跳到主要导航 跳到搜索 跳到主要内容

SDHN: Skewness-Driven Hypergraph Networks for Enhanced Localized Multi-robot Coordination

  • Delin Zhao
  • , Yanbo Shan
  • , Chang Liu
  • , Shenghang Lin
  • , Yingxin Shou
  • , Bin Xu
  • Northwestern Polytechnical University Xian
  • Southeast University, Nanjing

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Multi-Agent Reinforcement Learning is widely used for multi-robot coordination, where simple graphs typically model pairwise interactions. However, such representations fail to capture higher-order collaborations, limiting effectiveness in complex tasks. While hypergraph-based approaches enhance cooperation, existing methods often generate arbitrary hypergraph structures and lack adaptability to environmental uncertainties. To address these challenges, we propose the Skewness-Driven Hypergraph Network (SDHN), which employs stochastic Bernoulli hyperedges to explicitly model higher-order multi-robot interactions. By introducing a skewness loss, SDHN promotes an efficient structure with Small-Hyperedge Dominant Hypergraph, allowing robots to prioritize localized synchronization while still adhering to the overall information, similar to human coordination. Extensive experiments on Moving Agents in Formation and Robotic Warehouse tasks validate SDHN’s effectiveness, demonstrating superior performance over state-of-the-art baselines.

源语言英语
主期刊名Proceedings of the Second International Conference on Advanced Robotics, Control, and Artificial Intelligence - ICARCAI 2025
编辑Hai Wang
出版商Springer Science and Business Media Deutschland GmbH
页135-147
页数13
ISBN(印刷版)9789819209705
DOI
出版状态已出版 - 2027
活动2nd International Conference on Advanced Robotics, Control, and Artificial Intelligence, ICARCAI 2025 - Nadi, 斐济
期限: 24 11月 2025 → 27 11月 2025

丛书

姓名Lecture Notes in Networks and Systems
卷1985 LNNS
ISSN(印刷版)2367-3370
ISSN(电子版)2367-3389

会议

会议2nd International Conference on Advanced Robotics, Control, and Artificial Intelligence, ICARCAI 2025
国家/地区斐济
市Nadi
时期24/11/25 → 27/11/25

学术指纹

探究 'SDHN: Skewness-Driven Hypergraph Networks for Enhanced Localized Multi-robot Coordination' 的科研主题。它们共同构成独一无二的学术指纹。

引用此