四类强化学习方法在真实双摆系统上对比，验证其抗扰与实机迁移能力
Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition
- 四种强化学习算法用于控制具混沌特性的欠驱动双摆系统
- 实机测试中各方法在抗干扰和从仿真到现实的迁移上表现各异
- 为机器人动态控制提供真实场景下的性能评估参考
在机器人领域，从经典规划、最优控制到强化学习（RL）等不同方法被开发并借鉴，以实现多样任务中的可靠控制。为了清晰理解各类方法的优势与局限，并评估其在真实机器人场景中的适用性，进行仿真与实机双重基准测试至关重要。为此，2024年IROS会议举办了第二届‘AI奥运会：RealAIGym’竞赛，旨在评估不同控制器解决具有混沌动力学的欠驱动双摆系统动态控制问题的能力。本文介绍了参赛团队提交的四种强化学习方法，展示了它们在真实双摆系统上的上摆任务表现，依据多种标准进行评估，并讨论了从仿真到真实硬件的迁移能力及对外部干扰的鲁棒性。
原文摘要 · Abstract (English)
In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and their applicability in real world robotic scenarios is it important to benchmark and compare their performances not only in a simulation but also on real hardware. The '2nd AI Olympics with RealAIGym' competition was held at the IROS 2024 conference to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double pendulum system with chaotic dynamics. This paper describes the four different RL methods submitted by the participating teams, presents their performance in the swing-up task on a real double pendulum, measured against various criteria, and discusses their transferability from simulation to real hardware and their robustness to external disturbances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。