Bidirectional Assistance in Human Robot Interaction

As robots and humans increasingly co-exist in home, medical, industrial and entertainment environments, mechanisms for mutual assistance become increasingly crucial. Novel task knowledge can be demonstrated by the human, and learned by robots through observation and imitation, while robots can also build adaptive user models and modify their level of assistance depending on the short and long term inference of the human's needs.
In this talk, I will review our research on bidirectional assistance between humans and robots. I will first review statistical, one-shot, and grammatical approaches to learning by imitation in humanoid robots, followed by how robots can modify their level of assistance to adapt to changing user needs, giving examples from assistive robotic wheelchairs for children and adults, and adaptive robotic dance tutors for hospitalised children.