Tactile Probabilistic Contact Dynamics Estimation of Unknown Objects

TL;DR

This paper introduces a novel method combining neural network geometry representation and particle filtering to rapidly estimate contact dynamics of unknown objects in partially known environments, with active exploration to improve efficiency.

Contribution

It presents a new formulation for contact dynamics estimation as joint geometry and parameter estimation using DeepSDF and particle filters, coupled with active exploration.

Findings

Accurate contact dynamics estimation with fewer than 30 exploration moves.

Effective in both simulation and physical experiments.

Handles unknown objects in partially known environments.

Abstract

We study the problem of rapidly identifying contact dynamics of unknown objects in partially known environments. The key innovation of our method is a novel formulation of the contact dynamics estimation problem as the joint estimation of contact geometries and physical parameters. We leverage DeepSDF, a compact and expressive neural-network-based geometry representation over a distribution of geometries, and adopt a particle filter to estimate both the geometries in contact and the physical parameters. In addition, we couple the estimator with an active exploration strategy that plans information-gathering moves to further expedite online estimation. Through simulation and physical experiments, we show that our method estimates accurate contact dynamics with fewer than 30 exploration moves for unknown objects touching partially known environments.