THE Cognitive PERSONAL ASSISTANT.

This article discusses a computer-based administrative assistant developed by researchers at Carnegie Mellon University in Pittsburgh, Pennsylvania, that draws upon artificial intelligence (AI) techniques to perform routine tasks such as scheduling meetings for busy managers and filtering and prioritizing their e-mail. The project, called Radar (short for Reflective Agent with Distributed Adaptive Reasoning), is being funded by the U.S. Defense Advanced Research Projects Agency (DARPA) under a program called PAL, or Personalized Assistant that Learns. DARPA provided the Radar project, which was launched in May 2003, with $7 million in first-year funding. Radar will handle some routine tasks by itself, ask for a supervisor's confirmation on others and produce suggestions and drafts that its user can accept or modify as needed. Using AI, Radar will draw on statistical and symbolic learning. Applying AI to natural-language understanding is hardly a new concept -- researchers have been working on this for at least 25 years. Some of the technical challenges encountered in the project include trying to provide Radar with a sufficient amount of natural-language understanding. Another challenge is equipping Radar to build upon a body of knowledge and programming it to learn from its mistakes over time.