknown environment as quickly as possible. Compared with human-designed methods, which began with heuristic an…

Deep Reinforcement Learning Reinforcement Learning