点击次数：

所属单位：控制科学与工程学院

论文名称：A Deep Reinforcement Learning Approach Using Asymmetric Self-Play for Robust Multirobot Flocking

发表刊物：IEEE Transactions on Industrial Informatics

关键字：RobotsAdaptation modelsTrainingCollision avoidanceNavigationMulti-robot systemsUncertaintyRobot sensing systemsRobustnessVehicle dynamicsAdversarial trainingflockingmultiagent deep reinforcement learning (MADRL)autonomous vehicles

摘要：Flocking control, as an essential approach for survivable navigation of multirobot systems, has been widely applied in fields, such as logistics, service delivery, and search and rescue. However, realistic environments are typically complex, dynamic, and even aggressive, posing considerable threats to the safety of flocking robots. In this article, based on deep reinforcement learning, an Asymmetric Self-play-empowered Flocking Control framework is proposed to address this concern. Specifically, the flocking robots are trained concurrently with learnable adversarial interferers to stimulate the intelligence of the flocking strategy. A two-stage self-play training paradigm is developed to improve the robustness and generalization of the model. Furthermore, an auxiliary training module regarding the learning of transition dynamics is designed, dramatically enhancing the adaptability to environmental uncertainties. Feature-level and agent-level attention are implemented for action and value generation, respectively. Both extensive comparative experiments and real-world deployment demonstrate the superiority and practicality of the proposed framework.

第一作者：贾云杰

通讯作者：宋勇

全部作者：程吉禹,Jin Jiong,张伟,Yang X. Simon,Kwong Sam

论文类型：期刊论文

论文编号：1889209004728918017

学科门类：工学

卷号：21

期号：4

页面范围：3266-3275

字数：20

是否译文：否

发表时间：2025-01

收录刊物：SCI

发布时间：2025-11-29