Mixed-Initiative variable autonomy for remotely operated mobile robots

TL;DR

This paper introduces an Expert-guided Mixed-Initiative Control Switcher (EMICS) for remotely operated robots, demonstrating improved navigation performance and operator workload management through experiments in simulated and real disaster response scenarios.

Contribution

The paper presents a novel EMICS framework that enables dynamic switching between autonomy levels, with empirical evaluation highlighting its advantages over traditional control modes.

Findings

Mixed-Initiative systems outperform single-mode systems in navigation tasks.

MI systems improve operator performance and workload management.

Empirical evidence identifies key challenges in MI control design and control conflict.

Abstract

This paper presents an Expert-guided Mixed-Initiative Control Switcher (EMICS) for remotely operated mobile robots. The EMICS enables switching between different levels of autonomy during task execution initiated by either the human operator and/or the EMICS. The EMICS is evaluated in two disaster response inspired experiments, one with a simulated robot and test arena, and one with a real robot in a realistic environment. Analyses from the two experiments provide evidence that: a) Human-Initiative (HI) systems outperform systems with single modes of operation, such as pure teleoperation, in navigation tasks; b) in the context of the simulated robot experiment, Mixed-Initiative (MI) systems provide improved performance in navigation tasks, improved operator performance in cognitive demanding secondary tasks, and improved operator workload compared to HI. Results also reinforce previous human-robot interaction evidence regarding the importance of the operator's personality traits and their trust in the autonomous system. Lastly, our experiment on a physical robot provides empirical evidence that identify two major challenges for MI control: a) the design of context-aware MI control systems; and b) the conflict for control between the robot's MI control system and the operator. Insights regarding these challenges are discussed and ways to tackle them are proposed.