Practical Course: Location-based Services


The goal of this practical course is to analyze GPS data recorded during everyday activities. The includes identifying places of interest, transportation modes, social networks, and identifying traffic jams. The goal is not only to analyze the existing data but also to make prediction of future actions and states.
In this practical course, we will make use of probabilistic techniques and it is therefore suggested to have participated in the lecture "Introduction to Mobile Robotics" (even if this is not a hard constraint). Furthermore, programming skills are definitively needed. Students participating in this project will have to work in small teams of two students and each team will have to solve a subproblem. The students are requested to plan the project as a whole and to coordinate their actions.

Note that participating in this course, requires to collect GPS position data from your everyday life. This data will be used in the course/our research group. You can anonymize your data but due to the small number of participants, real anonymity in the course cannot be guaranteed. We recommend that people who have serious privacy concerns about that should not participate.
Further Reading
  • Liao, Fox, Kautz: Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields, 2007. Download paper.
  • Liao, Patterson, Fox, Kautz: Learning and Inferring Transportation Routines, 2007. Download paper.
  • Ashbrook, Starner: Learning Significant Locations and Predicting User Movement with GPS, 2002. Download paper.
  • Kang, Welbourne, Stwart, Borriello: Extracting Places From Traces of Locations, 2005. Download paper.