Unsupervised Segmentation and Alignment of Multi-Demonstration Trajectories via Multi-Feature Saliency and Duration-Explicit HSMMs
Sign Up to like & getrecommendations! Published in 2025 at "Mathematics"
DOI: 10.3390/math13193057
Abstract: Learning from demonstration with multiple executions must contend with time warping, sensor noise, and alternating quasi-stationary and transition phases. We propose a label-free pipeline that couples unsupervised segmentation, duration-explicit alignment, and probabilistic encoding. A dimensionless… read more here.
Keywords: duration; unsupervised segmentation; feature saliency; duration explicit ... See more keywords