An overview of the work at ATR on humanoid robots is given in Atkeson, et al., "Using Humanoid Robots to Study Human Behavior", IEEE Intelligent Systems, 15(4):46-56, 2000).
An overview of work on local learning algorithms is given by:
Atkeson, C. G., Moore, A. W., & Schaal, S.
"Locally Weighted Learning."
Artificial Intelligence Review, 11:11-73, 1997.
gzipped postscript
An overview of local learning applied to robots is given by:
Atkeson, C. G., Moore, A. W., & Schaal, S.
"Locally Weighted Learning for Control."
Artificial Intelligence Review, 11:75-113, 1997.
gzipped postscript
Looking at local learning from a neural network point of view:
Atkeson, C. G., and S. Schaal,
``Memory-Based Neural Networks For Robot Learning'',
Neurocomputing, 9(3):243-69, 1995.
gzipped postscript
A mixture of experts approach to local learning is presented in:
Schaal, S., & Atkeson, C. G.
"From Isolation to Cooperation: An Alternative View of a System of Experts"
In: D.S. Touretzky, and M.E. Hasselmo (Eds.), Advances in Neural Information Processing Systems 8. Cambridge, MA: MIT Press. 1996.
Stefan Schaal, Atkeson, and colleagues have explored new approaches to nonparametric learning, Receptive Field Weighted Regression (RFWR) and Locally Weighted Projection Regression (LWPR), in which receptive fields representing local models are created and maintained during learning. These approaches provide an interesting alternative perspective on locally weighted learning. Unlike the original version of locally weighted learning, these approaches maintain local intermediate data structures such as receptive fields. [Applied Intelligence 2002] [ICRA 2000] [Neural Computation 1998] [NIPS 1997]
How can a robot learn from watching a human?
Atkeson, C. G. and S. Schaal
``Robot Learning From Demonstration'',
Machine Learning: Proceedings of the Fourteenth International
Conference (ICML '97),
Edited by Douglas H. Fisher, Jr.
pp. 12-20,
Morgan Kaufmann, San Francisco, CA,
1997.
gzipped postscript
Bentivegna and Atkeson are currently
focusing on how to learn from observation and
practice using task-level primitives.
Bentivegna web page.
Being able to learn or plan how to do challenging dynamic tasks on high dimensional humanoid robots is a major challenge. Atkeson has emphasized the close links between model-based reinforcement learning, optimization, and planning for dynamic tasks. Dynamic programming provides a methodology for developing planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have developed procedures that allow complex planning and control problems to be solved in a reasonable amount of time. We use second order local plan optimization to generate locally optimal plans and local models of the value function and its derivatives. We combine many local plans to build more global plans. We maintain global consistency of the local models of the value function, guaranteeing that our locally optimal plans are actually globally optimal, up to the resolution of the search procedures. [NIPS 1993 (pdf) (ps.gz)] [NIPS 2002] Morimoto and Atkeson have developed robust versions of the local trajectory planner. [IROS 2003]
Applying local learning to robot learning:
Schaal, S., and C. G. Atkeson,
``Robot Juggling: An Implementation of Memory-based Learning'',
Control Systems Magazine, 14(1):57-71, 1994.
A book describing parametric model-based learning for robots:
C. H. An, C. G. Atkeson, and J. M. Hollerbach,
Model-Based Control of a Robot Manipulator,
MIT Press, Cambridge, Massachusetts, 1988.
Schaal, S., D. Sternad and C. G. Atkeson,
``One-handed Juggling: Dynamical Approaches to a Rhythmic Movement Task'',
Journal of Motor Behavior, 28(2):165-183, 1996.
Schaal, S. and C. G. Atkeson,
``Open Loop Stable Control Strategies for Robot Juggling'',
In: IEEE International Conference on Robotics and Automation,
Vol.3, pp.913-918, Atlanta, Georgia, 1993.