Abstract
Humans and many animals exhibit a robust capability to manipulate diverse objects, often directly with their bodies and sometimes indirectly with tools. Such flexibility is likely enabled by the fundamental consistency in underlying physics of object manipulation such as contacts and force closures. Inspired by viewing tools as extensions of our bodies, we present Tool-As-Embodiment (TAE), a parameterization for tool-based manipulation policies that treat hand-object and tool-object interactions in the same representation space. The result is a single policy that can be applied recursively on robots to use end effectors to manipulate objects, and use objects as tools, i.e. new end-effectors, to manipulate other objects. By sharing experiences across different embodiments for grasping or pushing, our policy exhibits higher performance than if separate policies were trained. Our framework could utilize all experiences from different resolutions of tool-enabled embodiments to a single generic policy for each manipulation skill. Videos at https://sites.google.com/view/recursivemanipulation
Tatsuya Matsushima
Project Researcher
My research interests include robot learning, robot system, and XR.
Yutaka Matsuo
Professor
Shixiang Shane Gu
Visiting Associate Professor
Shixiang Shane Gu is a Senior Research Scientist at Google Brain, and a Visiting Associate Professor at the University of Tokyo, with research interests around (1) algorithmic problems in deep learning, reinforcement learning, robotics, and probabilistic machine learning, and (2) mastering a universal physics prior for continuous control. website