期刊
IEEE ACCESS
卷 9, 期 -, 页码 136580-136592出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3113080
关键词
Control systems; Observers; Adaptive systems; Uncertainty; Fuzzy logic; Vehicle dynamics; Reinforcement learning; Saturation function; reinforcement learning; prescribed performance; high-gain observer; interval type-2 fuzzy neural networks; multilayer neural networks
资金
- Engineering and Physical Sciences Research Council (EPSRC) [EP/V027379/1, EP/R02572X/1]
- National Centre for Nuclear Robotics (NCNR)
- EPSRC [EP/R02572X/1, EP/V027379/1] Funding Source: UKRI
In this paper, a new neuro-fuzzy reinforcement learning-based control structure is proposed for precise trajectory tracking of autonomous underwater vehicles. By integrating multiple neural networks and fuzzy neural networks with a high-gain observer, a robust smart observer system is established to accurately estimate the velocities and dynamic parameters of AUVs.
In this brief, we propose a new neuro-fuzzy reinforcement learning-based control (NFRLC) structure that allows autonomous underwater vehicles (AUVs) to follow a desired trajectory in large-scale complex environments precisely. The accurate tracking control problem is solved by a unique online NFRLC method designed based on actor-critic (AC) structure. Integrating the NFRLC framework including an adaptive multilayer neural network (MNN) and interval type-2 fuzzy neural network (IT2FNN) with a high-gain observer (HGO), a robust smart observer-based system is set up to estimate the velocities of the AUVs, unknown dynamic parameters containing unmodeled dynamics, nonlinearities, uncertainties and external disturbances. By employing a saturation function in the design procedure and transforming the input limitations into input saturation nonlinearities, the risk of the actuator saturation is effectively reduced together with nonlinear input saturation compensation by the NFRLC strategy. A predefined funnel-shaped performance function is designed to attain certain prescribed output performance. Finally, stability study reveals that the entire closed-loop system signals are semi-globally uniformly ultimately bounded (SGUUB) and can provide prescribed convergence rate for the tracking errors so that the tracking errors approach to the origin evolving inside the funnel-shaped performance bound at the prescribed time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据