A Structured Prediction Approach for Robot Imitation Learning

TL;DR

This paper introduces a structured prediction framework for robot imitation learning that handles complex trajectory spaces and adapts to changing conditions, outperforming existing methods in accuracy and efficiency.

Contribution

It presents a novel structured prediction approach utilizing f-divergence-based loss functions for learning and adapting manifold trajectories in robot imitation learning.

Findings

Outperforms state-of-the-art methods in trajectory reproduction and adaptation

Effective in learning manifold trajectories in real-world tasks

Demonstrates improved accuracy and efficiency in experiments

Abstract

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework.