This paper presents an application of a multihierarchical, symbolic model of large-scale space for representing the environment of a robotic wheelchair that has been automated for assistance to mobility impaired people. Rehabilitation robotics has an issue that is not present in mobile robotics: the need for an interface with the human driver. Our hierarchical model demonstrates its suitability to represent the environment in a structure easily manageable by the human (it serves as a good interface with the human’s cognitive map) and, at the same time, provides better performance than flat topological maps in route planning. This is achieved by including multiple hierarchies of abstraction in the model, which improves the adaptation of the vehicle to its tasks and environment. The paper describes and illustrates an experiment in which the wheelchair, with the assistance of the human driver, builds a model of space and uses it for autonomous navigation. 1

The paper describes PECAS, an architecture for intelligent systems, and its application in the Explorer, an interactive mobile robot. PECAS is a new architectural combination of information fusion and continual planning. PECAS plans, integrates and monitors the asynchronous flow of information between multiple concurrent systems. Information fusion provides a suitable intermediary to robustly couple the various reactive and deliberative forms of processing used concurrently in the Explorer. The Explorer instantiates PECAS around a hybrid spatial model combining SLAM, visual search, and conceptual inference. This paper describes the elements of this model, and demonstrates on an implemented scenario how PECAS provides means for flexible control. 1

In the last few years in cognitive science there has been a growing interest in the connection between visual perception and natural language. The question of interest is: How can we discuss what we see. With this question in mind in this article we will look at the area of incremental route descriptions. Here, a speaker step-by-step presents the relevant route information in a 3D-environment. The speaker must adjust his/her descriptions to the curenntly visible objects. Two major questions arise in this context: 1. How is visually obtained information used in natural language generation? and 2. How are these modalitites coordinated? We will present a computational framework for the interaction of visual perception and natural language descriptions which integrates several processes and representations. Especially discussed is the interaction between the spatial representation and the presentation representation used for natural language descriptions. We have implemented a prototypical...

Image-based Navigation through Large-scale Environments May 1994 Brian Edmund Pinette B.S., Massachusetts Institute of Technology M.S., University of Massachusetts Amherst Ph.D., University of Massachusetts Amherst Directed by: Professor Andrew G. Barto To be truly autonomous, a robot must be able to infer its location from available landmarks. To navigate to locations whose landmarks are out of view, a robot must maintain some sort of map of the large-scale layout of landmarks and locations. Since landmarks can change, a map can become outdated; this work develops a principled approach to maintaining a reliable map in the face of uncertainty and change.

The background for this paper is the aim to build robotic assistants that can “naturally” interact with humans. One prerequisite for this is that the robot can correctly identify objects or places a user refers to, and produce comprehensible references itself. As robots typically act in environments that are larger than what is immediately perceivable, the problem arises how to identify the appropriate context, against which to resolve or produce a referring expression (RE). Existing algorithms for generating REs generally bypass this problem by assuming a given context. In this paper, we explicitly address this problem, proposing a method for context determination in large-scale space. We show how it can be applied both for resolving and producing REs. 1

To my parents ii Table of Contents Table of Contents iii Abstract xv Acknowledgements xvii

In this paper we present an approach to the task of generating and resolving referring expressions (REs) for conversational mobile robots. It is based on a spatial knowledge base encompassing both robot- and human-centric representations. Existing algorithms for the generation of referring expressions (GRE) try to find a description that uniquely identifies the referent with respect to other entities that are in the current context. Mobile robots, however, act in large-scale space, that is environments that are larger than what can be perceived at a glance, e.g. an office building with different floors, each containing several rooms and objects. One challenge when referring to elsewhere is thus to include enough information so that the interlocutors can extend their context appropriately. We address this challenge with a method for context construction that can be used for both generating and resolving REs – two previously disjoint aspects. Our approach is embedded in a bi-directional framework for natural language processing for robots. 1

Abstract not found

The architecture of a memory for autonomous agents is presented. It is based

Abstract not found