MARIOnET: Motion Acquisition for Robots through Iterative Online Evaluative Training

Although machine learning has improved the rate and accuracy at which robots are able to learn, there still exist tasks for which humans can improve performance significantly faster and more robustly than computers. While some ongoing work considers the role of human reinforcement in intelligent algorithms, the burden of learning is often placed solely on the computer. These approaches neglect the expressive capabilities of humans, especially regarding our ability to quickly refine motor skills. We have proposed a general framework for Motion Acquisition for Robots through Iterative Online Evaluative Training (MARIOnET). Our novel paradigm centers around a human in a motion-capture laboratory that "puppets" a robot in realtime. This mechanism allows for rapid motion development for different robots, with a training process that provides a natural human interface and requires no technical knowledge. As the name indicates, MARIOnET is a form of iterative online evaluative training. The human performs a motion, and the robot mimics in realtime. The human evaluates the robot's performance, and repeats the motion accounting for the errors perceived in the robot's previous actions. This loop is continued until a sufficient motion sequence is obtained. Fully implemented and tested on two robotic platforms (the Aldebaran Nao and Sony AIBO), our research has demonstrated that MARIOnET is a viable way to directly transfer human motion skills to robots.

Full details of our approach are available in the following paper:

Valid CSS!
Valid XHTML 1.0!