Modeling multiple autonomous robot behaviors and behavior switching with a single reservoir computing network

Reservoir computing (RC) uses a randomly created Recurrent Neural Network as a reservoir of rich dynamics which projects the input to a high dimensional space. These projections are mapped to the desired output using a linear output layer, which is the only part being trained by standard linear regression. In this work, RC is used for imitation learning of multiple behaviors which are generated by different controllers using an intelligent navigation system for mobile robots previously published in literature. Target seeking and exploration behaviors are conflicting behaviors which are modeled with a single RC network. The switching between the learned behaviors is implemented by an extra input which is able to change the dynamics of the reservoir, and in this way, change the behavior of the system. Experiments show the capabilities of Reservoir Computing for modeling multiple behaviors and behavior switching.

[1]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[2]  Albert-Jan Baerveldt,et al.  Intelligent autonomous navigation for mobile robots: spatial concept acquisition and object discrimination , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

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

[4]  Jun Tani,et al.  Learning to generate articulated behavior through the bottom-up and the top-down interaction processes , 2003, Neural Networks.

[5]  Albert-Jan Baerveldt,et al.  Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[6]  S. Quartz,et al.  Getting to Know You: Reputation and Trust in a Two-Person Economic Exchange , 2005, Science.

[7]  Benjamin Schrauwen,et al.  Mobile robot control in the road sign problem using Reservoir Computing networks , 2008, 2008 IEEE International Conference on Robotics and Automation.

[8]  K. Aberer,et al.  German National Research Center for Information Technology , 2007 .

[9]  Benjamin Schrauwen,et al.  Imitation Learning of an Intelligent Navigation System for Mobile Robots Using Reservoir Computing , 2008, 2008 10th Brazilian Symposium on Neural Networks.

[10]  Herbert Jaeger,et al.  A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach - Semantic Scholar , 2005 .

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

[12]  J.J. Steil,et al.  Backpropagation-decorrelation: online recurrent learning with O(N) complexity , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[13]  Benjamin Schrauwen,et al.  Generative Modeling of Autonomous Robots and their Environments using Reservoir Computing , 2007, Neural Processing Letters.

[14]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[15]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

[16]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

[17]  Benjamin Schrauwen,et al.  Event detection and localization for small mobile robots using reservoir computing , 2008, Neural Networks.