让四足机器人用后腿走路，前腿自由干活，还能抗干扰。
Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
- 后腿行走+前腿操作，不牺牲运动能力。
- 动态调整风险偏好，训练更稳定，性能优于基线。
- 真实机器人实测，能推车、探障碍、运货，抗扰性强。
四足机器人进行运动-操作协同可拓展应用范围，但将腿用于操作常影响移动性能，而加装机械臂又增加系统复杂性。为此，本文提出让四足机器人采用双足行走模式，从而释放前腿进行多样化环境交互。我们设计了一种风险自适应分布强化学习框架，用于在高不稳定性下以后腿行走的四足机器人，平衡最坏情况下的保守性与最优性能。训练中，根据回报分布系数变异（CV）动态调整风险偏好。仿真实验显示本方法显著优于基线。真实世界部署于Unitree Go2机器人，成功完成推车、探测障碍物和负载运输等任务，表现出对复杂动力学和外部扰动的鲁棒性。
原文摘要 · Abstract (English)
Loco-manipulation of quadrupedal robots has broadened robotic applications, but using legs as manipulators often compromises locomotion, while mounting arms complicates the system. To mitigate this issue, we introduce bipedalism for quadrupedal robots, thus freeing the front legs for versatile interactions with the environment. We propose a risk-adaptive distributional Reinforcement Learning (RL) framework designed for quadrupedal robots walking on their hind legs, balancing worst-case conservativeness with optimal performance in this inherently unstable task. During training, the adaptive risk preference is dynamically adjusted based on the uncertainty of the return, measured by the coefficient of variation of the estimated return distribution. Extensive experiments in simulation show our method's superior performance over baselines. Real-world deployment on a Unitree Go2 robot further demonstrates the versatility of our policy, enabling tasks like cart pushing, obstacle probing, and payload transport, while showcasing robustness against challenging dynamics and 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。