A Mixed Initiative Approach to Human-Robot Interaction for

We propose an innovative distributed multi-agent based mixed-initiative planning approach to facilitate true partnership among humans and robots useful in many application environments including "through-the-door" scenario. We plan to deploy our Multi Agent Robot Control System (MARCS) platform, to coordinate shoulder-to-shoulder team building and provide intelligent support for agile mission accomplishment. Our approach is inherently superior as it leads to significant improvement in human situational awareness and human-robot camaraderie for better coordination and control of different activities required to complete chaotic missions. We already have a versatile experimental distributed mobile robotic platform MARCS with multiple sensor and cognition modules readily available using Amigobot, SONAR, Cybele and Cricket based indoor positioning technologies. Algorithms wise, IAI will leverage its technologies like cooperative boundary tracking system employing a large number of robots and hierarchical task network representation to organize the team members and their task allocations efficiently in completely distributed manner. A clear demonstration of a "through-the-door" scene beginning with decomposition of tasks among the participants while noting partners' actions in decision making will be designed, implemented and demonstrated for different chaotic scenarios.