Enabling Intelligence through Middleware: Report of the AAAI 2010 Workshop

ty of life. For example, baby boomers are aging. Home-based robots that assist with housekeeping tasks enable more of the population to remain in their homes while reducing health-care costs. Using robots to survey, surveil, and secure regions of interest requires intelligent algorithms that can act and react autonomously in dynamic regions. Unfortunately this vision is quite distant from the current reality where deployed military unmanned vehicles can require teams of three to four operators. Researchers are actively pursuing interdisciplinary research that enables robots to function autnomously within arbitrary environments alongside people. The goal of the AAAI 2010 Workshop on Enabling Intelligence through Middleware was to examine both the successes and opportunities to provide tools that enable a larger pool of researchers to experiment with embodied, intelligent algorithms. The half-day workshop, attended by over 80 people, was held as part of the Twenty-Fourth AAAI Conference on Artificial Intelligence in Atlanta Georgia on July 12, 2010. The workshop consisted of two parts: (1) invited talks and (2) middleware presentations. Robert Kohout (DARPA), Sven Koenig (NSF) and Dustin Heaton (Alabama) delivered the invited talks, which focused on the perceptions of the current issues and possible research approaches. Middleware presenters, selected to encompass a wide range of views on middleware development, represented six frameworks: ROS (Stanford/Willow Garage), YARP (Italian Institute of Technology), CAST (University of Birmingham), LCM (University of Michigan), Tekkotsu (Carnegie Mellon University), and BotSense (Road Narrows/SIU-Edwardsville).