Stable Motion Primitives via Imitation and Contrastive Learning

TL;DR

This paper introduces a novel contrastive learning approach combined with imitation learning to train neural networks for stable, goal-reaching robot motions, ensuring stability without restricting network structure, validated on datasets and real robots.

Contribution

The paper proposes a new contrastive loss for stability in imitation learning, allowing arbitrary neural network structures to learn complex, stable robot motions.

Findings

Successfully learned stable motions in 2D and 4D datasets.

Validated on a real robot with 3D, 4D, and 6D motions.

Achieved high accuracy in complex motion tasks.

Abstract

Learning from humans allows non-experts to program robots with ease, lowering the resources required to build complex robotic solutions. Nevertheless, such data-driven approaches often lack the ability to provide guarantees regarding their learned behaviors, which is critical for avoiding failures and/or accidents. In this work, we focus on reaching/point-to-point motions, where robots must always reach their goal, independently of their initial state. This can be achieved by modeling motions as dynamical systems and ensuring that they are globally asymptotically stable. Hence, we introduce a novel Contrastive Learning loss for training Deep Neural Networks (DNN) that, when used together with an Imitation Learning loss, enforces the aforementioned stability in the learned motions. Differently from previous work, our method does not restrict the structure of its function approximator, enabling its use with arbitrary DNNs and allowing it to learn complex motions with high accuracy. We validate it using datasets and a real robot. In the former case, motions are 2 and 4 dimensional, modeled as first- and second-order dynamical systems. In the latter, motions are 3, 4, and 6 dimensional, of first and second order, and are used to control a 7DoF robot manipulator in its end effector space and joint space. More details regarding the real-world experiments are presented in: \url{https://youtu.be/OM-2edHBRfc}.