We also collaborate with the Department of Humanoid Robotics and Computational Neuroscience at ATR
Research in neuroscience and motor psychology has made tremendous progress in generating better understanding of how the human brain generates motor behaviors. At the same time robotics and computer graphics have created increasingly impressive examples of theories and implementations of a variety of movement behaviors, as seen in humanoid robotics and interactive animations and games. Despite this progress, however, a major shortcoming in all these disciplines remains an understanding of how complex movements that we make every day can be created and combined flexibly, robustly, and autonomously. The goal of this project is to develop and evaluate comprehensive information processing models of human motor behavior, to overcome these shortcomings. The PIs will investigate the algorithms and representations (such as what is stored in long term memory) that enable the skilled behavior we see every day, using studies of behavior and evaluations of our ideas on humanoid robots and in simulation. It brings together a set of researchers who have individually or in small collaborations addressed fragments of this challenge. The PIs have been successful in investigating individual and highly specialized motor tasks, but have not yet integrated a significant number of behaviors such that a robot or simulation could autonomously and robustly interact with a dynamic environment. Members of this team have built biologically inspired locomoting and humanoid robots that balance; walk and run on both flat terrain, inclines, and stairs at a wide range of speeds; accurately place their feet while walking and running; jump and leap; jump through hoops; perform flips; recover from slips, trips, and stumbles; compliantly interact with humans; throw, catch, hit, and juggle balls; devilstick; and play air hockey. They have received equipment funding to develop a next generation humanoid in collaboration with Sarcos, from the NSF CISE Collaborative Research Resources (Research Infrastructure) Program. This humanoid experimental testbed will allow them to develop and evaluate their proposals as to how behavior is generated much more effectively. In the past, this group and others have focused on modeling single tasks. This project focuses on developing and testing approaches to coordinate many behaviors, and handle behavior selection, multiple tasks, behavioral transitions, and error compensation, making the crucial step from highly specialized investigations to a more general theory of information processing in human motor control.
Sensory Adaptation in Human Balance Control: Lessons for Biomimetic Robotic Bipeds, Arash Mahboobin, Patrick J. Loughlin, Mark S. Redfern, Stuart O. Anderson, Christopher G. Atkeson, and Jessica K. Hodgins. Neural Networks, in press.
Random Sampling of States in Dynamic Programming, C. G. Atkeson and B. Stephens, Neural Information Processing Systems (NIPS) Conference, 2007.
Multiple Balance Strategies From One Optimization Criterion, Christopher Atkeson and Benjamin Stephens, Humanoids 2007.
Humanoid Push Recovery, Benjamin Stephens, Humanoids 2007.
Compliant Control of a Hydraulic Humanoid Joint, Darrin Bentivegna, Christopher Atkeson and Jung-Yup Kim, Humanoids 2007.
Online Gain Switching Algorithm for Joint Position Control of a Hydraulic Humanoid Robot, Jung-Yup Kim, Christopher Atkeson, Jessica Hodgins, Darrin Bentivegna and Sung Ju Cho, Humanoids 2007.
Approximate Policy Transfer applied to Simulated Bongo Board Balance, Anderson, S. O. and Hodgins, J. K. and Atkeson, C. G. IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2007.
Identifying Trajectory Classes in Dynamic Tasks, Anderson, S.O. and Srinivasa, S., International Symposium on Approximate Dynamic Programming and Reinforcement Learning, 2007.
Knowledge transfer using local features. Martin Stolle and Christopher G. Atkeson. In Proceedings of the IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007), 2007.
Integral Control of Humanoid Balance, B. Stephens, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2007.
Transfer of policies based on trajectory libraries, Martin Stolle and Christopher Atkeson, In Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2007
Randomly Sampling Actions In Dynamic Programming, C. G. Atkeson, IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL), 2007.
Learning Biped Locomotion: Application of Poincare-map-based reinforcement learning, Jun Morimoto and Christopher G. Atkeson, IEEE Robotics & Automation Magazine, 14(2):41-51 June 2007.
Improving humanoid locomotive performance with learnt approximated dynamics via Gaussian processes for regression Jun Morimoto, Christopher G. Atkeson, Gen Endo, and Gordon Cheng, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2007, 4234-4240.
Constrained Least-Squares Optimization for Robust Estimation of Center of Rotation, L.Y. Chang and N. Pollard, Journal of Biomechanics, Vol. 40, No. 6, 2007, pp. 1392 - 1400.
Feature Selection for Grasp Recognition from Optical Markers, L.Y. Chang, N. Pollard, T. Mitchell, and E.P. Xing Proceedings of the 2007 IEEE/RSJ Intl. Conference on Intelligent Robots and Systems (IROS 2007), October, 2007, pp. 2944-2950.
Robust estimation of dominant axis of rotation, L.Y. Chang and N. Pollard, Journal of Biomechanics, Vol. 40, No. 12, 2007, pp. 2707-2715.
Responsive Characters from Motion Fragments, J. McCann and N. Pollard, ACM Transactions on Graphics (SIGGRAPH), 26(3), 2007.
Data driven grasp synthesis using shape matching and task-based pruning, Y. Li, J. Fu, and N. Pollard IEEE Transactions on Visualization and Computer Graphics, Vol. 13, 2007.
Planar Batting with Shape and Pose Uncertainty, J. L. Fu, S. S. Srinivasa, N. S. Pollard, and B. C. Nabbe, Proceedings of the IEEE International Conference on Robotics and Automation, 2007.
Controlling Velocity In Bipedal Walking: A Dynamic Programming Approach, Thijs Mandersloot, Martijn Wisse, and Christopher G. Atkeson, Humanoids 2006.
Coordinating Feet in Bipedal Balance, Stuart Anderson, Christopher G. Atkeson, and Jessica Hodgins, Humanoids 2006.
Modulation of simple sinusoidal patterns by a coupled oscillator model for biped walking, J. Morimoto and G. Endo and J. Nakanishi and S. Hyon and G. Cheng and D. Bentivegna and C.G. Atkeson, IEEE International Conference on Robotics and Automation, 2006.
Policies based on trajectory libraries. Martin Stolle and Christopher G. Atkeson. In Proceedings of the International Conference on Robotics and Automation (ICRA 2006), 2006.
Planning and Executing Navigation Among Movable Obstacles, M. Stilman, K. Nishiwaki, S. Kagami and J. Kuffner. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct., 2006.
Physics-Based Motion Retiming, James McCann, Nancy S. Pollard, and Siddhartha S. Srinivasa, In ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2006.
On the Importance of Asymmetries in Grasp Quality Metrics for Tendon Driven Hands, J. L. Fu and N. S. Pollard, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 1068-1075, 2006.
Navigation Among Movable Obstacles: Real-Time Reasoning in Complex Environments, M. Stilman and J.J. Kuffner. International Journal of Humanoid Robotics, Vol. 2, No. 4, December, 2005, pp. 479-504.
Powered Bipeds Based on Passive Dynamic Principles, S. O. Anderson, M. Wisse, C. G. Atkeson, J. K. Hodgins, G. J. Zeglin, B. Moyer, Humanoids 2005, p. 110-6.
Swing leg retraction helps biped walking stability, M. Wisse, C. G. Atkeson, D. K. Kloimwieder, Humanoids 2005, p. 295-300.
Dynamic Programming in Reduced Dimensional Spaces: Dynamic Planning for Robust Biped Locomotion, Mike Stilman, Chris Atkeson, James Kuffner and Garth Zeglin, ICRA 2005.
Poincare-map-based Reinforcement Learning for Biped Walking, Jun Morimoto, Jun Nakanishi, Gen Endo, Gordon Cheng, Christopher G. Atkeson, Garth Zeglin, ICRA 2005.
Footstep Planning for the Honda ASIMO Humanoid, J. Chestnutt, M. Lau, K.M. Cheung, J. Kuffner, J.K. Hodgins, and T. Kanade Proceedings of the IEEE International Conference on Robotics and Automation, April, 2005.
Physically Based Grasping, Pollard, N. S. and Zordan, V. B. In 2005 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, August 2005.
A Shape Matching Algorithm for Synthesizing Humanlike Enveloping Grasps, Y. Li and N. S. Pollard, IEEE-RAS International Conference on Humanoid Robots (Humanoids 2005), pp 442-449, 2005.
Learning To Act From Observation and Practice, D.C. Bentivegna and C.G. Atkeson and A. Ude and G. Cheng, International Journal of Humanoid Robotics, 2004.
A Tiered Planning Strategy for Biped Navigation J. Chestnutt and J. Kuffner Proceedings of the IEEE - RAS / RSJ Conference on Humanoid Robots, November, 2004.
Learning from Observation and Practice using Primitives, Darrin C. Bentivegna, Christopher G. Atkeson, and Gordon Cheng. AAAI Fall Symposium Series, Symposium on "Real-life Reinforcement Learning", October 22-24, 2004.
Acquisition of Biped Walking Policy Using an Approximate Poincare Map, Jun Morimoto, Jun Nakanishi, Gen Endo, Gordon Cheng, Christopher G. Atkeson, and Garth Zeglin, IEEE-RAS/RSJ Int. Conf. on Humanoid Robots (Humanoids 2004)/Proceeding CD, (November 2004)
A Simple Reinforcement Learning Algorithm For Biped Walking, Jun Morimoto, Garth Zeglin, Christopher G. Atkeson, and Gordon Cheng, IEEE International Conference on Robotics and Automation, Pages 3030-3035, (April 2004)
Synthesizing Physically Realistic Human Motion in Low-Dimensional, Behavior-Specific Spaces, Alla Safonova, Jessica K. Hodgins, and Nancy S. Pollard, SIGGRAPH 2004.