Object Rearrangement Using Learned Implicit Collision Functions
This work provides a faster and more accurate collision prediction method for robots performing rearrangement tasks in cluttered environments, particularly when object models are unavailable.
This paper addresses the challenge of robotic object rearrangement in the absence of object models by proposing a learned implicit collision model. This model predicts collisions for 6DOF object poses using scene and query object point clouds, achieving a 9.8% higher accuracy and being 75x faster than baselines on simulated collision queries.
Robotic object rearrangement combines the skills of picking and placing objects. When object models are unavailable, typical collision-checking models may be unable to predict collisions in partial point clouds with occlusions, making generation of collision-free grasping or placement trajectories challenging. We propose a learned collision model that accepts scene and query object point clouds and predicts collisions for 6DOF object poses within the scene. We train the model on a synthetic set of 1 million scene/object point cloud pairs and 2 billion collision queries. We leverage the learned collision model as part of a model predictive path integral (MPPI) policy in a tabletop rearrangement task and show that the policy can plan collision-free grasps and placements for objects unseen in training in both simulated and physical cluttered scenes with a Franka Panda robot. The learned model outperforms both traditional pipelines and learned ablations by 9.8% in accuracy on a dataset of simulated collision queries and is 75x faster than the best-performing baseline. Videos and supplementary material are available at https://research.nvidia.com/publication/2021-03_Object-Rearrangement-Using.