The aim of the 3-year EU FP7 research project SPENCER was to develop algorithms for service robots that can guide groups of people through highly dynamic and crowded pedestrian environments, such as airports or shopping malls, while behaving in a socially compliant manner by e.g. not crossing in between families or couples. As a PhD student in this project, my main research focus was on people and group detection and tracking in 2D laser range and RGB-D data, as well as full-body real-time human attribute classification in RGB-D. I was also heavily involved in the overall system integration of the custom robot platform, which is equipped with two front- and two rear-facing RGB-D sensors, two 2D laser scanners, a stereo camera pair and 5 onboard computers. A very successful deployment of the prototype at Amsterdam-Schiphol took place in March 2016.
- Project Type EU FP7 research project
- My role PhD student
- My tasks Multi-modal people tracking, human attribute recognition in RGB-D, overall system integration
- Technologies ROS, C++, Python
- Website: http://www.spencer.eu/