Tool as Embodiment for Recursive Manipulation
Yuki Noguchi, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu

TL;DR
This paper introduces Tool-As-Embodiment (TAE), a unified framework enabling robots to recursively manipulate objects and tools by sharing experiences across different embodiments, leading to improved performance and generalization.
Contribution
The paper presents a novel parameterization that treats hand-object and tool-object interactions uniformly, allowing recursive manipulation policies that leverage shared experiences across embodiments.
Findings
Higher performance than separate policies for grasping and pushing.
Unified policy can be trained across different tool-enabled embodiments.
Framework enables recursive manipulation using a single policy.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning · Reinforcement Learning in Robotics · Robotic Locomotion and Control
