Abstract- This paper extends a taxonomy of humanrobot interaction (HRI) introduced in 2002 [1] to include additional categories as well as updates to the categories from the original taxonomy. New classifications include measures of the social nature of the task (human interaction roles and human-robot physical proximity), task type, and robot morphology. Keywords: Human-robot interaction (HRI), taxonomy, classification of systems. 1

Abstract – Most robot systems have discrete autonomy levels, if they possess more than a single autonomy level. A user or the robot may switch between these discrete modes, but the robot can not operate at a level between any two modes. We have developed a sliding scale autonomy system that allows autonomy levels to be created and changed on the fly. This paper discusses the system’s architecture and presents the results of experiments with the sliding scale autonomy system.

We are developing a coordinated team of robots to assemble structures. The assembly tasks are sufficiently complex that no single robot, or type of robot, can complete the assembly alone. Even with a group of multiple heterogeneous robots, each adding its unique set of capabilities to the system, the number of contingencies that must be addressed for a completely autonomous system is prohibitively large. Teleoperating a multiple robot system, at the other extreme, is difficult and performance may be highly dependent on the skill of the operator. We propose and evaluate an implementation of a framework that, ideally, provides the operator with a means to interact seamlessly with the autonomous control system. Using an architecture that incorporates sliding autonomy, the operator can augment autonomous control by providing input to help the system recover from unexpected errors and increase system efficiency. Our implementation is motivated by results from an extended series of experiments we are conducting with three robots that work together to dock both ends of a suspended beam.

We have been investigating ways to improve human-robot interaction (HRI) and situation awareness (SA) in urban search and rescue (USAR). In this task, a human directs the navigation of a remotely located robot using an

Abstract not found

Learning in many multi-agent settings is inherently repeated play. This calls into question the naive application of single play Nash equilibria in multi-agent learning and suggests, instead, the application of give-andtake principles of bargaining. We modify and analyze a satisficing algorithm based on (Karandikar et al., 1998) that is compatible with the bargaining perspective. This algorithm is a form of relaxation search that converges to a satisficing equilibrium without knowledge of game payoffs or other agents’ actions. We then develop an M action, N player social dilemma that encodes the key elements of the Prisoner’s Dilemma. This game is instructive because it characterizes social dilemmas with more than two agents and more than two choices. We show how several different multi-agent learning algorithms behave in this social dilemma, and demonstrate that the satisficing algorithm converges, with high probability, to a Pareto efficient solution in self play and to the single play Nash equilibrium against selfish agents. Finally, we present theoretical results that characterize the behavior of the algorithm. 1.