We propose a method to learn typical motion behaviors of persons.
As people move through their environments, they usually do not move
randomly. Instead, they often engage in typical motion patterns,
related to specific locations they might be interested in
approaching and specific trajectories they might follow in doing so.
Knowledge about such patterns may enable a mobile robot to develop
improved people following and obstacle avoidance skills. We present
an algorithm that learns collections of typical trajectories that
characterize a person's motion patterns. Data, recorded by mobile
robots equipped with laser-range finders, is clustered into
different types of motion using the popular expectation maximization
algorithm while simultaneously learning multiple motion patterns.
Experimental results, obtained using data collected in a domestic
residence and in an office building, illustrate that highly
predictive models of human motion patterns can be learned.
Learning Motion Patterns of People for Compliant Robot Motion
M. Bennewitz, W. Burgard, G. Cielniak, and S. Thrun. In: The International Journal of Robotics Research, Vol. 24, Number 1, 2005.
Mobile Robot Navigation
in Dynamic Environments (PhD Thesis)
M. Bennewitz, University of Freiburg, 2004. Webpage with detailed information.
- Using EM to Learn Motion Behaviors of Persons with Mobile
M. Bennewitz, W. Burgard and S. Thrun. In: Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2002.
Please check this webpage for further related publications in the years 2002-2004.
|Video (mpg) showing the individual learning steps.|