Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design
This work addresses the challenge of rapid, data-driven robot mechanism design for manipulation tasks, offering a novel framework that is incremental in its approach.
The paper tackles the problem of generating sensor-less robot manipulator designs for specific tasks without task-specific training, achieving an average success rate improvement of 31.5% over optimization-based baselines and 45.3% over unguided diffusion baselines, with designs generated in under 0.8 seconds.
We present Dynamics-Guided Diffusion Model (DGDM), a data-driven framework for generating task-specific manipulator designs without task-specific training. Given object shapes and task specifications, DGDM generates sensor-less manipulator designs that can blindly manipulate objects towards desired motions and poses using an open-loop parallel motion. This framework 1) flexibly represents manipulation tasks as interaction profiles, 2) represents the design space using a geometric diffusion model, and 3) efficiently searches this design space using the gradients provided by a dynamics network trained without any task information. We evaluate DGDM on various manipulation tasks ranging from shifting/rotating objects to converging objects to a specific pose. Our generated designs outperform optimization-based and unguided diffusion baselines relatively by 31.5% and 45.3% on average success rate. With the ability to generate a new design within 0.8s, DGDM facilitates rapid design iteration and enhances the adoption of data-driven approaches for robot mechanism design. Qualitative results are best viewed on our project website https://dgdm-robot.github.io/.