A Unified Approach to 3 Basic Challenges in Shared Autonomy

TL;DR

This paper addresses key challenges in shared autonomy, including network reliability, modeling individual human operators, and integrating sliding autonomy into human-machine systems.

Contribution

It presents a unified approach that tackles three fundamental challenges in shared autonomy, enhancing system robustness and personalization.

Findings

Effective handling of unreliable network conditions

Modeling of individual human operators rather than averages

Natural integration of sliding autonomy mechanisms

Abstract

We discuss some of the challenges facing shared autonomy. In particular, we explore 1) shared autonomy over unreliable networks, 2) how we can model individual human operators (in contrast to the average of a human operator), and 3) how our approach naturally models and integrates sliding autonomy into the joint human-machine system. We include a Background Section for completeness.