Unsupervised Temporal Segmentation Using Models That Discriminate Between Demonstrations and Unintentional Actions
Takayuki Komatsu,Yoshiyuki Ohmura,Yasuo Kuniyoshi,Takayuki Komatsu,Yoshiyuki Ohmura,Yasuo Kuniyoshi
Segmentation of a compound task with multiple subtasks is crucial for imitation learning. Conventional unsupervised segmentation methods focused on only reproducibility of demonstrations and did not use the property that goal-directed actions rarely occur without intention. In this paper, we propose a novel method to segment demonstrations into goal-directed actions by self-supervised learning. We...
