OPF: A Distributed Context-Sensing Framework for Ubiquitous Computing Environments Max Van Kleek 1 , Kai Kunze 2 , Kurt Partridge 3 , and James “Bo” Begole 3 1 MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), 32 Vassar St. Cambridge, MA 02139 emax@csail.mit.edu 2 Institute for Embedded Systems (IES) University Passau, Innstrae 43 D-94032 Passau, Germany kai.kunze@uni-passau.de 3 Palo Alto Research Center, 3333 Coyote Hill Rd. Palo Alto, CA 94304 {kurt.partridge,bo.begole}@parc.com Abstract. This paper describes the Obje Perception Framework (OPF ), a distributed software architecture for context sensing and inference in ubiquitous computing environments. OPF provides flexibility, scalabil- ity, and robustness even as the sensor configuration changes. For flex- ibility, OPF supports many context inference tasks, ways of achieving those tasks, and heterogeneity in sensor types. With respect to scala- bility, OPF accommodates the needs of a large number of applications simultaneously while conserving power and reducing the amount of data transmitted over the network. And to support robustness to dynamism, OPF constructs context inference pipelines to satisfy each applications’ needs in a goal-directed fashion. The value of OPF is demonstrated by a case study of an end-user application that helps users establish and manage connections among the various digital resources in their envi- ronment. 1 Introduction Throughout the past decade, a number of projects have demonstrated that sensed context about the user and his or her environment can greatly improve the user experience of many types of software applications [27, 10, 14, 16, 29, 3]. The vision sought by ubiquitous computing [30] is attractive for the future of further context-enabling applications, as it provides a way by which this context might be captured. Yet, despite the proliferation of mobile digital devices and wireless communications technology, we are still far from having the computa- tion, bandwidth, and sensing capabilities embedded at a sufficient density to