Human-Agent Collaborative Optimization of Real-Time Distributed Dynamic Multi-Agent Coordination
Rajiv T. Maheswaran, Marina Del Rey, Craig Milo Rogers, Romeo Sanchez, Pedro A. Szekely · 2010
Creating decision support systems to help people coordinate in the real world is difficult because it requires simultaneously addressing planning, scheduling, uncertainty and distribution. Generic AI approaches produce inadequate solutions because they cannot leverage the structure of domains and the intuition that end-users have for solving particular problem instances. We present a general approach where end-users can encode their intuition as guidance enabling the system to decompose large distributed problems into simpler problems that can be solved by traditional centralized AI techniques. Evaluations in field exercises with real users show that teams assisted by our multi-agent decision-support system outperform teams coordinating using radios.