Integrating task planning and interactive learning for robots to work in human environments

Human environments are challenging for robots, which need to be trainable by lay people and learn new behaviours rapidly without disrupting much the ongoing activity. A system that integrates AI techniques for planning and learning is here proposed to satisfy these strong demands. The approach rapidly learns planning operators from few action experiences using a competitive strat-egy where many alternatives of cause-effect expla-nations are evaluated in parallel, and the most suc-cessful ones are used to generate the operators. The success of a cause-effect explanation is evaluated by a probabilistic estimate that compensates the lack of experience, producing more confident esti-mations and speeding up the learning in relation to other known estimates. The system operates with-out task interruption by integrating in the planning-learning loop a human teacher that supports the planner in making decisions. All the mechanisms are integrated and synchronized in the robot using a general decision-making framework. The feasibil-ity and scalability of the architecture are evaluated in two different robot platforms: a Stäubli arm, and the humanoid ARMAR III.