Continual Learning from Demonstration of Robotics Skills

TL;DR

This paper introduces a continual learning method for robotic skills from demonstration using hypernetworks and neural ODEs, enabling robots to learn new tasks without forgetting previous ones, demonstrated on real robot datasets.

Contribution

The paper presents a novel continual learning approach for robotics from demonstration using hypernetworks and neural ODEs, outperforming existing methods and introducing new datasets.

Findings

Hypernetworks outperform state-of-the-art continual learning methods.

Effective learning of long sequences of robotic tasks without data storage.

Successful real-world robot experiments with changing positions and orientations.

Abstract

Methods for teaching motion skills to robots focus on training for a single skill at a time. Robots capable of learning from demonstration can considerably benefit from the added ability to learn new movement skills without forgetting what was learned in the past. To this end, we propose an approach for continual learning from demonstration using hypernetworks and neural ordinary differential equation solvers. We empirically demonstrate the effectiveness of this approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations. Our results show that hypernetworks outperform other state-of-the-art continual learning approaches for learning from demonstration. In our experiments, we use the popular LASA benchmark, and two new datasets of kinesthetic demonstrations collected with a real robot that we introduce in this paper called the HelloWorld and RoboTasks datasets. We evaluate our approach on a physical robot and demonstrate its effectiveness in learning real-world robotic tasks involving changing positions as well as orientations. We report both trajectory error metrics and continual learning metrics, and we propose two new continual learning metrics. Our code, along with the newly collected datasets, is available at https://github.com/sayantanauddy/clfd.