Robots are going to assist elderly people with daily tasks in the future. Each user has his/her own preferences and needs, so coming up with a robot that adapts to them remains a challenge. Gerard Canal, Gullem Alenyà and Carme Torras have proposed a method that allows robots to adapt their behavior to each user’s preference. They have developed:

a method to perform behavior adaptation to the user preferences, using symbolic task planning. A user model is built from the user’s answers to simple questions with a fuzzy inference system, and it is then integrated into the planning domain.

[HT]