This paper surveys the field of Augmented Reality, in which 3-D virtual objects are integrated into a 3-D real environment in real time. It describes the medical, manufacturing, visualization, path planning, entertainment and military applications that have been explored. This paper describes the characteristics of Augmented Reality systems, including a detailed discussion of the tradeoffs between optical and video blending approaches. Registration and sensing errors are two of the biggest problems in building effective Augmented Reality systems, so this paper summarizes current efforts to overcome these problems. Future directions and areas requiring further research are discussed. This survey provides a starting point for anyone interested in researching or using Augmented Reality. 1. Introduction 1.1 Goals This paper surveys the current state-of-the-art in Augmented Reality. It describes work performed at many different sites and explains the issues and problems encountered when ...

embedded, interactive spaces that we call Intelligent Environments. The motivation for building these systems is to bring computation into the real, physical world to support what is traditionally considered non-computational activity.

This paper argues that complex, embedded software agent systems are best constructed with parallel, layered architectures. These systems resemble Minskian Societies of Mind and Brooksian subsumption controllers for robots, and they demonstrate that complex behaviors can be had via the aggregates of relatively simple interacting agents. We illustrate this principle with a distributed software agent system that controls the behavior of our laboratory's Intelligent Room. Introduction This paper argues that software agent systems that interact with dynamic and complex worlds are best constructed with parallel, layered architectures. We draw on Brooks' subsumption architecture (Brooks, 1985) and Minsky's Society of Mind (Minsky, 1986) theory to dispel the notion that sophisticated and highly capable agent systems need elaborately complex and centralized control. Towards this end, we present an implemented system of software agents that forms the backbone of our laboratory's "Intelligent Ro...

One challenge in multimodal interface research is the lack of robust subsystems that support multimodal interactions. By focusing on a chair—an object that is involved in virtually all human–computer interactions, the sensing chair project enables an ordinary office chair to become aware of its occupant’s actions and needs. Surface-mounted pressure distribution sensors are placed over the seatpan and backrest of the chair for real time capturing of contact information between the chair and its occupant. Given the similarity between a pressure distribution map and a grayscale image, pattern recognition techniques commonly used in computer and robot vision, such as principal components analysis, have been successfully applied to solving the problem of sitting posture classification. The current static posture classification system operates in real time with an overall classification accuracy of 96 % and 79 % for familiar (people it had felt before) and unfamiliar users, respectively. Future work is aimed at a dynamic posture tracking system that continuously tracks not only steady-state (static) but transitional (dynamic) sitting postures. Results reported here form important stepping stones toward an intelligent chair that can find applications in many areas including multimodal interfaces, intelligent environment, and safety of automobile operations.

Intelligent spaces [1, 2] are rooms or areas that are equipped with sensors such as microphones or cameras that enable them to perceive what is happening in them. In such spaces that have an intelligence of their own a world model no longer is something the robot has alone but a service offered by the information infrastructure of the space. In this article we show how such an intelligent space can generate a topological map for robots by looking at the movements of people in the room. We describe the stereo vision system that is capable of tracking the 3D movements of several humans in real time and give experimental results obtained in a real-world environment with several people. 1 Introduction Autonomous robotic systems such as service robots need maps in order to complete their tasks. This is partially due to the fact that navigation in completely unknown environments is still an unsolved problem. Even if this was possible maps would be needed to specify the robots task or const...

The self-organizing desk is a system that enhances a physical desk-top with electronic information. It can remember, organize, update, and manipulate the information contained in the documents on a desk. The system consists of a simple robot eye that can survey the desk, a module for smart extraction of information from the images taken by the robot, a module for representing this information in multiple views, and a module that allows a user to interact with this information. 1 Introduction We wish to create smart physical worlds, that can augment reality with electronic information. Such spaces will keep track of their own contents, indexing and organizing their objects in electronic views. We hope to achieve this vision by using sensors to extract information about the physical world. The self-organizing desk, a system that can keep track of its contents autonomously, is an example of such systems. Consider the flow of paper that arrives for processing at someone's desk. Many pap...

While active vision is a relatively new approach to computer vision, it offers impressive computational benefits for scene analysis in realistic environments. This paper describes a novel camera platform for the real-time, real-world application of active vision in robots. Requirements for performance are presented as are the figures actually achieved, along with an alternative, task-based method of specifying active visual system abilities. Details of the platform's cable drive transmission mechanism are provided as well as the advantages given by this scheme. Finally, research directions involving this platform are discussed. 1 Introduction An important decision in the design of an autonomous robotic system is the choice of sensory mechanism(s) to be employed. The robot must be able to gather data from its environment which is both of adequate content and in a sufficiently timely fashion for it to make the decisions necessary for task-oriented behaviour. For the purposes of our rese...

Abstract. Facilitating interaction between users and their environment has been the subject of much research in computer science. One practical application that evolves from this research is that of an intelligent tourist assistant. In this paper, HIPS, an innovative implementation of such an application is briefly outlined. In particular, we describe an implementation that exploits HIPS concepts to enable intelligent interaction between tourists and their environment. 1

. In this paper, we propose the knowledgeable environment as a framework for integrated systems for human-machine co-existing space. In the knowledgeable environment, integration is achieved as knowledgelevel communication and cooperation. We abstract all machines as information agents whose roles and communication are understandable for people. Ontology is here used as explicit representation of the abstraction of the environment which includes agents, objects, and activities of agents and people. Cooperation is also achieved by using ontology. We re-define concept of human-machine interaction in the light of knowledge-level interaction, i.e., interaction with various logical and spatial relation among participants. We realized a prototype of the knowledgeable environment with two mobile robots, rack and door agents, and demonstrated how cooperation among robots, machines and people could be implemented. Keyword: real-world agent, ontology, mediation, cooperation, human-robot interact...

There is no record being kept by computers about our personal information consumption. By capturing the content and context of all the information we interact with, computers can help us manage this information. This thesis describes such a tool, which we call a personal information management system. We build on traditional and personalized information retrieval tools, software agents, and the advanced multi-modal user interface provided by the MIT AI Lab's Intelligent Room. Thesis Supervisor: Lynn Andrea Stein Title: Associate Professor 2 Acknowledgments I must thank Michael Coen first and foremost. For both his mentoring, advice, humor, and friendship as well as his amazing creation, SodaBot. I am honored that he let me tinker under its hood, and after 2 years, I think I finally understand how the heck it works, sorta. I can hardly wait to see HAL, which I know will be slick and will hopefully find your keys for you. Professor Lynn Stein, thank you so much. I greatly appreciat...