Movement Prediction from Real-World Images Using a Liquid State Machine

Prediction is an important task in robot motor control where it is used to gain feedback for a controller. With such a self-generated feedback, which is available before sensor readings from an environment can be processed, a controller can be stabilized and thus the performance of a moving robot in a real-world environment is improved. So far, only experiments with artificially generated data have shown good results. In a sequence of experiments we evaluate whether a liquid state machine in combination with a supervised learning algorithm can be used to predict ball trajectories with input data coming from a video camera mounted on a robot participating in the RoboCup. This pre-processed video data is fed into a recurrent spiking neural network. Connections to some output neurons are trained by linear regression to predict the position of a ball in various time steps ahead. Our results support the idea that learning with a liquid state machine can be applied not only to designed data but also to real, noisy data.

[1]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[2]  H. Markram,et al.  Differential signaling via the same axon of neocortical pyramidal neurons. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[3]  P. S. Maybeck,et al.  The Kalman Filter: An Introduction to Concepts , 1990, Autonomous Robot Vehicles.

[4]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[6]  Yun Wang,et al.  Synaptic connections and small circuits involving excitatory and inhibitory neurons in layers 2-5 of adult rat and cat neocortex: triple intracellular recordings and biocytin labelling in vitro. , 2002, Cerebral cortex.

[7]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[8]  R. Legenstein,,et al.  Input Prediction and Autonomous Movement Analysis in Recurrent Circuits of Spikitfg Neurons , 2003, Reviews in the neurosciences.

[9]  Alexander Ferrein,et al.  On-Line Decision-Theoretic Golog for Unpredictable Domains , 2004, KI.

[10]  Seong-Whan Lee,et al.  Biologically Motivated Computer Vision , 2002, Lecture Notes in Computer Science.

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[13]  M. Paradiso,et al.  Neuroscience: Exploring the Brain , 1996 .

[14]  Gordon Fraser,et al.  A Modular Architecture for a Multi-purpose Mobile Robot , 2004, IEA/AIE.

[15]  Gordon Fraser,et al.  A modular architecture for a multi-purpose mobile robot , 2004 .

[16]  Zoubin Ghahramani,et al.  Computational motor control , 2004 .

[17]  Henry Markram,et al.  A New Approach towards Vision Suggested by Biologically Realistic Neural Microcircuit Models , 2002, Biologically Motivated Computer Vision.

[18]  H. Markram,et al.  Organizing principles for a diversity of GABAergic interneurons and synapses in the neocortex. , 2000, Science.

[19]  Henry Markram,et al.  Computational models for generic cortical microcircuits , 2004 .

[20]  Leon O. Chua,et al.  Fading memory and the problem of approximating nonlinear operators with volterra series , 1985 .

[21]  A. PearlmutterB..  Gradient calculations for dynamic recurrent neural networks , 1995 .