Abstract
A neural network based robust control system design for the trajectory of Autonomous Underwater Vehicles (AUVs) is presented in this paper. Two types of control structure were used to control prescribed trajectories of an AUV. The vehicle was tested with random disturbances while taxiing under water. The results of the simulation showed that the proposed neural network based robust control system has superior performance in adapting to large random disturbances such as underwater flow. It is proved that this kind of neural predictor could be used in real-time AUV applications.
Highlights
Nowadays, AUVs are widely used for underwater investigations
The proposed simulation model was established on the basis of discrete-event system specification formalism, representative of a discrete-event system simulation
Santhakumar and Asokan analysed dynamic station keeping of an under-actuated flat-fish-type AUV, and proposed a new method of station keeping with the addition of dedicated thrusters [2]
Summary
AUVs are widely used for underwater investigations. Son and Kim [1] investigated manoeuvrable control of an underwater vehicle using a combined discrete-event and discrete-time system simulation. An adaptive neuro-fuzzy sliding-mode-based genetic algorithm control system for a remotely operated vehicle with four degrees of freedom was presented by Moghaddam and Bagheri [3]. The stability of the proposed control law was proven and the performance of the developed controller was verified via simulation on the underwater vehicle. According to the simulation results, the adaptive control system accomplished precise depth control of the biorobotic autonomous underwater vehicle using dorsal fins, in spite of large uncertainties in the system parameters [6]. The simulation results showed that effective depth control was accomplished in spite of the uncertainties in the system parameters and control fin deflection constraints. Simulation results showed effectiveness of the neuro-fuzzy controller for autonomous underwater vehicles.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
