Learning Efficient Flocking Control based on Gibbs Random Fields

2025-02-05 · Dengyu Zhang, Chenghao, Feng Xue, Qingrui Zhang

Flocking control is essential for multi-robot systems in diverse applications, yet achieving efficient flocking in congested environments poses challenges regarding computation burdens, performance optimality, and motion safety. This paper addresses these challenges through a multi-agent reinforcement learning (MARL) framework built on Gibbs Random Fields (GRFs). With GRFs, a multi-robot system is represented by a set of random variables conforming to a joint probability distribution, thus offering a fresh perspective on flocking reward design. A decentralized training and execution mechanism, which enhances the scalability of MARL concerning robot quantity, is realized using a GRF-based credit assignment method. An action attention module is introduced to implicitly anticipate the motion intentions of neighboring robots, consequently mitigating potential non-stationarity issues in MARL. The proposed framework enables learning an efficient distributed control policy for multi-robot systems in challenging environments with success rate around $99\%$, as demonstrated through thorough comparisons with state-of-the-art solutions in simulations and experiments. Ablation studies are also performed to validate the efficiency of different framework modules.

📄 PDF Abstract BibTeX arXiv:2502.02984

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control

2022-09-17 · Yunbo Qiu, Yue Jin, Jian Wang, Xudong Zhang

Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Flocking control against the malicious agent

2023-08-08 · Chencheng Zhang, Hao Yang, Bin Jiang, Ming Cao

This paper investigates the flocking control of a swarm with a malicious agent that falsifies its controller parameters to cause collision, division, and escape of agents in the swarm. A novel geometric flocking conditio…

A new class of Markov random fields enabling lightweight sampling

2025-11-04 · Jean-Baptiste Courbot, Hugo Gangloff, Bruno Colicchio arxiv

This work addresses the problem of efficient sampling of Markov random fields (MRF). The sampling of Potts or Ising MRF is most often based on Gibbs sampling, and is thus computationally expensive. We consider in this wo…

Computational Efficiency

Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion

2013-12-01 · NeurIPS 2013 12 · Nguyen Viet Cuong, Wee Sun Lee, Nan Ye, Kian Ming A. Chai 외

We introduce a new objective function for pool-based Bayesian active learning with probabilistic hypotheses. This objective function, called the policy Gibbs error, is the expected error rate of a random classifier drawn…

Active Learning named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)+2

An Adversarial Approach to Private Flocking in Mobile Robot Teams

2019-09-23 · Hehui Zheng, Jacopo Panerati, Giovanni Beltrame, Amanda Prorok

Privacy is an important facet of defence against adversaries. In this letter, we introduce the problem of private flocking. We consider a team of mobile robots flocking in the presence of an adversary, who is able to obs…

Motion Planning