Anchoring is the process of creating and maintaining the correspondence between symbols and percepts that refer to the same physical objects. Although this process must necessarily be present in any physically embedded system that includes a symbolic component (e.g., an autonomous robot), no systematic study of anchoring as a problem per se has been reported in the literature on intelligent systems. In this paper, we propose a domain-independent definition of the anchoring problem, and identify its three basic functionalities: find, reacquire, and track. We illustrate our definition on two systems operating in two different domains: an unmanned airborne vehicle for traffic surveillance; and a mobile robot for office navigation.

Anchoring is the process of creating and maintaining the correspondence between symbols and percepts that refer to the same physical objects. Although this process must necessarily be present in any symbolic reasoning system embedded in a physical environment (e.g., an autonomous robot), the systematic study of anchoring as a clearly separated problem is just in its initial phase. In this paper we focus on the use of symbols in actions and plans and the consequences this has for anchoring. In particular we introduce action properties and partial matching of objects descriptions. We also consider the use of indefinite references in the context of action. The use of our formalism is exemplified in a mobile robotic domain. 1

This paper describes technology and tools for intelligent human-computer interaction (IHCI) where human cognitive, perceptual, motor, and affective factors are modeled and used to adapt the H--C interface. IHCI emphasizes that human behavior encompasses both apparent human behavior and the hidden mental state behind behavioral performance. IHCI expands on the interpretation of human activities, known as W4 (what, where, when, who). While W4 only addresses the apparent perceptual aspect of human behavior, the W5+ technology for IHCI described in this paper addresses also the why and how questions, whose solution requires recognizing specific cognitive states. IHCI integrates parsing and interpretation of nonverbal information with a computational cognitive model of the user, which, in turn, feeds into processes that adapt the interface to enhance operator performance and provide for rational decision-making. The technology proposed is based on a general four-stage interactive framework, which moves from parsing the raw sensory-motor input, to interpreting the user's motions and emotions, to building an understanding of the user's current cognitive state. It then diagnoses various problems in the situation and adapts the interface appropriately. The interactive component of the system improves processing at each stage. Examples of perceptual, behavioral, and cognitive tools are described throughout the paper. Adaptive and intelligent HCI are important for novel applications of computing, including ubiquitous and human-centered computing

We wish to organize furniture with teams of mobile robots in dynamic, unstructured environments. We describe a distributed heterogeneous system of robots that cooperate to achieve this task. This system consists of two robot pushers and a mobile-sensor robot that guides and synchronizes the pushers. We present algorithms and experimental results for this system. We also discuss how this heterogeneous system of robots cooperates by decoupling and then fusing the navigation and manipulation sensory data. 1 Introduction We wish for robots to be versatile in mundane tasks in structured, as well as unstructured environments. Such robots must have the ability to manipulate objects. Consider a task in which a couch is to be moved to a designated place in a different room. The couch has to be pushed in between the furniture, out of the door, and onto its designated place. Human furniture movers coordinate complex furniture manipulation (like the motions required to move a couch through a nar...

MORIA is a low cost fuzzy controlled autonomous service robot.

Anchoring is the process of creating and maintaining the correspondence between symbols and percepts that refer to the same physical objects. This process must necessarily be present in any physically embedded system that includes a symbolic component, for instance, in an autonomous robot that uses a planner to generate strategic decisions.

We start from the observation that non-trivial mobility tasks can be recognized, described, and performed automatically, based on machine vision. We compare several approaches to representations for tasks at the conceptual level used in this context. All the approaches taken into account have been implemented and used for extensive experiments. It is thus of particular interest to study the relations between descriptive and prescriptive versions of the formulation of a mobility task. In addition, analogies and differences between applications for (indoor) mobile robots and for (outdoor) vision-based automatic road vehicles are compared to better understand the general properties of the required representations. 1: Introduction and motivation Imagine a system which evaluates signals from video-sensors to initiate, control, and terminate the execution of operations selected from a set of admissible actions. As long as this set is small, for example when sub-standard workpieces are rejec...

Self-reconfigurable robots are robots composed of many physically connected modules which can change their structural configuration to support multiple functionalities. The modules may be complete robots in themselves capable of performing some tasks without cooperation, or they may be units which are functional only when some minimum number of modules are present. Modules create structures by attaching themselves to static objects or to each other. We claim that self-reconfigurable robots are more versatile, extensible, and reliable than conventional fixed-architecture robots. In this thesis proposal we describe two di#erent self-reconfigurable robot systems. One system is based on the Inchworm robot, a small mobile robot which can perform independent navigation and manipulation tasks and can also cooperate to create structures with expanded functionality. The second system is based on our recently developed Molecule robot. Molecules are simple robots which cannot act as independent units but can cooperate to form three-dimensional structures which can move using selfreconfiguration. We discuss the scientific challenges of these systems, present a proposal for future thesis work, and describe the current status of our research. Thesis committee Dr. Bruce Donald, Department of Computer Science, Dartmouth College Dr. Michael Erdmann, Departments of Computer Science and Robotics, Carnegie Mellon University Dr. Daniel Rockmore, Department of Computer Science, Dartmouth College Dr. Daniela Rus, Department of Computer Science, Dartmouth College 1 Contents 1