Imitating Human Search Strategies for Assembly

TL;DR

This paper introduces a Learning from Demonstration approach enabling robots to imitate human search strategies for assembly tasks, improving success in alignment failures caused by position uncertainty.

Contribution

It proposes a novel method combining learned dynamics and exploration distributions to teach robots effective search strategies from few human demonstrations.

Findings

Successfully learned search strategies with minimal demonstrations

Effective in 2D peg-in-hole and 3D socket tasks

Improved search success rates in experiments

Abstract

We present a Learning from Demonstration method for teaching robots to perform search strategies imitated from humans in scenarios where alignment tasks fail due to position uncertainty. The method utilizes human demonstrations to learn both a state invariant dynamics model and an exploration distribution that captures the search area covered by the demonstrator. We present two alternative algorithms for computing a search trajectory from the exploration distribution, one based on sampling and another based on deterministic ergodic control. We augment the search trajectory with forces learnt through the dynamics model to enable searching both in force and position domains. An impedance controller with superposed forces is used for reproducing the learnt strategy. We experimentally evaluate the method on a KUKA LWR4+ performing a 2D peg-in-hole and a 3D electricity socket task. Results show that the proposed method can, with only few human demonstrations, learn to complete the search task.