Intelligent driving trajectory tracking control algorithm based on deep learning

Author(s):  
Yuzhe Shang ◽  
Wei Qiao
IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 59470-59484 ◽  
Author(s):  
Jingwei Cao ◽  
Chuanxue Song ◽  
Silun Peng ◽  
Shixin Song ◽  
Xu Zhang ◽  
...  

2021 ◽  
Author(s):  
Xuting Duan ◽  
Qi Wang ◽  
Daxin Tian ◽  
Jianshan Zhou ◽  
Jian Wang ◽  
...  

2021 ◽  
Author(s):  
Rui Deng ◽  
Qingfang Zhang ◽  
Rui Gao ◽  
Mingkang Li ◽  
Peng Liang ◽  
...  

2018 ◽  
Vol 25 (3) ◽  
pp. 26-34 ◽  
Author(s):  
Yong Liu ◽  
Renxiang Bu ◽  
Xiaori Gao

Abstract The paper reports the design and tests of the planar autopilot navigation system in the three-degree-of-freedom (3-DOF) plane (surge, sway and yaw) for a ship. The aim of the tests was to check the improved maneuverability of the ship in open waters using the improved nonlinear control algorithm, developed based on the sliding mode control theory for the ship-trajectory tracking problem of under-actuated ships with static constraints, actuator saturation, and parametric uncertainties. With the integration of the simple increment feedback control law, the dynamic control strategy was developed to fulfill the under-actuated tracking and stabilization objectives. In addition, the LOS (line of sight) guidance system was applied to control the motion path, whereas the sliding mode controller was used to emulate the rudder angle and propeller rotational speed control. Firstly, simulation tests were performed to verify the validity of the basic model and the tracking control algorithm. Subsequently, full scale maneuverability tests were done with a novel container ship, equipped with trajectory tracking control and sliding mode controller algorithm, to check the dynamic stability performance of the ship. The results of the theoretical and numerical simulation on a training ship verify the invariability and excellent robustness of the proposed controller, which: effectively eliminates system chattering, solves the problem of lateral drift of the ship, and maintains the following of the trajectory while simultaneously achieving global stability and robustness.


2021 ◽  
Vol 2021 ◽  
pp. 1-22
Author(s):  
Wenli Sun ◽  
Xu Gao

Trajectory tracking control based on waypoint behavior is a promising way for unmanned surface vehicle (USV) to achieve autonomous navigation. This study is aimed at the guidance progress in the kinematics; the artificial intelligence method of deep learning is adopted to improve the trajectory tracking level of USV. First, two deep neural network (DNN) models are constructed to evaluate navigation effects and to estimate guidance law parameters in real time, respectively. We then pretrain the DNN using a Gaussian–Bernoulli restricted Boltzmann machine to further improve the accuracy of predicting navigation effect. Finally, two DNNs are connected in parallel with the control loop of USV to provide predictive supervision and auxiliary decision making for traditional control methods. This kind of parallel way conforms to the ship manipulation of habit. Furthermore, we develop a new application on the basis of Mission Oriented Operating Suite Interval Programming named “pDeepLearning.” It can predict the navigation effect online by DNN and adjust the guidance law parameters according to the effect level. The experimental results show that, compared with the original waypoint behavior of USV, the prediction model proposed in this study reduces the trajectory tracking error by 19.0% and increases the waypoint behavior effect level.


2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Xianghua Ma ◽  
Yang Zhao ◽  
Yiqun Di

A new trajectory tracking control method based on the U-model is proposed to improve the trajectory tacking speed of robot manipulators. The U-model method is introduced to relieve the requirement of the dynamic mathematical model and make the design of trajectory tracking controller of robot manipulators simpler. To further improve the trajectory tacking speed, an improved iterative learning control algorithm is used to suppress the influence of the initial state error with less computation time. Experimental results show that the proposed control method is effective and practical for the trajectory tracking control of robot manipulators, especially with a high real-time requirement.


Sign in / Sign up

Export Citation Format

Share Document