环游世界：270克连续旋转四足机器人的统一学习运动控制
Around the World: Unified Learned Locomotion on a 270 g Continuous-Rotation Quadruped
浏览论文内容
中文总结 AI 辅助
针对270克连续旋转四足机器人，提出姿态条件化强化学习策略，实现直立、倒立行走与着陆恢复的统一控制，并在硬件上验证了高精度速度跟踪与鲁棒恢复能力。
中文摘要 AI 辅助
闭环学习运动控制在商用四足机器人上已得到广泛应用，但在亚千克尺度上仍不常见。连续旋转腿部使270克的MiNI-Q四足机器人能够接触到身体两侧的支撑构型。我们利用这一运动范围，采用单一姿态条件化的强化学习策略，该策略完全在机载运行。环面$T^8$上的连续关节空间参考及其重力条件化变换，使得直立行走、倒立行走和着陆恢复之间无需状态机或相位切换即可实现转换。协调的姿态与释放课程训练了这一行为系列；已识别的驱动、跨引擎验证和嵌入式执行支持硬件迁移。该子10万参数网络以0.037米/秒（直立）和0.050米/秒（倒立）的均方根误差跟踪前进速度，在30次释放试验中24次恢复行走，并在四种室内表面上使用四种可互换的脚部几何形状运行。硬件实验和模拟消融将这些能力与利用平台运动范围的表示、条件化和训练选择联系起来。演示视频和补充材料可在项目网站上获取：此https URL。
英文摘要
Closed-loop learned locomotion is established on commercial quadrupeds but remains uncommon at the sub-kilogram scale. Continuous-rotation legs give MiNI-Q, a 270 g quadruped, access to supporting configurations on either side of the body. We exploit this range with a single posture-conditioned reinforcement-learning policy that runs entirely onboard. A continuous joint-space reference on the torus $T^8$ and its gravity-conditioned transformation connect upright walking, inverted walking, and landing recovery without state machines or phase switching. Coordinated posture and release curricula train this behavior family; identified actuation, cross-engine validation, and embedded execution support hardware transfer. The same sub-100k-parameter network tracks forward velocity with RMSE of 0.037 m/s upright and 0.050 m/s inverted, resumes walking in 24 of 30 release trials, and operates with four interchangeable foot geometries across four indoor surfaces. Hardware experiments and simulation ablations connect these capabilities to the representation, conditioning, and training choices that exploit the platform's motion range. Demonstration videos and supplementary material are available on the project website: https://submissionreview.github.io/around-the-world/.
发表机构
- University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。
