Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks

• Published in: Hri '15: ACM/IEEE International Conference on Human-Robot Interaction USB Stick pp. 189 - 196
• Main Authors: Nikolaidis, Stefanos, Ramakrishnan, Ramya, Keren Gu, Shah, Julie
• Format: Conference Proceeding
• Language: English
• Published: ACM 02.03.2015
• Subjects: Clustering algorithms; Collaboration; Computational modeling; Data models; Markov processes; Robots; Task analysis

We present a framework for automatically learning human user models from joint-action demonstrations that enables a robot to compute a robust policy for a collaborative task with a human. First, the demonstrated action sequences are clustered into different human types using an unsupervised learning...