6-DoF Stability Field via Diffusion Models
This addresses the challenge of generalizable stability reasoning for robot manipulation, moving beyond hand-crafted heuristics, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of generating stable 3D object placements in cluttered robot manipulation scenes, presenting 6-DoFusion, a diffusion model that produces stable poses, and demonstrates improved accuracy in pose estimation and handling novel object classes.
A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning, with limited generalizability beyond a small number of object instances and object interaction patterns. Recent approaches instead learn notions of physical interaction, namely motion prediction, but require supervision in the form of labeled object information or come at the cost of high sample complexity, and do not directly reason over stability or object placement. We present 6-DoFusion, a generative model capable of generating 3D poses of an object that produces a stable configuration of a given scene. Underlying 6-DoFusion is a diffusion model that incrementally refines a randomly initialized SE(3) pose to generate a sample from a learned, context-dependent distribution over stable poses. We evaluate our model on different object placement and stacking tasks, demonstrating its ability to construct stable scenes that involve novel object classes as well as to improve the accuracy of state-of-the-art 3D pose estimation methods.