My research centers around intelligent coordination among multiple (semi-)autonomous systems, involving the proactive selection (planning) of physical, communicative, and/or computational actions that improve performance in a multiagent context. My work thus is concerned with how artificial agents should decide what courses of action to commit to given a multiagent world, how they should meet those commitments (including meeting real-time constraints), and how they should revise and renegotiate their commitments based on unexpected events in their environment.
My research group (my students and I) is cleverly (for those who know University of Michigan campus landmarks) called:
My active projects include:
- Making and Keeping Informed Commitments in Human-Machine Systems (AFOSR)
- Augmented Cognition Technologies to Improve Decisions About Active Participation in Life Situations by Adolescents and Young Adults (NIDILRR-HHS)
- Manned-Unmanned Teaming for Reconnaissance in Adversarial Environments (Army)
Some of the projects that I have worked on in the past have included:
- Manned-Unmanned Teaming Mission Integration (Army)
- Creating Organizationally-Adept Software Agents and Their Organizations (NSF)
- Multiagent Plan Management for Socio-Cognitive Orthotics (NSF)
- Temporal Planning for Automatic Service Composition (AFOSR)
- Adjustable Autonomy for Safe, Coordinated Control (DARPA)
- A Shared Intelligence Framework Targeting Flexible Human Agent Cooperative Tasks (DARPA)
- Congregating Agents: Studies in Self-Organization in Multi-Agent Systems (NSF)
- UMDL: The University of Michigan Digital Library project (NSF/DARPA/NASA)
- The UGV (Unmanned Ground Vehicles) Project, part of the DARPA Real-Time Planning and Control Initiative
- SSA: Ship System Automation (DARPA)
- An Agent-Based Architecture for Distributed Configuration Design
- UMPRS: The University of Michigan Procedural Reasoning System (DARPA)
- CIRCA: The Cooperative Intelligent Real-Time Control Architecture (NSF)
- Multilevel Coordination Mechanisms for Real-Time Autonomous Agents (NSF)
- Strategic Positioning in Information Product Space (NSF)
Our multiagent simulation testbed, MICE, is available via anonymous ftp.