Diffusion-Informed Probabilistic Contact Search for Multi-Finger Manipulation

TL;DR

This paper introduces DIPS, a novel method combining diffusion models, A* search, and learned discriminators to improve contact sequence planning in multi-finger manipulation, outperforming prior data-driven approaches.

Contribution

The paper presents a new diffusion-informed planning method that integrates classical search with learned models and variability reasoning for better manipulation planning.

Findings

Outperforms ablations without variability reasoning.

Successfully transfers from simulation to real-world tasks.

Achieves better contact sequences than training data in multiple tasks.

Abstract

Planning contact-rich interactions for multi-finger manipulation is challenging due to the high-dimensionality and hybrid nature of dynamics. Recent advances in data-driven methods have shown promise, but are sensitive to the quality of training data. Combining learning with classical methods like trajectory optimization and search adds additional structure to the problem and domain knowledge in the form of constraints, which can lead to outperforming the data on which models are trained. We present Diffusion-Informed Probabilistic Contact Search (DIPS), which uses an A* search to plan a sequence of contact modes informed by a diffusion model. We train the diffusion model on a dataset of demonstrations consisting of contact modes and trajectories generated by a trajectory optimizer given those modes. In addition, we use a particle filter-inspired method to reason about variability in diffusion sampling arising from model error, estimating likelihoods of trajectories using a learned discriminator. We show that our method outperforms ablations that do not reason about variability and can plan contact sequences that outperform those found in training data across multiple tasks. We evaluate on simulated tabletop card sliding and screwdriver turning tasks, as well as the screwdriver task in hardware to show that our combined learning and planning approach transfers to the real world.