Real-Time Motor Control using Recurrent Neural Networks

2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

Volumn , Issue , 2009, Pages 42-49

  Huh, Dongsung ^a   Todorov, Emanuel ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Stochastic optimal control, Recurrent neural network (RNN), Risk sensitive control, Step response, Attractor dynamics

Indexed keywords

ATTRACTOR DYNAMICS; BUILDING BLOCK; COMPUTATIONAL MODEL; CONJUGATE GRADIENT DESCENTS; GLOBAL CONTROL; LIMIT-CYCLE; MODELING METHOD; MOTOR CONTROL; NEURAL NETWORK TRAINING; OBJECTIVE FUNCTIONS; OPTIMIZATION EFFICIENCY; OPTIMIZATION PROBLEMS; PONTRYAGIN'S MAXIMUM PRINCIPLE; SAMPLING METHOD; SENSORY-MOTOR SYSTEMS; STOCHASTIC OPTIMAL CONTROL; STOCHASTIC OPTIMAL CONTROL, RECURRENT NEURAL NETWORK (RNN), RISK SENSITIVE CONTROL, STEP RESPONSE, ATTRACTOR DYNAMICS;

CONJUGATE GRADIENT METHOD; CONTROLLERS; DYNAMIC PROGRAMMING; DYNAMICS; MOTORS; OPTIMIZATION; REAL TIME CONTROL; REINFORCEMENT; REINFORCEMENT LEARNING; SPEED CONTROL; STEP RESPONSE; STOCHASTIC CONTROL SYSTEMS; SYSTEMS ENGINEERING;

RECURRENT NEURAL NETWORKS;

EID: 67650475902     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2009.4927524     Document Type: Conference Paper

References (15)

1. Optimality principles in sensorimotor control (review) Todorov E (2004). Nature Neuroscience 7(9): 907-915 (Pubitemid 39129496)
2. Optimal feedback control as a theory of motor coordination Todorov E and Jordan M (2002). Nature Neuroscience 5(11): 1226-1235 (Pubitemid 35247183)
3. Fang, Y.; Sejnowski, T. J.; Faster Learning for Dynamic Recurrent Backpropagation, Neural Computation, 2, 270-273, 1990
4. Lockery, S. R.; Fang, Y.; Sejnowski, T. J.; A Dynamic Neural Network Model of Sensorimotor Transformations in the Leech, Neural Computation, 2, 274-282, 1990
5. Jacobson, D.H. (1973). Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games. IEEE Trans. Automatic Control. AC-18: 124-131
6. Iyanaga, S. and Kawada, Y. (Eds.). "Pontrjagin's Maximum Principle." Encyclopedic Dictionary of Mathematics. Cambridge, MA: MIT Press, pp. 295-296, 1980.
7. Georgopoulos, A., Kalaska, J., Caminiti, R., & Massey, J. (1982). On the relations between the direction of two-dimensional arm movements and cell discharge in primate motor cortex. Journal of Neuroscience, 2(11), 1527-1537 (Pubitemid 13178240)
8. Graziano, M.S.A, Taylor, C.S.R and Moore, T., 2002. Complex movements evoked by microstimulation of precentral cortex. Neuron 34, pp. 841-851
9. P. Werbos. The Roots of the Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting, Wiley, New York (1993).
10. Narendra, K.S. and Annaswamy, A.M., 1989. Stable adaptive systems, Prentice-Hall, Englewood Cliffs, NJ
11. D. Prokhorov, G. Puskorius, and L. Feldkamp, Dynamical Neural Networks for Control. In J. Kolen and S. Kremer (Eds.) A Field Guide to Dynamical Recurrent Networks, IEEE Press, 2001.
12. Danil V. Prokhorov: Training Recurrent Neurocontrollers for Robustness With Derivative-Free Kalman Filter. IEEE Transactions on Neural Networks 17(6): 1606-1616 (2006) (Pubitemid 44824271)
13. Ganguli S., Huh D., Sompolinsky H., 2008 Memory traces in dynamical systems. 18970-18975 | PNAS December 2, 2008 | Vol. 105 | no. 4
14. C. E. Rasmussen, "minimize.m", 2006 http://www.kyb.tuebingen. mpg.de/bs/people/carl/code/minimize/
15. Steven H. Collins, Andy Ruina, Russ Tedrake, and Martijn Wisse. Efficient bipedal robots based on passive-dynamic walkers. Science, 307:1082-1085, February 18 (2005) (Pubitemid 40262108)