Adaptive Dynamic Programming Applied to a 6DoF Quadrotor

2011 ◽  
pp. 102-130 ◽  
Author(s):  
Petru Emanuel Stingu ◽  
Frank L. Lewis
Keyword(s):  
Dynamic Programming ◽  
Cost Function ◽  
Control Policy ◽  
Adaptive Dynamic Programming ◽  
Optimal Controller ◽  
Policy Action ◽  
Adaptive Dynamic ◽  
Quadrotor Helicopter ◽  
The Cost ◽  
Number Of Iterations

This chapter discusses how the principles of Adaptive Dynamic Programming (ADP) can be applied to the control of a quadrotor helicopter platform flying in an uncontrolled environment and subjected to various disturbances and model uncertainties. ADP is based on reinforcement learning. The controller (actor) changes its control policy (action) based on stimuli received in response to its actions by the critic (cost function, reward). There is a cause and effect relationship between action and reward. Reward acts as a reinforcement signal that leads to learning of what actions are likely to generate it. After a number of iterations, the overall actor-critic structure stores information (knowledge) about the system dynamics and the optimal controller that can accomplish the explicit or implicit goal specified in the cost function.

Data-driven active flutter control of airfoil with input constraints based on adaptive dynamic programming method

2021 ◽  
pp. 107754632110011
Author(s):  
Su Jia ◽  
Ye Tang ◽  
Jianqiao Sun ◽  
Qian Ding
Keyword(s):  
Dynamic Programming ◽  
Limit Cycle ◽  
Adaptive Dynamic Programming ◽  
Data Driven ◽  
Optimal Controller ◽  
Limit Cycle Oscillation ◽  
Input Constraints ◽  
Trailing Edge ◽  
Adaptive Dynamic ◽  
Model Free

The stable flight region can be extended by adding control flap at the wing trailing edge and combined with active control technology. We studied the active flutter control by considering the input constraints. By designing the data-driven optimal controller, the limit cycle oscillations of a typical two-dimensional airfoil wing can be suppressed with single trailing edge control surface. The traditional control methods always need a precise mathematical model of the system, which put high requirements on system modeling. In this study, a novel data-driven optimal controller is proposed by using the input–output data and without depending on the nonlinear system dynamic model. This model-free approach avoids the effects of modeling errors and system uncertainty. When the data-driven controller is applied, the limit cycle oscillation phenomenon of the airfoil wing is eliminated within several seconds. It can be seen from the numerical simulation result that the data-driven adaptive dynamic programming control method possess superiority and feasibility.

scholarly journals A tractor-trailer parking control scheme using adaptive dynamic programming

2021 ◽  
Author(s):  
Chenyong Guan ◽  
Yu Jiang
Keyword(s):  
Dynamic Programming ◽  
Online Learning ◽  
Control Policy ◽  
Adaptive Dynamic Programming ◽  
Adaptive Dynamic ◽  
Parking Problem ◽  
Control Scheme ◽  
Learning Capabilities ◽  
Online Measurements ◽  
Linearized System

AbstractThis paper studies the online learning control of a truck-trailer parking problem via adaptive dynamic programming (ADP). The contribution is twofold. First, a novel ADP method is developed for systems with parametric nonlinearities. It learns the optimal control policy of the linearized system at the origin, while the learning process utilizes online measurements of the full system and is robust with respect to nonlinear disturbances. Second, a control strategy is formulated for a commonly seen truck-trailer parallel parking problem, and the proposed ADP method is integrated into the strategy to provide online learning capabilities and to handle uncertainties. A numerical simulation is conducted to demonstrate the effectiveness of the proposed methodology.

scholarly journals Adaptive dynamic programming-based feature tracking control of visual servoing manipulators with unknown dynamics

2021 ◽  
Author(s):  
Xiaolin Ren ◽  
Hongwen Li
Keyword(s):  
Neural Network ◽  
Dynamic Programming ◽  
Cost Function ◽  
Tracking Control ◽  
Feature Tracking ◽  
Visual Servoing ◽  
Error Control ◽  
Lyapunov Theory ◽  
Adaptive Dynamic Programming ◽  
Adaptive Dynamic

AbstractThis paper investigates a feature tracking control method for visual servoing (VS) manipulators adaptive dynamic programming (ADP)-based the unknown dynamics. The major superiority of ADP-based optimal control lies in that the visual tracking problem is converted to the feature tracking error control with optimal cost function. Moreover, an adaptive neural network observer is developed to approximate the entire uncertainties, which are utilized to construct an improved cost function. By establishing a critic neural network, the Hamilton–Jacobi–Bellman (HJB) equation is solved, and the approximate optimal error control policy is derived. The closed-loop VS manipulator system is verified to be ultimately uniformly bounded with the developed ADP-based feature tracking control strategy according to the Lyapunov theory. Finally, simulation results under various situations demonstrate that the proposed method achieves higher tracking accuracy than other methods, as well as satisfies energy optimal requirements.

scholarly journals Adaptive dynamic programing based optimal control for a robot manipulator

2020 ◽  
Vol 11 (3) ◽  
pp. 1123
Author(s):  
Dao Phuong Nam ◽  
Nguyen Hong Quang ◽  
Tran Phuong Nam ◽  
Tran Thi Hai Yen
Keyword(s):  
Optimal Control ◽  
Control Problem ◽  
Robot Manipulator ◽  
Control Policy ◽  
Point Of View ◽  
Adaptive Dynamic Programming ◽  
Exact Linearization ◽  
Constraint Force ◽  
Adaptive Dynamic ◽  
The Cost

<p><span>In this paper, the optimal control problem of a nonlinear robot manipulator in absence of holonomic constraint force based on the point of view of adaptive dynamic programming (ADP) is presented. To begin with, the manipulator was intervened by exact linearization. Then the framework of ADP and Robust Integral of the Sign of the Error (RISE) was developed. The ADP algorithm employs Neural Network technique to tune simultaneously the actor-critic network to approximate the control policy and the cost function, respectively. The convergence of weight as well as position tracking control problem was considered by theoretical analysis. Finally, the numerical example is considered to illustrate the effectiveness of proposed control design. </span></p>

scholarly journals Adaptive dynamic programming enhanced admittance control for robots with environment interaction and actuator saturation

2021 ◽  
Vol 5 (1) ◽  
pp. 89-100
Author(s):  
Hong Zhan ◽  
Dianye Huang ◽  
Chenguang Yang
Keyword(s):  
Dynamic Programming ◽  
Actuator Saturation ◽  
Adaptive Dynamic Programming ◽  
System Stability ◽  
Environment Interaction ◽  
Adaptive Dynamic ◽  
Control Scheme ◽  
Robot Systems ◽  
Hamilton Jacobi Bellman ◽  
The Cost

AbstractThis paper focuses on the optimal tracking control problem for robot systems with environment interaction and actuator saturation. A control scheme combined with admittance adaptation and adaptive dynamic programming (ADP) is developed. The unknown environment is modelled as a linear system and admittance controller is derived to achieve compliant behaviour of the robot. In the ADP framework, the cost function is defined with non-quadratic form and the critic network is designed with radial basis function neural network which introduces to obtain an approximate optimal control of the Hamilton–Jacobi–Bellman equation, which guarantees the optimal trajectory tracking. The system stability is analysed by Lyapunov theorem and simulations demonstrate the effectiveness of the proposed strategy.

Sign in / Sign up

Export Citation Format

Share Document