Experience-driven robotic assistant for haptic collaboration
Contributor: Dongheui Lee
An incremental learning and prediction framework for an assistive controller in human-robot cooperative manipulation tasks is proposed. Instead of offline learning of manually segmented human’s motions and forces, the proposed method can learn human behaviors in an autonomous and incremental manner from an online unsegmented incoming data stream. As a consequence, the robot can improve its task knowledge over time and improve its assistance for the haptic collaboration. The proposed concepts are implemented and evaluated using a mobile bi-manual platform.
- Dana Kulic, Christian Ott, Dongheui Lee and Yoshihiko Nakamura, Incremental Learning of Full Body Motion Primitives through Human Motion Observation. The International Journal of Robotics Research, 31(3):330–345, 2012
Peer-reviewed conference papers
- Jose Ramon Medina, Tamara Lorenz, Dongheui Lee, and Sandra Hirche, Adaptive Risk-Sensitive Optimal Feedback Control for Haptic Assistance, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3639-3645, 2012
- Jose Ramon Medina, M. Shelley, Dongheui Lee, W. Takano, and Sandra Hirche, Towards Interactive Physical Robotic Assistance: Parameterizing Motion Primitives Through Natural Language, in Proc. 21st IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 1097-1102, 2012
- Jose Ramon Medina, Dongheui Lee, and Sandra Hirche, Risk-Sensitivity Optimal Feedback Control for Haptic Assistance, in Proc. IEEE International Conference on Robotics and Automation (ICRA), pp.
- Jose Ramon Medina, Martin Lawitzky, Alexander M¨ortl, Dongheui Lee, and Sandra Hirche, An Experience-Driven Robotic Assistant Acquiring Human Knowledge to Improve Haptic Cooperation, in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2416-2422, 2011
- Dana Kulic, Dongheui Lee, Christian Ott and Yoshihiko Nakamura, Incremental Learning of Full Body Motion Primitives for Humanoid Robots, in Proc. 8th IEEE International Conference on Humanoid Robots (HUMANOIDS), pp. 326-332, Daejeon, Korea, Dec 1-3, 2008