Human-robot skill transmission for mobile robot via learning by demonstration

This paper proposed a skill transmission technique for the mobile robot via learning by demonstration. When the material is transported to the designated location, the robot can show the human-like capabilities: autonomous tracking target. In this case, a skill transmission framework is designed, which the Kinect sensor is utilized to distinguish human activity recognition to create a planned path. Moreover, the dynamic movement primitive method is implemented to represent the teaching data, and the Gaussian mixture regression is utilized to encode the learning trajectory. Furthermore, in order to realize the accurate position control of trajectory tracking, a model predictive tracking control is investigated, where the recurrent neural network is used to eliminate the uncertain interaction. Finally, some experimental tasks using the mobile robot (BIT-6NAZA) are carried out to demonstrate the effectiveness of the developed techniques in real-world scenarios.

Automated summary

This paper proposes a skill transmission technique for mobile robots through learning by demonstration, enabling them to autonomously track targets similar to humans. A framework is designed using the Kinect sensor for human activity recognition and a dynamic movement primitive method combined with Gaussian mixture regression for teaching data representation and learning trajectory encoding. The study also investigates model predictive tracking control with recurrent neural networks to achieve accurate position control for trajectory tracking by eliminating uncertain interactions. Experimental tasks using the mobile robot (BIT-6NAZA) are conducted to demonstrate the effectiveness of the developed techniques in real-world scenarios.