Bob Price works on inference, tracking, learning, and planning applications for government and industry clients. He has developed technologies for inferring the strategic intent of military forces from low-level reports of individual military units in the field for the DARPA Deep Green Program. Bob developed algorithms for PARC client Dai Nippon Printing to learn behavior patterns of cell phone users from logs of their GPS traces and use these patterns together with background databases of local vendors to infer user preferences for activities. He has also worked in the area of model-based control on a system for improving the diagnostic information generated from automatically constructed plans; machine learning of rules to diagnose problems in printing engines from fault code sequences; and optimization of power loads to minimize power and cost and maximize utility. Previously, Bob held a post-doctoral fellowship at the University of Alberta where he modeled the online purchasing behavior of consumers, worked on predictive models of web searching behavior and constructing recommendation sets with optimal diversity. At the University of Toronto, Bob worked on symbolic/relational approaches to planning under uncertainty. His thesis work developed methods to exploit observations of other agents to guide learning of an agent and exchange knowledge between heterogeneous representations. Bob continues to pursue a variety of projects involving extraction of structure from noisy data, computer support of human learning and decision making, and automatic planning under uncertainty. Bob earned his MSc in Computer Science at the University of Saskatchewan and Ph.D. in Computer Science from the University of British Columbia.