힘과 위치를 동시에 고려한 양팔 물체 조작 솜씨의 모방학습
Imitation Learning of Bimanual Manipulation Skills Considering Both Position and Force Trajectory
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.
Abstract
Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.
참고문헌 (21)
- S. Schaal, "Is imitation learning the route to humanoid robots?", Trends in cognitive sciences, 3(6), pp.233~242 (1999)
- Imitative learning mechanisms in robots and humans, "J. Demiris", DAI, ~ (1996)
- Y. Demiris, "Special issue on robot learning by observation, demonstration, and imitation", Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 37(2), pp.254~255 (2007)
- Y. Kuniyoshi, "Teaching by showing: Generating robot programs by visual observation of human performance", in Proc. of the 20th International Symp. on Industrial Robots, pp.119~126 (1989)
- Y. Kuniyoshi, "Learning by watching : Extracting reusable task knowledge from visual observation of human performance", Robotics and Automation, IEEE Transactions on, 10(6), pp.799~822 (1994)
- B. Argall, "A survey of robot learning from demonstration", Robotics and Autonomous Systems, 57(5), pp.469~483 (2009)
- C. Nehaniv, "Imitation in Animals and Artifacts" (2002), MIT Press
- D. Lee, "Mimetic communication model with compliant physical contact in human-humanoid interaction", The International Journal of Robotics Research, 29(13), pp.684~1704 (2010)
- T. Inamura, "Keyframe compression and decompression for time series data based on the continuous hidden markov model", in Intelligent Robots and Systems (IROS), 2011 IEEE, 2011, 344~349
- S. Calinon, "Incremental learning of gestures by imitation in a humanoid robot", in Proceedings of the ACM, 2007, 255~262[DOI]
- S. Calinon, "On learning, representing, and generalizing a task in a humanoid robot", Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 37(2), pp.286~298 (2007)
- M. Muhlig, "Task level imitation learning using variance-based movement optimization", in Robotics and Automation, 2009. ICRA’09. IEEE International Conference on, pp.1177~1184 (2009), IEEE
- A. Ijspeert, "Movement imitation with nonlinear dynamical systems in humanoid robots", in Robotics and Automation, 2002. Proceedings. ICRA’02. IEEE International Conference on, 2, pp.1398~1403 (2002), IEEE
- S. Schaal, "Computational approaches to motor learning by imitation", Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, 358(1431), pp.537~547 (2003)
- V. Koropouli, "Learning interaction control policies by demonstration", in Intelligent Robots and Systems (IROS), 2011 IEEE, 2011, 344~349[DOI]
- H. Hoffmann, "Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance", in Robotics and Automation, 2009. ICRA’09. IEEE International Conference on, pp.2587~2592 (2009), IEEE
- F. Meier, "Movement segmentation using a primitive library", in Intelligent Robots and Systems (IROS), 2011 IEEE, 2011, 3407~3412[DOI]
- C. Atkeson, "Locally weighted learning", Artificial intelligence review, 11(1), pp.11~73 (1997)
- L. Aiken, "Multiple linear regression" (2003), Handbook of psychology
- "RoboticsLab"[URL]
- D. Ruspini, "Beyond the looking glass: the haptic exploration of virtual environments" (2003), Stanford University