VolleyBots: 多无人机乒乓球竞技测试平台，结合运动控制与战略博弈
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
AI总结：
VolleyBots通过结合运动控制与战略博弈，测试多无人机乒乓球竞技，展示了强化学习在复杂任务中的应用与潜力。
摘要：
机器人体育以其明确的目标、显式的规则和动态互动而著称，为展示具身智能提供了理想场景。本文介绍了VolleyBots，一种新的机器人体育测试平台，其中多个无人机在乒乓球运动中合作与竞争，受物理动力学影响。VolleyBots在一个统一平台上集成了三个特征：竞争与合作的游戏玩法、回合制互动结构以及敏捷的3D机动。这些交织的特征产生了一个结合运动控制和战略博弈的复杂问题，没有可用的专家演示。我们提供了一套全面的任务，从单无人机训练到多无人机合作与竞争任务，并伴有代表性的强化学习（RL）、多智能体强化学习（MARL）和博弈论算法的基线评估。模拟结果显示，在单体任务中，在线强化学习方法优于离线方法，但在结合运动控制和战略博弈的复杂任务中，两种方法都表现不佳。我们还设计了一种分层策略，在3 vs 3任务中以69.5%的胜率对抗最强基线，展示了其在低层控制与高层策略之间复杂互动方面的潜力。为了突出VolleyBots的仿真到现实的潜力，我们进一步展示了在现实世界无人机上部署完全在仿真中训练的策略的零样本部署。
英文摘要：
Robot sports, characterized by well-defined objectives, explicit rules, and dynamic interactions, present ideal scenarios for demonstrating embodied intelligence. In this paper, we present VolleyBots, a novel robot sports testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics. VolleyBots integrates three features within a unified platform: competitive and cooperative gameplay, turn-based interaction structure, and agile 3D maneuvering. These intertwined features yield a complex problem combining motion control and strategic play, with no available expert demonstrations. We provide a comprehensive suite of tasks ranging from single-drone drills to multi-drone cooperative and competitive tasks, accompanied by baseline evaluations of representative reinforcement learning (RL), multi-agent reinforcement learning (MARL) and game-theoretic algorithms. Simulation results show that on-policy RL methods outperform off-policy methods in single-agent tasks, but both approaches struggle in complex tasks that combine motion control and strategic play. We additionally design a hierarchical policy which achieves 69.5% win rate against the strongest baseline in the 3 vs 3 task, demonstrating its potential for tackling the complex interplay between low-level control and high-level strategy. To highlight VolleyBots' sim-to-real potential, we further demonstrate the zero-shot deployment of a policy trained entirely in simulation on real-world drones.
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。
