Anthony LaMarca


Integrated Platforms Research, Intel Labs

University of Washington Allen Center AC436
Seattle, WA 98195 USA




(external link)


Current Research Project


Intel Science and Technology Center on Pervasive Computing (2011-)



In 2011, Intel announced the creation of a set of science and technology centers to help develop future technology in collaboration with top university research departments. (See the Intel press release and white paper describing these new research centers.) I will be a researcher in the new center forming at the University of Washington focusing on Pervasive Computing.


Selected past Intel projects I worked on

Everyday Sensing and Perception (2007-2010)








The Everyday Sensing and Perception (ESP) project sought to develop technology that can infer a user’s context with 90% accuracy over 90% of their day. ESP focused on the perception of everyday situations that many context-aware applications depend on. Specifically, ESP developed algorithms to infer:

  • Location: Where is the user, in both absolute (latitude, longitude) as well as symbolic (Grocery Store) terms?
  • Activity: What is the user doing right now in terms of physical (standing) and object-based (washing dishes) activity?
  • Gesture and Pose: What gesture is the user making with their hands, how are they standing and what are they pointing at?
  • Social interaction: Who is the user interacting with and what role are they acting in (teacher)?


To reach a 90% level of coverage, the ESP research approach employed sensors integrated into a user’s mobile devices to sense their environment and how they interact with it. ESP investigated both low-power, low data-rate sensors (e.g., RFID tags, accelerometers and radios), as well as high data-rate sensors (e.g., video cameras and microphones). To achieve 90% level of accuracy, ESP developed state algorithms employing joint modeling of video and audio data with other worn sensors, on-the-fly refinement of user models with online learning, parallelization of machine learning algorithms and compressive sensing and synopsis based reasoning for mobile devices.

The ESP project also investigated a variety of applications and new device form factors that are enabled by rich, continuous context information. We  specifically focused on systems that coupled camera-based perception with projectors and tablet displays.



Place Lab




The goal of the Place Lab project was to build a privacy-observant indoor/outdoor location system for commodity laptops, cell phones and PDAs. Place Lab was the first system to demonstrate the viability of metro-scale coverage by an 802.11 location system and was influential in the creation of SkyHook and other commercial beacon-based location systems. Place Lab was an open sourced project and can be downloaded from placelab.org.







The PlantCare project investigated challenges associated with an automated, sensor and actuator-rich, ubiquitous system. The ambitious goal was to build a system capable of monitoring the dryness of house plants and to deploy a robot to water the ones needing attention. (While we learned about deploying and maintaining sensor networks as well as instrumenting robots with novel sensors and chargers, we never managed to build a robust system.)