One-Shot Manipulation Strategy Learning by Making Contact Analogies

TL;DR

MAGIC is a novel one-shot manipulation learning method that generalizes contact strategies to new objects by combining shape matching and curvature analysis, enabling fast and versatile manipulation in robotics.

Contribution

Introduces MAGIC, a two-stage contact-point matching approach that enhances one-shot manipulation learning with improved speed and generalization capabilities.

Findings

Outperforms existing methods in manipulation tasks

Achieves faster runtime and better generalization

Successfully applies to scooping, hanging, and hooking tasks

Abstract

We present a novel approach, MAGIC (manipulation analogies for generalizable intelligent contacts), for one-shot learning of manipulation strategies with fast and extensive generalization to novel objects. By leveraging a reference action trajectory, MAGIC effectively identifies similar contact points and sequences of actions on novel objects to replicate a demonstrated strategy, such as using different hooks to retrieve distant objects of different shapes and sizes. Our method is based on a two-stage contact-point matching process that combines global shape matching using pretrained neural features with local curvature analysis to ensure precise and physically plausible contact points. We experiment with three tasks including scooping, hanging, and hooking objects. MAGIC demonstrates superior performance over existing methods, achieving significant improvements in runtime speed and generalization to different object categories. Website: https://magic-2024.github.io/ .