Learning Context-Adaptive Task Constraints for Robotic Manipulation

TL;DR

This paper introduces a data-driven method for automatically learning and adapting task constraints in robotic manipulation, improving flexibility and accuracy in unseen contexts.

Contribution

It proposes a programming-by-demonstration approach to automatically derive and adapt task constraints for constraint-based controllers in robotic manipulation.

Findings

Outperforms manually specified constraints in reproduction accuracy

Uses probabilistic models to map context to constraints

Validated on three dual-arm manipulation tasks

Abstract

Constraint-based control approaches offer a flexible way to specify robotic manipulation tasks and execute them on robots with many degrees of freedom. However, the specification of task constraints and their associated priorities usually requires a human-expert and often leads to tailor-made solutions for specific situations. This paper presents our recent efforts to automatically derive task constraints for a constraint-based robot controller from data and adapt them with respect to previously unseen situations (contexts). We use a programming-by-demonstration approach to generate training data in multiple variations (context changes) of a given task. From this data we learn a probabilistic model that maps context variables to task constraints and their respective soft task priorities. We evaluate our approach with 3 different dual-arm manipulation tasks on an industrial robot and show that it performs better in terms of reproduction accuracy than constraint-based controllers with manually specified constraints.