Estimating 3-D rigid body transformations: a comparison of four major algorithms
Machine Vision and Applications - Special issue on performance evaluation
A Mathematical Introduction to Robotic Manipulation
A Mathematical Introduction to Robotic Manipulation
Automated Derivation of Primitives for Movement Classification
Autonomous Robots
Mimetic communication with impedance control for physical human-robot interaction
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Mimesis Model from Partial Observations for a Humanoid Robot
International Journal of Robotics Research
Associating and reshaping of whole body motions for object manipulation
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Robot Programming by Demonstration
Robot Programming by Demonstration
A compliant contact model with nonlinear damping for simulation of robotic systems
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
| Hi-index | 0.00 |
In this paper we aim at extending imitation learning to physical human-robot interaction (pHRI) including contact transitions (from non-contact to contact and vice versa). For interactive learning of pHRI, the paper raises four key issues: (1) motion imitation, (2) understanding motion primitives, (3) understanding interaction primitives, and (4) physical contact establishment.These issues are solved by (1) marker control, (2) mimesis model, (3) mimetic communication model, and (4) real-time motion reshaping and impedance control, respectively. The simple human motion imitation is realized by a direct marker control method in which the robot is virtually connected to the markers attached to the human via virtual springs. Learning procedures are based on “imitation of a human” and “active involvement” of the robot during the learning. The “imitation of a human” scheme provides efficient learning. The “active involvement” scheme supports incremental learning and it also enables to acquire sensory information for physical contacts. By modifying the mimetic communication model proposed by Nakamura et al., we achieve communication in physical domain as well as the symbolic domain. The communication in the symbolic domain is realized through the concept of motion primitives and interaction primitives. In the physical domain, the trajectory of the motion primitive is reshaped in accordance with the human's motions in real-time. Moreover, for performing compliant contact motion, an appropriate impedance controller is integrated into the setting. All of the presented concepts are applied to “high five”-like interaction tasks and evaluated in experiments with a human-size humanoid robot.