Collaborators: Peter Stone, Michael Quinlan
MARIONET, or Motion Acquisition for Robots through Iterative Online Evaluative Training, is a framework I developed with my undergraduate/masters adviser, Dr. Peter Stone.
Although machine learning has improved the rate and accuracy at which robots are able to learn, there are still tasks at 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. In this paper, we propose 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. Fully implemented and tested on two robotic platforms (one quadruped and one biped), our research has demonstrated that MARIONET is a viable way to directly transfer human motion skills to robots.
Relevant Publications
Adam Setapen, Michael Quinlan, and Peter Stone. Beyond Teleoperation: Exploiting Human Motor Skills with MARIOnET. In AAMAS 2010 Workshop on Agents Learning Interactively from Human Teachers (ALIHT), Toronto, Canada - May 2010.
Adam Setapen, Michael Quinlan, and Peter Stone. MARIOnET: Motion Acquisition for Robots through Iterative Online Evaluative Training (Extended Abstract). In The Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS)*, International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, May 2010.
Adam Setapen. Exploiting Human Motor Skills for Training Bipedal Robots. Undergraduate Honors Thesis/Technical Report HR-09-02. Committee: Peter Stone (chair), Dana Ballard, Gordon Novak.
Relevant Technologies
Machine learning, Motion Capture (Vicon), Robot Kinematics, C++, Qt, MATLAB, Sony AIBO, Aldebaran Nao
