Broad Area Colloquium For AI-Geometry-Graphics-Robotics-Vision
(CS 528)

Robust Activity Recognition

Henry Kautz
Research Scientist
Department of Computer Science & Engineering
University of Washington
Monday, March 8, 2004, 4:15PM
TCSeq 200
http://graphics.stanford.edu/cs528/

Abstract

In the early days of the field of artificial intelligence, researchers often explicitly strove to develop systems that could understand a broad range of everyday human experience. As the field matured research concentrated on better-defined, more limited domains. In the Assisted Cognition project we are returning to this original vision, armed with the modern toolkit for probabilistic inference and a new generation of ubiquitous sensing technology. I will describe progress in learning and tracking activities of daily living in the home and patterns of transportation use throughout a community, in the context of practical applications for assistive healthcare technology. Finally I will mention some surprising new connections between probabilistic inference and classical methods for logical reasoning.

About the Speaker

Henry Kautz is an Associate Professor in the Department of Computer Science and Engineering at the University of Washington. He joined the faculty in the summer of the year 2000 after a career at Bell Labs and AT&T Laboratories, where he was Head of the AI Principles Research Department. He is a recipient of the Computers and Thought Award from the International Joint Conference on Artificial Intelligence and a Fellow of the American Association for Artificial Intelligence.

Contact: bac-coordinators@cs.stanford.edu

Back to the Colloquium Page