强化学习
机器人
计算机科学
人工智能
反事实思维
群机器人
机器人学习
进化机器人
软件
控制(管理)
动作选择
学习迁移
群体行为
主动学习(机器学习)
机器学习
比例(比率)
过度拟合
工作(物理)
机器人学
控制工程
执行机构
汽车工业
机器人控制
人机交互
作者
Ilyes Gharbi,Miquel Kegeleirs,Guillermo Legarda Herranz,Jeanne Szpirer,Ken Hasselmann,Mauro Birattari
出处
期刊:Science robotics
[American Association for the Advancement of Science]
日期:2026-10-21
卷期号:11 (119): eadw4624-eadw4624
标识
DOI:10.1126/scirobotics.adw4624
摘要
Reinforcement learning offers a powerful framework for automatically generating control policies for robot swarms, yet its application to physical multirobot systems has been limited by the simulation-to-reality gap. Despite substantial advances in multiagent reinforcement learning, systematic demonstrations of gradient-based sim-to-real transfer to physical robot swarms remain scarce. Most work remains confined to simulation, and the few real-robot demonstrations lack evaluation across multiple runs and tasks. We show that this barrier can be overcome by embedding structural constraints into policy learning. We introduce attention-based counterfactual policy gradients for behavior selection in robot swarms (SwarmACB), a multiagent actor-critic method in which robots arbitrate among predefined behavior modules-reactive sensorimotor routines such as phototaxis or aggregation-rather than learning low-level motor commands. This architectural choice reduces the variance of learned solutions, which we argue mitigates overfitting to simulation artifacts. Through systematic evaluation on five collective missions using 20 physical e-puck robots (250 real-robot runs), we demonstrate that SwarmACB transfers successfully from simulation to reality, substantially outperforming continuous-action baselines. By progressively constraining policy architecture, perception, and model capacity, we show that smaller, structured policies transfer more reliably than large, unconstrained ones. These findings challenge the assumption that scale is necessary for successful transfer, suggesting instead that principled structural design enables reinforcement learning to produce control software for robot swarms that is both learned automatically and directly deployable in the physical world.
科研通智能强力驱动
Strongly Powered by AbleSci AI