An on-line adaptation method in a neural network based control system for AUVs

A neural network based control system "Self-Organizing Neural-Net-Controller System: SONCS" has been developed as an adaptive control system for Autonomous Underwater Vehicles (AUVs). In this paper, an on-line adaptation method "Imaginary Training" is proposed to improve the time-consuming adaptation process of the original SONCS. The Imaginary Training can be realized by a parallel structure which enables the SONCS to adjust the controller network independently of actual operation of the controlled object. The SONCS is divided into two separate parts: the Real-World Part where the controlled object is operated according to the objective, and the Imaginary-World Part where the Imaginary Training is carried out. In order to adjust the controller network by the Imaginary Training, it is necessary to introduce a forward model network which can generate simulated state variables without involving actual data. A neural network "Identification Network" which has a specific structure to simulate the behavior of dynamical systems is proposed as the forward model network. The effectiveness of the Imaginary Training is demonstrated by applying to the heading keeping control of an AUV "Twin-Burger". It is shown that the SONCS adjusts the controller network-through on-line processes in parallel with the actual operation. >

[1]  James G. Bellingham,et al.  Keeping layered control simple (autonomous underwater vehicles) , 1990, Symposium on Autonomous Underwater Vehicle Technology.

[2]  Jean-Jacques E. Slotine,et al.  The influence of thruster dynamics on underwater vehicle behavior and their incorporation into control system design , 1990 .

[3]  Tamaki Ura,et al.  Development of motion control system for AUV using neural nets , 1990, Symposium on Autonomous Underwater Vehicle Technology.

[4]  Jean-Jacques E. Slotine,et al.  Robust trajectory control of underwater vehicles , 1985 .

[5]  Tamaki Ura,et al.  CONTROL WITH NEURAL NETWORK FOR AUTONOMOUS UNDERWATER VEHICLE - APPLICATION TO LONGITUDINAL MOTION CONTROL , 1989 .

[6]  S. Chappell,et al.  A blackboard based system for context sensitive mission planning in an autonomous vehicle , 1987, Proceedings of the 1987 5th International Symposium on Unmanned Untethered Submersible Technology.

[7]  Tamaki Ura,et al.  A quick adaptation method in a neural network based control system for AUVs , 1994, Proceedings of IEEE Symposium on Autonomous Underwater Vehicle Technology (AUV'94).

[8]  A. J. Healey,et al.  Adaptive sliding mode control of autonomous underwater vehicles in the dive plane , 1990 .

[9]  Shin Morishita,et al.  Damping-controllable dynamic damper with neural network based adaptive control system , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[10]  Tamaki Ura,et al.  SONCS: Self-organizing neural-net-controller system for autonomous underwater robots , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[11]  Tamaki Ura,et al.  Development of a versatile test-bed "Twin-Burger" toward realization of intelligent behaviors of autonomous underwater vehicles , 1993, Proceedings of OCEANS '93.

[12]  Kenichi Asakawa,et al.  Cable tracking for autonomous underwater vehicle , 1994, Proceedings of IEEE Symposium on Autonomous Underwater Vehicle Technology (AUV'94).

[13]  Junku Yuh,et al.  A neural net controller for underwater robotic vehicles , 1990 .

[14]  Tamaki Ura,et al.  Self-organizing Control System For Underwater Vehicles , 1990, Conference Proceedings on Engineering in the Ocean Environment.

[15]  T. Ura,et al.  A feedforward neural network for identification and adaptive control of autonomous underwater vehicles , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[16]  A. J. Healey,et al.  Experimental verification of mission planning by autonomous mission execution and data visualization using the NPS AUV II , 1992, Proceedings of the 1992 Symposium on Autonomous Underwater Vehicle Technology.