Effects of Probing Behaviors to Adapt Machine Autonomy in Shared Control Systems

Abstract

This paper addresses the adaptability in the human-machine collaboration as a necessary element for the adequate coordination between human and mechanized control. Currently, all efforts to resolve any mismatch between humans and machines are charged only to the human operators as machines have no ability to deal with and adapt to variable behaviors of their human partners. Concerning this issue, inspired by our human proactive actions to the external world, the authors advocate introducing proactive agency into machine autonomies so that they can probe or sound out the partner's covert judgments for their adaptation. This behavioral model is implemented into a simulated sharedcontrol environment, in which both a human operator and a machine autonomy can control the behavior of a mobile robot. This testbed environment is utilized to investigate their joint activity and then discuss feasibility of the coadaptive approach towards the well-coordinated collaboration by the human operator and the machine autonomy.

A new multi-criteria optimization strategy for shared control in wheelchair assisted navigation

“…A second group of approaches (Connell and Viola 1990;Horiguchi and Sawaragi 2005;Miller 1998;Rao et al 2002;Simpson and Levine 1998) rely on using a basic set of primitives like AvoidObstacle, FollowWall and PassDoorway to assist the person in difficult maneuvers, either by manual selection or automatic triggering. Hence, the operator may guide the robot directly, or switch among various autonomous behaviors to deal with complex situations.…”

“…There are many studies on the level of autonomy a robot might have when interacting with a human and viceversa (Aigner and McCarragher 2000;Bruemmer et al 2005;Horiguchi and Sawaragi 2005;Kofman et al 2005). Depending on the amount of autonomy given to the machine, collaborative approaches for human/machine control can be roughly categorized into i) safeguarded operation; and ii) shared control.…”

Reactive adapted assistance for wheelchair navigation based on a standard skill profile

“…In safeguarded navigation, the mobile is controlled by the human except when a potentially dangerous situation is detected [5] [6] [7]. Frequently, shared control approaches [8] [9] [10] rely on a basic set of primitives like AvoidObstacle, F ollowW all and P assDoorway to assist the user in difficult maneuvers. These primitives can be triggered manually, by the user, or automatically, when sensors detect a specific situation.…”

Adaptive collaborative assistance for wheelchair driving via CBR learning

“…There are many studies on the level of autonomy a robot might have when interacting with a human and viceversa [1] [2] [3] [4]. Depending on how much autonomy the machine has, collaborative approaches can be roughly categorized into i) safeguarded operation; and ii) shared control.…”