Access Restriction

Author Vasquez, Dizan ♦ Fraichard, Thierry ♦ Aycard, Olivier ♦ Laugier, Christian
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword New Observa-tions ♦ Possible Mo-tion Pattern ♦ Motion Prediction ♦ Prediction Phase ♦ Long-term Prediction ♦ Intentional Motion On-line Learning ♦ Tech-nique Work ♦ Learned Plan ♦ Decision Process ♦ Dynamic Environment ♦ Future Motion ♦ Incremental Fashion ♦ Hidden Markov Model ♦ Novel Learning Approach ♦ Neural Gas Algorithm ♦ Chal-lenging Problem ♦ Existing Approach ♦ Related Work
Description Summary. Motion prediction for objects which are able to decide their trajectory on the basis of a planning or decision process (e.g. humans and robots) is a chal-lenging problem. Most existing approaches operate in two stages: a) learning, which consists in observing the environment in order to identify and model possible mo-tion patterns or plans and b) prediction, which uses the learned plans in order to predict future motions. In existing techniques, learning is performed off-line, hence, it is impossible to refine the existing knowledge on the basis of the new observa-tions obtained during the prediction phase. This paper proposes a novel learning approach which represents plans as Hidden Markov Models and is able to estimate the parameters and structure of those models in an incremental fashion by using the Growing Neural Gas algorithm. Our experiments demonstrate that the tech-nique works in real-time, is able to operate concurrently with prediction and that the resulting model produces long-term predictions. 1 Introduction and Related Work In order to successfully interact with a dynamic environment, a person, a robot
In "Machine Vision and Applications", 2008. Publications of the year Articles In International Peer-Reviewed Journal
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article