ContactSDF: Signed Distance Functions as Multi-Contact Models for Dexterous Manipulation

TL;DR

ContactSDF introduces a novel approach using signed distance functions to model multi-contact dynamics, enabling efficient learning and real-time control for dexterous manipulation tasks.

Contribution

It presents a differentiable, closed-form multi-contact dynamic model based on SDFs, improving simulation accuracy and control efficiency in manipulation tasks.

Findings

Effective model learning within 2 minutes on hardware

Achieves 30-60Hz real-time control

High-quality dexterous manipulation demonstrated

Abstract

In this paper, we propose ContactSDF, a method that uses signed distance functions (SDFs) to approximate multi-contact models, including both collision detection and time-stepping routines. ContactSDF first establishes an SDF using the supporting plane representation of an object for collision detection, and then uses the generated contact dual cones to build a second SDF for time-stepping prediction of the next state. Those two SDFs create a differentiable and closed-form multi-contact dynamic model for state prediction, enabling efficient model learning and optimization for contact-rich manipulation. We perform extensive simulation experiments to show the effectiveness of ContactSDF for model learning and real-time control of dexterous manipulation. We further evaluate the ContactSDF on a hardware Allegro hand for on-palm reorientation tasks. Results show with around 2 minutes of learning on hardware, the ContactSDF achieves high-quality dexterous manipulation at a frequency of 30-60Hz. Project page https://yangwen-1102.github.io/contactsdf.github.io/