Distributed Continual Planning and Execution for Autonomous Air Vehicles

Principal Investigator:  Charles L Ortiz Mailing address: AI Center SRI International 333 Ravenswood Avenue Menlo Park, CA 94025-3493 AIC Program:  Representation and Reasoning

The DCOPE project is a project funded under ONR which will develop a new software capability for the reprogrammable, coordinated command and control of teams of autonomous unmanned combat air vehicles (UCAVs). This new software capability will allow developers to build and test UCAV teams that collaboratively perform tasks - such as reconnaissance and surveillance - with minimal supervision in dynamic, unstructured environments. Our major contribution will be an integrated planning and distributed control architecture in which collective behavior is uniquely adaptive and fault tolerant. A strategy manager will generate coordinated strategies relative to mission goals, and individual UCAVs will have sufficient autonomy to respond to unexpected situations. SRI’s Procedural Reasoning System (PRS) will be enhanced and used to develop reactive planning/controllers. Using PRS, we will also incorporate SharedPlans constructs as well as a capability for UCAV’s to reason about communication limitations and the relevance of information.

• Ortiz, C. . Varieties of emergent behavior in large-scale systems, in Proceedings of the Autonmous Intelligent Networks and SystemsSymposium, 2003.  [Details]

• Ortiz, C. and Stavridou, V. New directions in the analysis of massive multiagent systems, in Proceedings of the Autonomous Intelligent Networks and Systems Symposium, 2002.  [Details]

• Ortiz, C.L. and Hsu, E. Structured Negotiation, in First International Conference on Autonomous Agents and Multiagent Systems, 2002.  [Details]

• Ortiz, C.L. and Agno, A. and Berry, P. and Vincent, R. Multilevel Adaptation in teams of unmanned air and ground vehicles, in Proceedings of the First AIAA Unmanned Aerospace Vehicles, Systems, Technologies and Operations Conference and Workshop, 2002.  [Details]