Task-Adaptive Robot Learning from Demonstration with Gaussian Process Models under Replication

TL;DR

This paper introduces a Gaussian Process-based method for robot learning from demonstration that leverages demonstration variations and replications to create adaptable, robust, and computationally efficient manipulation policies.

Contribution

It proposes a novel GP model that incorporates task parameters and exploits demonstration replications to improve adaptability and reduce computational costs in robot learning from demonstration.

Findings

Enhanced adaptability through task parameter integration.

Significant reduction in model fitting computational cost.

Successful application on handwritten letter dataset.

Abstract

Learning from Demonstration (LfD) is a paradigm that allows robots to learn complex manipulation tasks that can not be easily scripted, but can be demonstrated by a human teacher. One of the challenges of LfD is to enable robots to acquire skills that can be adapted to different scenarios. In this paper, we propose to achieve this by exploiting the variations in the demonstrations to retrieve an adaptive and robust policy, using Gaussian Process (GP) models. Adaptability is enhanced by incorporating task parameters into the model, which encode different specifications within the same task. With our formulation, these parameters can be either real, integer, or categorical. Furthermore, we propose a GP design that exploits the structure of replications, i.e., repeated demonstrations with identical conditions within data. Our method significantly reduces the computational cost of model fitting in complex tasks, where replications are essential to obtain a robust model. We illustrate our approach through several experiments on a handwritten letter demonstration dataset.