Human-robot collaboration by intention recognition using probabilistic state machines

Combining the intelligent and situation dependent decision making capabilities of a human with the accuracy and power of a robot, performance of many tasks can be improved. The human-robot collaboration scenarios are increasing. Human-robot interaction is not only restricted to the humanoid robots interacting with the humans or to the mobile service robots providing different services but also industrial robots opens a wide range of human-robot collaboration set-ups. Intention recognition plays a key role in intuitive human-robot collaboration. In this paper we present a novel approach for recognizing the human intention using weighted probabilistic state machines. We categorize the recognition task into two categories namely explicit and implicit intention communication. We present a general intention recognition approach that can be applied to any human-robot cooperation situation. The algorithm is tested with an industrial robotic arm.