This video is a media attachment to the following paper: Automatic Segmentation and Recognition of Human Activities from Observation based on Semantic Reasoning, Karinne Ramirez-Amaro, Michael Beetz, Gordon Cheng. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), September 2014.
This video presents a framework that combines different signals via semantic reasoning to enable robots for on-line segmentation and recognition of human activities from observation. In other words, the robot understands and infers what the human is doing with 85% accuracy. Additionally, we show how the robot learns new activities on the fly.
Социальные закладки