Abstract-One major design goal in human-robot interaction is that the robots behave in an intelligent manner, preferably in a similar way as humans. This constraint must also be taken into consideration when the navigation system for the platform is developed. However, research in human-robot interaction is often restricted to other components of the system including gestures, manipulation, and speech. On the other hand, research for mobile robot navigation focuses primarily on the task of reaching a certain goal point in an environment. We believe that these two problems can not be treated separately for a personal robot that coexists with humans in the same surrounding. Persons move constantly while they are interacting with each other. Hence, also a robot should do that, which poses constraints on the navigation system. This type of navigation is the focus of this paper. Methods have been developed for a robot to join a group of people engaged in a conversation. Results show that the platform's moving patterns are very similar to the ones of the persons. Moreover, this dynamic interaction has been judged naturally be the test subjects, which greatly increases the perceived intelligence of the robot.

Explanations of cognitive processes provided by traditional artificial intelligence were based on the notion of the knowledge level. This perspective has been challenged by new AI that proposes an approach based on embodied systems that interact with the real‐world. We demonstrate that these two views can be unified. Our argument is based on the assumption that knowledge level explanations can be defined in the context of Bayesian theory while the goals of new AI are captured by using a well established robot based model of learning and problem solving, called Distributed Adaptive Control (DAC). In our analysis we consider random foraging and we prove that minor modifications of the DAC architecture renders a model that is equivalent to a Bayesian analysis of this task. Subsequently, we compare this enhanced, “rational,” model to its “non‐rational” predecessor and a further control condition using both simulated and real robots, in a variety of environments. Our results show that the changes made to the DAC architecture, in order to unify the perspectives of old and new AI, also lead to a significant improvement in random foraging.

No abstract

No abstract

Behaviour coordination i s a notorious problem in mobile robotics. Behaviours are either in competition o r collaborating to achieve the goals of a system, which leads to requirements for arbitration and/or fusion of control signals. I n most systems the arbitration is specified in t e r n of "events" that denote positions or sensory input. The detection of these events allows discrete switching between groups of behaviours. In contrast, the fusion of behaviours is often achieved using potential fields, fuzzy rules, o r superposition. In most cases, the underlying theoretical foundation is rather weak and the behaviour switching results in discrete changes in the overall system dynamics. I n this paper, we present a scheme for behaviour coordination that is grounded in the dynamical systems approach. The methodology provides a solid theoretical basis for analysis and design of a behaviour coordination framework. This framework is demonstrated in the context of a domestic robot for fetch-and-cany type tasks. I t is here shown that behaviour coordination can be analyzed as an integral part of the design to facilitate smooth transition and fusion between behaviours.