arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07409cs.ROcs.AI
收藏

鲁棒机器人步行器:学习在微小陷阱上实现敏捷运动

Robust Robot Walker: Learning Agile Locomotion over Tiny Traps

Tsinghua University(清华大学);Shanghai Qi Zhi Institute(上海期智研究院);University of Pennsylvania(宾夕法尼亚大学)

Shaoting Zhu, Runhan Huang, Linzhan Mou, Hang Zhao

AI总结:

针对四足机器人穿越微小陷阱的需求,提出仅靠本体感受输入、含接触编码器与分类头的两阶段训练框架及定制奖励函数,构建新基准,实验验证了方法的有效性与鲁棒性。

摘要:

四足机器人在实际应用中必须具备鲁棒的行走能力。本研究提出了一种新方法,可使四足机器人通过各类小型障碍物,即“微小陷阱”。现有方法通常依赖外部感知传感器,这类传感器在检测此类微小陷阱时可靠性不足。为克服这一局限,我们的方法仅采用本体感受输入。我们提出了一个两阶段训练框架,该框架融合接触编码器与分类头,用于学习不同陷阱的隐式表征。此外,我们设计了一组定制化奖励函数,以提升目标跟踪任务的训练稳定性与部署便捷性。为助力后续研究,我们设计了一个全新的微小陷阱任务基准。仿真与真实环境下的大量实验均验证了该方法的有效性与鲁棒性。项目页面:https://robust-robot-walker.github.io/

英文摘要:

Quadruped robots must exhibit robust walking capabilities in practical applications. In this work, we propose a novel approach that enables quadruped robots to pass various small obstacles, or "tiny traps". Existing methods often rely on exteroceptive sensors, which can be unreliable for detecting such tiny traps. To overcome this limitation, our approach focuses solely on proprioceptive inputs. We introduce a two-stage training framework incorporating a contact encoder and a classification head to learn implicit representations of different traps. Additionally, we design a set of tailored reward functions to improve both the stability of training and the ease of deployment for goal-tracking tasks. To benefit further research, we design a new benchmark for tiny trap task. Extensive experiments in both simulation and real-world settings demonstrate the effectiveness and robustness of our method. Project Page: https://robust-robot-walker.github.io/

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。

↑