From a Single Demonstration to a General Policy for Contact-Rich Manipulation

TL;DR

This paper introduces a novel Learning from Demonstration framework that enables robots to generalize contact-rich manipulation tasks from a single demonstration by leveraging environmental constraints as the core inductive bias.

Contribution

The approach uniquely represents demonstrations as sequences of environmental constraints, separating task structure from instance-specific details to enable one-shot generalization.

Findings

Achieved over 90% success rate on seven real-world tasks.

Demonstrated effective generalization across object poses and geometries.

Validated the importance of environmental constraints for efficient learning.

Abstract

We present a Learning from Demonstration (LfD) framework that achieves one-shot generalization in multi-stage, contact-rich manipulation tasks. Central to our approach is the utilization of environmental constraints as the inductive bias. By representing a demonstration as a sequence of behaviors that exploit environmental constraints, the robot separates task-general structure -- the constraint types and their transitions -- from instance-specific details such as exact demonstration trajectories, poses, and local geometries. Our four-stage pipeline builds a complete policy on this representation: the robot first abstracts a single demonstration into environmental-constraint primitives, then disambiguates them through self-guided exploration, next assimilates targeted human corrections that handle out-of-distribution variations, and finally recovers the abstracted-away details online through compliant interaction. Because the resulting policy follows constraints rather than mimics trajectories, it generalizes across object poses, local geometries, and unmodeled contact dynamics. We validate our approach on seven real-world multi-stage contact-rich manipulation tasks and achieve over 90% success. These extensive experimental results establish environmental constraints as fundamental building blocks for efficient generalization in learning from demonstration.