SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy
This addresses a significant problem in robotics for tasks requiring precise deformation control, such as manufacturing or art, and is not incremental as it claims to be the first real-world method.
The paper tackles the challenge of robotic manipulation of 3D deformable objects like clay by proposing SculptDiff, a goal-conditioned diffusion-based imitation learning framework that learns sculpting policies from human demonstrations, achieving the first real-world method for this task.
Manipulating deformable objects remains a challenge within robotics due to the difficulties of state estimation, long-horizon planning, and predicting how the object will deform given an interaction. These challenges are the most pronounced with 3D deformable objects. We propose SculptDiff, a goal-conditioned diffusion-based imitation learning framework that works with point cloud state observations to directly learn clay sculpting policies for a variety of target shapes. To the best of our knowledge this is the first real-world method that successfully learns manipulation policies for 3D deformable objects. For sculpting videos and access to our dataset and hardware CAD models, see the project website: https://sites.google.com/andrew.cmu.edu/imitation-sculpting/home