Learning Guided Planning for Robust Task Execution in Cognitive Robots

Abstract:

In most robotic scenarios, having constructed a valid plan is not sufficient to guarantee success due to unexpected outcomes in the physical world. Robustness in task execution requires tight integration of continual monitoring, planning, reasoning and learning processes. We investigate how robustness is attained for cognitive robots. In this talk, I will present our cognitive robot framework for learning from experimentation. The framework ensures that the robot gains its experience from action execution failures through lifelong experimental learning. Inductive Logic Programming (ILP) is used as the learning method to frame hypotheses for failure situations. It provides first-order logic representation of the robot's experience. The robot uses this experience to construct heuristics to guide its planner in its future decisions. The performance of the learning guided planning process is analyzed on our mobile robots. The results reveal that the hypotheses framed for failure cases are sound and ensure safety and robustness in future tasks of the robot.

Bio: