Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation

TL;DR

This paper investigates nonlinear action maps for data-driven teleoperation, finding minimal advantages over linear models and highlighting the need for further research in data augmentation and human behavior analysis.

Contribution

Proposes end-to-end nonlinear action maps with odd function properties for teleoperation, but shows limited practical benefits over existing linear models.

Findings

Nonlinear odd functions behave linearly in most control space.

Minimal advantages of nonlinear maps over linear models in experiments.

Future improvements may require data augmentation and human behavior analysis.

Abstract

As robots become more common for both able-bodied individuals and those living with a disability, it is increasingly important that lay people be able to drive multi-degree-of-freedom platforms with low-dimensional controllers. One approach is to use state-conditioned action mapping methods to learn mappings between low-dimensional controllers and high DOF manipulators -- prior research suggests these mappings can simplify the teleoperation experience for users. Recent works suggest that neural networks predicting a local linear function are superior to the typical end-to-end multi-layer perceptrons because they allow users to more easily undo actions, providing more control over the system. However, local linear models assume actions exist on a linear subspace and may not capture nuanced actions in training data. We observe that the benefit of these mappings is being an odd function concerning user actions, and propose end-to-end nonlinear action maps which achieve this property. Unfortunately, our experiments show that such modifications offer minimal advantages over previous solutions. We find that nonlinear odd functions behave linearly for most of the control space, suggesting architecture structure improvements are not the primary factor in data-driven teleoperation. Our results suggest other avenues, such as data augmentation techniques and analysis of human behavior, are necessary for action maps to become practical in real-world applications, such as in assistive robotics to improve the quality of life of people living with w disability.