Access the full text.
Sign up today, get DeepDyve free for 14 days.
B. Ugurlu, N. Tsagarakis, Emmanouil Spyrakos-Papastavridis, D. Caldwell (2011)
Compliant joint modification and real-time dynamic walking implementation on bipedal robot cCub2011 IEEE International Conference on Mechatronics
A. Jafari, N. Tsagarakis, D. Caldwell (2013)
A Novel Intrinsically Energy Efficient Actuator With Adjustable Stiffness (AwAS)IEEE/ASME Transactions on Mechatronics, 18
A. Moore, C. Atkeson (2004)
The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spacesMachine Learning, 21
Shuhei Shimmyo, Tomoya Sato, K. Ohnishi (2013)
Biped Walking Pattern Generation by Using Preview Control Based on Three-Mass ModelIEEE Transactions on Industrial Electronics, 60
International Journal of Humanoid Robotics c ○ World Scientific Publishing Company An Analytical Method on Real-time Gait Planning for a Humanoid Robot
J Morimoto, CG Atkeson (2007)
Learning biped locomotion: Application of poincare-map-based reinforcement learningIEEE Robotics and Automation Magazine, 14
M. Ishikawa, P. Komi, M. Grey, V. Lepola, G. Bruggemann (2005)
Muscle-tendon interaction and elastic energy usage in human walking.Journal of applied physiology, 99 2
K. Koch, Debora Clever, K. Mombaur, Dominik Endres (2015)
Learning movement primitives from optimal and dynamically feasible trajectories for humanoid walking2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)
A. Bernstein, N. Shimkin (2010)
Adaptive-resolution reinforcement learning with polynomial exploration in deterministic domainsMachine Learning, 81
F. Stulp, J. Buchli, Evangelos Theodorou, S. Schaal (2010)
Reinforcement learning of full-body humanoid motor skills2010 10th IEEE-RAS International Conference on Humanoid Robots
Adam Coates, P. Abbeel, A. Ng (2009)
Apprenticeship learning for helicopter controlCommun. ACM, 52
M. Deisenroth, R. Calandra, A. Seyfarth, Jan Peters (2012)
Toward fast policy search for learning legged locomotion2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
F. Guenter, M. Hersch, S. Calinon, A. Billard (2007)
Reinforcement learning for imitating constrained reaching movementsAdvanced Robotics, 21
Alexander Herzog, S. Schaal, L. Righetti (2016)
Structured contact force optimization for kino-dynamic motion generation2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Petar Kormushev, B. Ugurlu, S. Calinon, N. Tsagarakis, D. Caldwell (2011)
Bipedal walking energy minimization by reinforcement learning with evolving policy parameterization2011 IEEE/RSJ International Conference on Intelligent Robots and Systems
T. Sugihara, Yoshihiko Nakamura (2009)
Boundary Condition Relaxation Method for Stepwise Pedipulation Planning of Biped RobotsIEEE Transactions on Robotics, 25
M. Rosenstein, A. Barto, R. Emmerik (2006)
Learning at the level of synergies for a robot weightlifterRobotics Auton. Syst., 54
R. Calandra, A. Seyfarth, Jan Peters, M. Deisenroth (2014)
An experimental comparison of Bayesian optimization for bipedal locomotion2014 IEEE International Conference on Robotics and Automation (ICRA)
H. Geyer, A. Seyfarth, R. Blickhan (2006)
Compliant leg behaviour explains basic dynamics of walking and runningProceedings of the Royal Society B: Biological Sciences, 273
Stefan Schaal, A. Ijspeert, A. Billard (2003)
Computational approaches to motor learning by imitation.Philosophical transactions of the Royal Society of London. Series B, Biological sciences, 358 1431
D. Orin, A. Goswami, Sung-Hee Lee (2013)
Centroidal dynamics of a humanoid robotAutonomous Robots, 35
Jan Peters, S. Schaal (2006)
Policy Gradient Methods for Robotics2006 IEEE/RSJ International Conference on Intelligent Robots and Systems
T. McGeer (1990)
Passive Dynamic WalkingThe International Journal of Robotics Research, 9
J. Kober, Jan Peters (2009)
Learning motor primitives for robotics2009 IEEE International Conference on Robotics and Automation
Petar Kormushev, D. Nenchev, S. Calinon, D. Caldwell (2011)
Upper-body kinesthetic teaching of a free-standing humanoid robot2011 IEEE International Conference on Robotics and Automation
B. Ugurlu, J. Saglia, N. Tsagarakis, Stephen Morfey, D. Caldwell (2014)
Bipedal Hopping Pattern Generation for Passively Compliant Humanoids: Exploiting the ResonanceIEEE Transactions on Industrial Electronics, 61
Nate Kohl, P. Stone (2004)
Machine Learning for Fast Quadrupedal Locomotion
Petar Kormushev, S. Calinon, D. Caldwell (2010)
Robot motor skill coordination with EM-based Reinforcement Learning2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
Xiaoxiang Yu, F. Iida (2013)
Minimalistic Models of an Energy-Efficient Vertical-Hopping RobotIEEE Transactions on Industrial Electronics, 61
Qi Liu, Jie Zhao, Steffen Schütz, K. Berns (2015)
Adaptive motor patterns and reflexes for bipedal locomotion on rough terrain2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Yue Hu, Martin Felis, K. Mombaur (2014)
Compliance analysis of human leg joints in level ground walking with an optimal control approach2014 IEEE-RAS International Conference on Humanoid Robots
Jan Peters, S. Schaal (2008)
Reinforcement learning of motor skills with policy gradientsNeural networks : the official journal of the International Neural Network Society, 21 4
Justin Carpentier, S. Tonneau, M. Naveau, O. Stasse, N. Mansard (2016)
A versatile and efficient pattern generator for generalized legged locomotion2016 IEEE International Conference on Robotics and Automation (ICRA)
Nima Shafii, N. Lau, Luis Reis (2015)
Learning to Walk Fast: Optimized Hip Height Movement for Simulated and Real Humanoid RobotsJournal of Intelligent & Robotic Systems, 80
Jan Peters, S. Vijayakumar, S. Schaal (2003)
Natural Actor-CriticNeurocomputing, 71
H. Minakata, H. Seki, S. Tadakuma (2008)
A Study of Energy-Saving Shoes for Robot Considering Lateral Plane MotionIEEE Transactions on Industrial Electronics, 55
Y. Wada, K. Sumita (2004)
A reinforcement learning scheme for acquisition of via-point representation of human motion2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), 2
J. Rosado, Filipe Silva, Vítor Santos (2015)
Biped Walking Learning from Imitation Using Dynamic Movement Primitives
Ronald Williams (1992)
Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 8
(2003)
He was also a finalist for Best Entertainment Robots and Systems-20th Anniversary Award at IROS 2007 and finalist for the Best Manipulation Paper at ICRA 2012 and Best Paper at Humanoids 2012
S. Kagami, T. Kitagawa, K. Nishiwaki, T. Sugihara, M. Inaba, H. Inoue (2002)
A Fast Dynamically Equilibrated Walking Trajectory Generation Method of Humanoid RobotAutonomous Robots, 12
M. Wisse, A. Schwab, R. Linde, F. Helm (2005)
How to keep from falling forward: elementary swing leg action for passive dynamic walkersIEEE Transactions on Robotics, 21
Hao Shen, J. Yosinski, Petar Kormushev, D. Caldwell, Hod Lipson (2012)
Learning Fast Quadruped Robot Gaits with the RL PoWER Spline Parameterization, 12
(2007)
Posture/walking control for humanoid robot based on resolution of CoM Jacobian with embedded motion
Justus Ortega, C. Farley (2005)
Minimizing center of mass vertical movement increases metabolic cost in walking.Journal of applied physiology, 99 6
P. Pastor, Mrinal Kalakrishnan, Sachin Chitta, Evangelos Theodorou, S. Schaal (2011)
Skill learning and task outcome prediction for manipulation2011 IEEE International Conference on Robotics and Automation
Noname manuscript No. (will be inserted by the editor) Policy Search for Motor Primitives in Robotics
Evangelos Theodorou, J. Buchli, S. Schaal (2010)
Reinforcement learning of motor skills in high dimensions: A path integral approach2010 IEEE International Conference on Robotics and Automation
A. Amran, B. Ugurlu, A. Kawamura (2010)
Energy and torque efficient ZMP-based bipedal walking with varying center of mass height2010 11th IEEE International Workshop on Advanced Motion Control (AMC)
Evangelos Theodorou, J. Buchli, S. Schaal (2010)
A Generalized Path Integral Control Approach to Reinforcement LearningJ. Mach. Learn. Res., 11
B. Ugurlu, T. Hirabayashi, A. Kawamura (2009)
A unified control frame for stable bipedal walking2009 35th Annual Conference of IEEE Industrial Electronics
J Kober, J Peters (2011)
Policy search for motor primitives in roboticsMachine Learning, 84
K Harada, S Kajita, K Kaneko, H Hirukawa (2004)
An analytical method on real-time gait planning for a humanoid robotInternational Journal of Humanoid Robotics, 3
Hiroyuki Miyamoto, J. Morimoto, K. Doya, M. Kawato (2004)
Reinforcement learning with via-point representationNeural networks : the official journal of the International Neural Network Society, 17 3
A. Abdolmaleki, N. Lau, Luis Reis, Jan Peters, G. Neumann (2016)
Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking ControllerJournal of Intelligent & Robotic Systems, 83
Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.
Autonomous Robots – Springer Journals
Published: Feb 13, 2018
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.