CoLF: 为视觉-语言引导的多机器人协作运输学习一致的领导者-跟随者策略
CoLF: Learning Consistent Leader-Follower Policies for Vision-Language-Guided Multi-Robot Cooperative Transport
AI总结：
CoLF 通过不对称策略和互信息训练目标，为多机器人协作运输提供稳定领导者-跟随者角色区分的强化学习框架。
摘要：
在本研究中，我们解决了视觉-语言引导的多机器人协作运输问题，其中每个机器人通过 onboard 相机观测来接地自然语言指令。在这种去中心化设置中，一个关键挑战是机器人之间的感知不一致，其中视角差异和语言歧义可能导致不一致的解释并降低协作运输的效率。为了解决这个问题，我们采用了一种依赖的领导者-跟随者设计，其中一台机器人作为领导者，另一台作为跟随者。尽管这种领导者-跟随者结构看起来很简单，但使用独立和对称的智能体进行学习往往会导致对称或不稳定的行为，而没有显式的归纳偏置。为了解决这一挑战，我们提出了 Consistent Leader-Follower（CoLF），一种用于稳定领导者-跟随者角色区分的多智能体强化学习（MARL）框架。CoLF 包含两个关键组成部分：（1）一种不对称的策略设计，用于诱导领导者-跟随者角色区分，以及（2）一种基于互信息的训练目标，该目标最大化变分下界，鼓励跟随者从其本地观察预测领导者的行为。领导者和跟随者策略在集中训练和去中心化执行（CTDE）框架下联合优化，以平衡任务执行和一致的协作行为。我们通过使用两台四足机器人在仿真和真实机器人实验中验证了 CoLF。演示视频可在 https://sites.google.com/view/colf/ 上找到。
英文摘要：
In this study, we address vision-language-guided multi-robot cooperative transport, where each robot grounds natural-language instructions from onboard camera observations. A key challenge in this decentralized setting is perceptual misalignment across robots, where viewpoint differences and language ambiguity can yield inconsistent interpretations and degrade cooperative transport. To mitigate this problem, we adopt a dependent leader-follower design, where one robot serves as the leader and the other as the follower. Although such a leader-follower structure appears straightforward, learning with independent and symmetric agents often yields symmetric or unstable behaviors without explicit inductive biases. To address this challenge, we propose Consistent Leader-Follower (CoLF), a multi-agent reinforcement learning (MARL) framework for stable leader-follower role differentiation. CoLF consists of two key components: (1) an asymmetric policy design that induces leader-follower role differentiation, and (2) a mutual-information-based training objective that maximizes a variational lower bound, encouraging the follower to predict the leader's action from its local observation. The leader and follower policies are jointly optimized under the centralized training and decentralized execution (CTDE) framework to balance task execution and consistent cooperative behaviors. We validate CoLF in both simulation and real-robot experiments using two quadruped robots. The demonstration video is available at https://sites.google.com/view/colf/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
