Mixed-initiative Variable Autonomy for Remotely Operated Mobile Robots

Abstract

This article 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. Last, 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.

Trust, Shared Understanding and Locus of Control in Mixed-Initiative Robotic Systems

“…In the current context, MI control refers to the authority of both the robot's MI control switcher and the operator to initiate LoA switches at any moment. The MI control switcher used was proposed in [5] and uses an expert-guided approach to initiate LoA switches. It assumes the existence of an AI task expert (i.e.…”

“…In practice, the MI control switcher parameters were trained to use this error to initiate LoA switches based on what the human operators did to improve performance on data from previous experiments. For further details regarding the expert-guided MI control switcher, please refer to [5].…”

“…The software 1 used was developed in Robot Operating System (ROS) and is described in more detail in [4], [5]. The robot's autonomous navigation uses the framework and algorithms (i.e.…”

“…In HI control, the human operator is solely responsible for switching LoA based on their judgement [4]. In MI control, both the operator and the robot's AI have the authority to initiate actions and switch LoA [5], meaning the robot is essentially a peer with equal authority. This makes designing HRI uniquely challenging, as transferring control authority fluidly requires communication, trust and shared understanding within the human-robot team.…”

VFH+ based shared control for remotely operated mobile robots

“…the human has the authority to initiate switches between different LOAs) [7] or Mixed-Initiative (i.e. both the human and the robot can initiate LOA switches) [8] systems. An additional advantage is the ability to cope with dynamic environments due to the reactive nature of our shared control method.…”