The Location Stack: Multi-sensor Fusion in Action

The Location Stack is a set of design abstractions and sensor fusion techniques for location systems. It employs novel probabilistic techniques such as particle filters to fuse readings from multiple sensor technologies while providing a uniform programming interface to applications. Our implementation is publicly available and supports many location sensor technologies. Specifically, our live demonstration tracks multiple people using statistical sensor fusion of RFID proximity tags and ultrasonic distance measurement badges. Participants are invited to don tracking badges and watch a projected visualization of the real-time probabilistic estimates of all participants’ locations.

[1]  Henry Kautz,et al.  Foundations of Assisted Cognition Systems , 2003 .

[2]  Gaetano Borriello,et al.  Location Systems for Ubiquitous Computing , 2001, Computer.

[3]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[4]  Dieter Fox,et al.  Bayesian Filtering for Location Estimation , 2003, IEEE Pervasive Comput..

[5]  Andy Hopper,et al.  Implementing a Sentient Computing System , 2001, Computer.

[6]  Nando de Freitas,et al.  Sequential Monte Carlo in Practice , 2001 .

[7]  Gaetano Borriello,et al.  The location stack: a layered model for location in ubiquitous computing , 2002, Proceedings Fourth IEEE Workshop on Mobile Computing Systems and Applications.

[8]  Henry A. Kautz,et al.  Voronoi tracking: location estimation using sparse and noisy sensor data , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).