Reflective Agents with Distributed Adaptive Reasoning

Project Description

RADAR (Reflective Agents with Distributed Adaptive Reasoning) is a flagship research project within CMU to develop a personal cognitive assistant that integrates with current desktop and applications, and helps users to carry out routine tasks, such as organizing meetings, answering routine emails, managing web pages, etc. RADAR is composed of several specialist components that have knowledge about how to do a task, and which learn over time user preferences and idiosyncrasies when performing tasks.

The ABLE group is researching the software architectural style that is required to put together such a system, and also in providing task management support within RADAR.

Project home page:http://www.radar.cs.cmu.edu/

Research focus of ABLE Group

Architectural: What are the appropriate high-level structures for cognitive architectures?

Our position: Generic agent architectures are just a first step.

Sample Issues:

• What are the important semantic distinctions between task-aware computing elements?
• How can you provide an engineering basis (toolkit) for developers of task-aware systems?
• What are the reusable building blocks, and how can you make them easy to use by component writers?
• How can you make this pluggable into legacy systems?

Task Management: How can you make it possible for ordinary users to benefit from this technology?

Our position: Task management is a task too.

Sample Issues:

• How do you help a user manage many tasks?
• What structures allow ease of recovery from faulty assistance? Is there a cognitive "undo"?
• Coping with legacy, heterogeneity, mobility, abuse.
• How can users specify new tasks spanning simple (e.g., to do lists) to complex (e.g., trip planning) tasks?

Contacts

David Garlan, Bradley Schmerl, Prabhu Ragunathan, Nicholas Sherman, Gabe Zenarosa.

Related Publications