scholarly journals Predictive Course Control and Guidance of Autonomous Unmanned Sailboat Based on Efficient Sampled Gaussian Process

2021 ◽  
Vol 9 (12) ◽  
pp. 1420
Author(s):  
Yuqin Dong ◽  
Nailong Wu ◽  
Jie Qi ◽  
Xinyuan Chen ◽  
Chenhua Hua
Keyword(s):  
Model Predictive Control ◽  
Gaussian Process ◽  
Predictive Control ◽  
Process Model ◽  
Fast Response ◽  
Feature Model ◽  
Tracking Accuracy ◽  
Navigation Data ◽  
Adaptive Weight ◽  
Predictive Controller

In view of the vulnerability of ocean unmanned sailboats to the large lateral velocities due to wind and waves during navigation, this paper proposes a Gaussian Process Model Predictive Control (GPMPC) method based on data-driven learning technique to improve the navigation tracking accuracy of unmanned sailboats. The feature model of the sailing course change subject to the wind and waves is learned from the efficient sampling data. It is then combined with the model predictive control to form the course controller. To reduce the influence of wind and waves disturbances, an adaptive weight term is designed in the object function to improve the tracking accuracy of the model predictive control. The guidance commands received by the model predictive controller take into account the path deviation caused by the current and lateral motion of the ship. The results show that GPMPC has the advantages of fast response time and less overshoot; the unmanned sailboat can better achieve waypoint tracking by learning navigation data.

Event-triggered nonlinear model predictive control for trajectory tracking of unmanned vehicles

2021 ◽  
pp. 095440702199216
Author(s):  
Kai Zou ◽  
Yingfeng Cai ◽  
Long Chen ◽  
Xiaoqiang Sun
Keyword(s):  
Model Predictive Control ◽  
Real Time ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Unmanned Vehicles ◽  
Tracking Accuracy ◽  
Model Predictive Controller ◽  
Time Performance ◽  
Predictive Controller ◽  
Event Triggered

In order to increase the real-time performance of lateral trajectory tracking of unmanned vehicles, this paper designs an event-triggered nonlinear model predictive controller, which can save computation resource to a large extent while the tracking accuracy is still guaranteed. Firstly, a simplified vehicle is established using a two-degree-of-freedom dynamics model. Then, according to the theory of model predictive control, a nonlinear model predictive controller (NMPC) is designed. Since traditional NMPCs often have poor real-time control performance, this paper introduces an event-triggered mechanism, which allows the remaining elements of the control variables in the control horizon to be applied to the system once a specific condition is satisfied. Finally, the proposed controller is established by Matlab/Simulink, and the different trigger conditions are compared and verified in a double lane change maneuvers Then a system for evaluation is designed to quantify the performance of the controller in different trigger conditions. For further verification of the proposed controller, a Hard-in-the-loop simulation system based on Xpack package is established to conduct an HIL experiment. The results show that compared with traditional nonlinear model predictive control, our method offers greatly improved real-time performance while the tracking accuracy is guaranteed.

scholarly journals LVD-NMPC: A learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles

2021 ◽  
Vol 18 (3) ◽  
pp. 172988142110195
Author(s):  
Sorin Grigorescu ◽  
Cosmin Ginerica ◽  
Mihai Zaha ◽  
Gigel Macesanu ◽  
Bogdan Trasnea
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Autonomous Vehicles ◽  
Process Model ◽  
Network Performance ◽  
Vision System ◽  
Nonlinear Model Predictive Control ◽  
Scaled Model

In this article, we introduce a learning-based vision dynamics approach to nonlinear model predictive control (NMPC) for autonomous vehicles, coined learning-based vision dynamics (LVD) NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to calculate the dynamics of the driving scene, the controlled system’s desired state trajectory, and the weighting gains of the quadratic cost function optimized by a constrained predictive controller. The vision system is defined as a deep neural network designed to estimate the dynamics of the image scene. The input is based on historic sequences of sensory observations and vehicle states, integrated by an augmented memory component. Deep Q-learning is used to train the deep network, which once trained can also be used to calculate the desired trajectory of the vehicle. We evaluate LVD-NMPC against a baseline dynamic window approach (DWA) path planning executed using standard NMPC and against the PilotNet neural network. Performance is measured in our simulation environment GridSim, on a real-world 1:8 scaled model car as well as on a real size autonomous test vehicle and the nuScenes computer vision dataset.

Sign in / Sign up

Export Citation Format

Share Document