A Comparison of Imitation Learning Algorithms for Bimanual Manipulation

TL;DR

This paper compares various imitation learning algorithms for complex bimanual manipulation tasks, analyzing their strengths and limitations in terms of hyperparameter sensitivity, data efficiency, and performance in high-precision environments.

Contribution

It provides a comprehensive evaluation of prominent imitation learning algorithms on a complex bimanual task, highlighting their relative advantages and challenges.

Findings

Imitation learning can effectively solve complex bimanual manipulation tasks.

Algorithms differ significantly in robustness to environmental and hyperparameter variations.

Training efficiency and ease of use vary across algorithms.

Abstract

Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision industry-inspired environments. In this work, we demonstrate the limitations and benefits of prominent imitation learning approaches and analyze their capabilities regarding these properties. We evaluate each algorithm on a complex bimanual manipulation task involving an over-constrained dynamics system in a setting involving multiple contacts between the manipulated object and the environment. While we find that imitation learning is well suited to solve such complex tasks, not all algorithms are equal in terms of handling environmental and hyperparameter perturbations, training requirements, performance, and ease of use. We investigate the empirical influence of these key characteristics by employing a carefully designed experimental procedure and learning environment. Paper website: https://bimanual-imitation.github.io/