Dynamic Recurrent Neural Network for Biped Robot Equilibrium Control: Preliminary Results

The purpose of the research addressed in this paper is to develop a real time neural control algorithm for the balance of a biped robot. Our approach is based on dynamic recurrent neural networks and dynamic backpropagation through time algorithm. The neural architecture and its learning process are validated on the control of the ROBIAN biped torso. The neural controller described is trained to compensate, by the torso’s joint motions, applied external perturbations. The algorithm is embedded in the real time electronic unit of the robot and online learning is achieved. The learning behavior and the control performances are the preliminary results presented in this paper. These experimental results show the ability and efficiency of the proposed approach.

[1]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

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

[3]  Toshio Fukuda,et al.  Stabilization control of biped locomotion robot based learning with GAs having self-adaptive mutation and recurrent neural networks , 1997, Proceedings of International Conference on Robotics and Automation.

[4]  B. Mohamed,et al.  Emulation of the Dynamic Effects of Human Torso During a Walking Gait , 2004 .

[5]  Shigeo Hirose,et al.  Toward Development of Practical Quadruped Walking Vehicles , 1993, J. Robotics Mechatronics.

[6]  Atsushi Konno,et al.  Design of a 3 DOFs parallel actuated mechanism for a biped hip joint , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[7]  Friedrich Pfeiffer,et al.  The concept of jogging JOHNNIE , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[8]  Hooshang Hemami,et al.  Coordinated three-dimensional motion of the head and torso by dynamic neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Mark J. Randall.  Adaptive neural control of walking robots , 2001 .

[10]  Atsushi Konno,et al.  Design and development of the biped prototype ROBIAN , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[11]  Anthony J. Robinson,et al.  Static and Dynamic Error Propagation Networks with Application to Speech Coding , 1987, NIPS.

[12]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[13]  Toshikazu Kawasaki,et al.  Design and experiments of advanced leg module (HRP-2L) for humanoid robot (HRP-2) development , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Atsuo Takanishi,et al.  Physical interaction between human and a bipedal humanoid robot-realization of human-follow walking , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[15]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[16]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[17]  Andrew L. Kun,et al.  Adaptive dynamic balance of a biped robot using neural networks , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[18]  David W. L. Wang,et al.  Feedforward and deterministic fuzzy control of balance and posture during human gait , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[19]  Shigeo Hirose,et al.  Toward Development of Practical Quadruped Walking Vehicle , 1993 .

[20]  Daniel E. Koditschek,et al.  RHex: A Simple and Highly Mobile Hexapod Robot , 2001, Int. J. Robotics Res..

[21]  Shin-Min Song,et al.  Machines That Walk , 1988 .