scholarly journals Path Planning for Autonomous Driving of Mobile Robots using Deep Neural Network based Model Predictive Control

2021 ◽  
Vol 11 (11) ◽  
pp. 31-38
Author(s):  
Kiwon Yeom ◽  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Model Predictive Control ◽  
Mobile Robot ◽  
Predictive Control ◽  
Deep Neural Network ◽  
Optimal Solution ◽  
Autonomous Driving ◽  
Physical Constraints ◽  
Predictive Controller

A car-like mobile robot is a nonlinear affine system, and the mobile robot has physical constraints such as velocity and acceleration. Thus, no satisfactory solution may not be provided during self-driving under unknown environments. Although Model Predictive Control (MPC) has provided good performance in terms of control strategy, it is difficult to optimize the control parameters due to the uncertainty and non-linearity of a process. In this paper, the Deep Neural Networks (DNN) based Model Predictive Controller (MPC) is derived for tracking the given path during self-driving. The proposed DNN MPC produces the global optimal solution which has better performance than traditional MPC in terms of the errors of position and orientation. This paper verifies that the proposed DNN MPC based controller can track the desired path with high precision for the car-like mobile robot. Keywords—Path planning, autonomous driving, mobile robot, deep neural network, model predictive control.

scholarly journals Nonlinear Model Predictive Control for Mobile Robot Using Varying-Parameter Convergent Differential Neural Network

Robotics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 64 ◽  
Author(s):  
Yingbai Hu ◽  
Hang Su ◽  
Longbin Zhang ◽  
Shu Miao ◽  
Guang Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Mobile Robot ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Network Structure ◽  
Kinematic Model ◽  
Optimal Solution ◽  
Nonlinear Model Predictive Control ◽  
Neural Network Structure

The mobile robot kinematic model is a nonlinear affine system, which is constrained by velocity and acceleration limits. Therefore, the traditional control methods may not solve the tracking problem because of the physical constraint. In this paper, we present the nonlinear model predictive control (NMPC) algorithm to track the desired trajectory based on neural-dynamic optimization. In the proposed algorithm, the NMPC scheme utilizes a new neural network named the varying-parameter convergent differential neural network (VPCDNN) which is a Hopfifield-neural network structure with respect to the differential equation theory to solve the quadratic programming (QP) problem. The new network structure converges to the global optimal solution and it is more efficient than traditional numerical methods. In the simulation, we verify that the proposed method is able to successfully track reference trajectories with a two-wheel mobile robot. The experimental validation has been conducted in simulation and the results show that the proposed method is able to precisely track the trajectory maintaining a high robustness based on the VPCDNN solver.

A method for avoiding obstacles of a self-driving carin the dynamic environment based on model predictive control

2021 ◽  
Author(s):  
N.P. Demenkov ◽  
Kai Zou
Keyword(s):  
Path Planning ◽  
Model Predictive Control ◽  
Urban Environment ◽  
Predictive Control ◽  
Potential Field ◽  
Dynamic Environment ◽  
Field Method ◽  
Artificial Potential Field ◽  
Physical Constraints ◽  
Local Path

The paper discusses the problem of obstacle avoidance of a self-driving car in urban road conditions. The artificial potential field method is used to simulate traffic lanes and cars in a road environment. The characteristics of the urban environment, as well as the features and disadvantages of existing methods based on the structure of planning-tracking, are analyzed. A method of local path planning is developed, based on the idea of an artificial potential field and model predictive control in order to unify the process of path planning and tracking to effectively cope with the dynamic urban environment. The potential field functions are introduced into the path planning task as constraints. Based on model predictive control, a path planning controller is developed, combined with the physical constraints of the vehicle, to avoid obstacles and execute the expected commands from the top level as the target for the task. A joint simulation was performed using MATLAB and CarSim programs to test the feasibility of the proposed path planning method. The results show the effectiveness of the proposed method.

Aero-engine direct thrust control with nonlinear model predictive control based on linearized deep neural network predictor

2019 ◽  
Vol 234 (3) ◽  
pp. 330-337 ◽  
Author(s):  
Qiangang Zheng ◽  
Yong Wang ◽  
Fengyong Sun ◽  
Haibo Zhang
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Deep Neural Network ◽  
Sliding Window ◽  
Nonlinear Model Predictive Control ◽  
Thrust Control ◽  
Direct Thrust Control ◽  
Linearized Model

A novel nonlinear model predictive control method for aero-engine direct thrust control is proposed to improve engine response ability and reduce computational complexity of nonlinear model predictive control. The control objective of the proposed method is the thrust directly instead of the measurable parameters. The linearized model based on online sliding window deep neural network is proposed as predictive model. The online sliding window deep neural network has strong fitting capacity for nonlinear object and adopted to fitting the transient process of engine. The back propagation is adopted to obtain linearized model of online sliding window deep neural network, which greatly reduce the calculated amount. The comparison simulations of the popular nonlinear model predictive control based on extended Kalman filter and the proposed one are carried out. The simulation results show that compared with the popular nonlinear model predictive control, the proposed nonlinear model predictive control not only has the better response ability but also has reduced computational complexity greatly, nearly reduce computation time more than 35 ms.

scholarly journals INTEGRATION OF MOTION PLANNING AND MODEL-PREDICTIVE-CONTROL-BASED CONTROL SYSTEM FOR AUTONOMOUS ELECTRIC VEHICLES

Transport ◽  
2015 ◽  
Vol 30 (3) ◽  
pp. 353-360 ◽  
Author(s):  
Guodong Yin ◽  
Jianghu Li ◽  
Xianjian Jin ◽  
Chentong Bian ◽  
Nan Chen
Keyword(s):  
Control System ◽  
Model Predictive Control ◽  
Motion Planning ◽  
Predictive Control ◽  
Electric Vehicles ◽  
Autonomous Driving ◽  
Planning System ◽  
Time Interval ◽  
Physical Constraints ◽  
Autonomous Electric Vehicles

This paper introduces the development of an autonomous driving system in autonomous electric vehicles, which consists of a simplified motion-planning program and a Model-Predictive-Control-Based (MPC-based) control system. The motion-planning system is based on polynomial parameterization, which computes a path toward the expected longitudinal and lateral positions within required time interval in real scenarios. Then the MPC-based control system cooperates the front steering and individual wheel torques to track the planned trajectories, while fulfilling the physical constraints of actuators. The proposed system is evaluated through simulation, using a seven-degrees-offreedom vehicle model with a ‘magic formula’ tire model. The simulations and validation through CarSim show that the proposed planner algorithm and controller are feasible and can achieve requirements of autonomous driving in normal scenarios.

scholarly journals Performance Analysis of Deep Neural Network Controller for Autonomous Driving Learning from a Nonlinear Model Predictive Control Method

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 767
Author(s):  
Taekgyu Lee ◽  
Yeonsik Kang
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Deep Neural Network ◽  
Nonlinear Model Predictive Control ◽  
Control Technique ◽  
Computational Time ◽  
Target System ◽  
Neural Network Controller

Nonlinear model predictive control (NMPC) is based on a numerical optimization method considering the target system dynamics as constraints. This optimization process requires large amount of computation power and the computation time is often unpredictable which may cause the control update rate to overrun. Therefore, the performance must be carefully balanced against the computational time. To solve the computation problem, we propose a data-based control technique based on a deep neural network (DNN). The DNN is trained with closed-loop driving data of an NMPC. The proposed "DNN control technique based on NMPC driving data" achieves control characteristics comparable to those of a well-tuned NMPC within a reasonable computation period, which is verified with an experimental scaled-car platform and realistic numerical simulations.

Sign in / Sign up

Export Citation Format

Share Document