ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking
ECO:基于强化学习的人形机器人能量受限优化
机构 * State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI)(通用人工智能国家重点实验室,北京通用人工智能研究院(BIGAI)) ; Department of Automation, Tsinghua University(自动化系,清华大学) ; Department of Automation, University of Science and Technology of China(自动化系,中国科学技术大学) ; Department of Computer Science, Harbin Institute of Technology(计算机科学系,哈尔滨工业大学) ; Institute for Artificial Intelligence and School of Artificial Intelligence, Peking University(人工智能研究院和人工智能学院,北京大学)
AI总结 ECO通过将能量指标作为约束而非奖励,提升人形机器人行走的能效与稳定性。
Comments IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING. PREPRINT VERSION. ACCEPTED FEB, 2026