Layered HMM for Motion Intention Recognition

— We evaluate Layered Hidden Markov Models (LHMM) for motion intention recognition based on actionprimitives or gestemes. The proposed methodology uses three different HMM models at the gesteme level: one-dimensional HMM, multi-dimensional HMM and multi-dimensional HMM with Fourier transform. These three models are evaluated with respect to the number of gestemes, the influence of the number of training samples, the effect of noise and the effect of the number of observation symbols.

• Type: Conference
• Year: 2006
• Where: IROS
• Authors: Daniel Aarno, Danica Kragic
• Keywords: Hidden Markov Models, IROS 2006, Multi-dimensional Hmm, One-dimensional Hmm, Robotics