AN ARTIFICIAL NEURAL NETWORK ALGORITHM FOR DYNAMIC PROGRAMMING

1990 ◽  
Vol 01 (03) ◽  
pp. 211-220 ◽  
Author(s):  
Chinchuan Chiu ◽  
Chia-Yiu Maa ◽  
Michael A. Shanblatt
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dynamic Programming ◽  
Optimal Path ◽  
Dynamic Programming Algorithm ◽  
Performance Measure ◽  
Programming Algorithm ◽  
Network Dynamic ◽  
Destination Node ◽  
Artificial Neural

An artificial neural network (ANN) formulation for solving the dynamic programming problem (DPP) is presented. The DPP entails finding an optimal path from a source node to a destination node which minimizes (or maximizes) a performance measure of the problem. The optimization procedure is implemented and demonstrated using a modified Hopfield–Tank ANN. Simulations show that the ANN can provide a near-optimal solution during an elapsed time of only a few characteristic time constants of the circuit for DPPs with sizes as large as 64 stages with 64 states in each stage. An application of the proposed algorithm to an optimal control problem is presented. The proposed artificial neural network dynamic programming algorithm is attractive due to its radically improved speed over conventional techniques especially where real-time near-optimal solutions are required.

On The Selection of Discrete Grid Systems for On-Board Micro-based Weather Routeing

1990 ◽  
Vol 43 (1) ◽  
pp. 104-117 ◽  
Author(s):  
R. H. Motte ◽  
S. Calvert
Keyword(s):  
Dynamic Programming ◽  
Dynamic Programming Algorithm ◽  
Performance Measure ◽  
Programming Algorithm ◽  
Grid Systems ◽  
Objective Performance ◽  
The Cost ◽  
Discrete Grid ◽  
Ship Speed ◽  
Selection Of

The purpose of this paper is to show the effect of incorporating various discrete grid systems in a micro-based, ship weather-routeing system, which employs Bellman's dynamic programming algorithm, and either a cost-objective or time-objective performance measure. A simple ship speed and power function is utilized, in the cost computation. The calculation of the least-cost/least-time route is briefly described, but it is the derivation of the discrete grids and their influence on the route decisions that forms the paper's emphasis. The measure of cost within this paper is necessarily notional.

Optimal Flight Path Planning of Cruising Phase with No-Fly Zone Constraints Based on Dynamic Programming Algorithm

2012 ◽  
Vol 433-440 ◽  
pp. 5911-5917
Author(s):  
Su Xiao Wang ◽  
Yong Sheng Yang ◽  
Zhong Liang Jing
Keyword(s):  
Dynamic Programming ◽  
Path Planning ◽  
Real Time ◽  
Optimal Path ◽  
Dynamic Programming Algorithm ◽  
Optimization Method ◽  
Flight Path ◽  
Programming Algorithm ◽  
Effective Implementation ◽  
Arbitrary Selection

The purpose of flight path planning is to find the optimal path from the real-time and conflict-free airspace to meet the targets, according to one or several performance index. Effective avoiding the no-fly zones, such as the areas of martial movement and the areas of rain and thunderstorm, has great significance to the current flight management system (FMS) that is real-time and effective implementation of the flight plan. The dynamic optimization method of level route based on DP (Dynamic Programming) algorithm without no-fly zone constraints is discussed. Quick and effective to find out an optimal path from the waypoints of arbitrary selection and input can be realized. On this basis, the situation of adding no-fly zone constraints is focused on. In order to ensure that the aircraft is able to effectively avoid no-fly zone constraints in actual flight, Gauss Kruger projection method to convert geographic coordinates to plane coordinates is adopted. Simulation results show that the method used can not only effectively avoid no-fly zone constraints, and the path passed is still optimal.

Neuro-Dynamic Programming in Control of the Ball and Beam System

2013 ◽  
Vol 210 ◽  
pp. 206-214
Author(s):  
Andrzej Burghardt ◽  
Marcin Szuster
Keyword(s):  
Neural Network ◽  
Dynamic Programming ◽  
Control System ◽  
Control Algorithm ◽  
Main Part ◽  
Dynamic Programming Algorithm ◽  
Discrete Control ◽  
Programming Algorithm ◽  
Beam System ◽  
Ball And Beam System

This paper presents a new approach to the control problem of the ball and beam system, with a Neuro-Dynamic Programming algorithm implemented as the main part of the control system. The controlled system is included in the group of underactuated systems, which are nonlinear dynamical objects with the number of control signals smaller than the number of degrees of freedom. This results in problems in the formulation of a stable control algorithm, that guarantees stabilization of the ball in the desired position on the beam. The type of ball and beam material has a noticeable influence on the difficulties in stabilization of the ball, because of a smaller rolling friction and big inertia of the used metallic ball in comparison to other, for example made of non-metallic materials. The main part of the proposed discrete control system is the Neuro-Dynamic Programming algorithm in a Dual-Heuristic Dynamic Programming configuration, realized in a form of two neural networks: the actor and the critic. Neuro-Dynamic Programming algorithms use the Reinforcement Learning idea for adaptation of artificial neural network weights. Additional elements of the control system are the PD controller and the supervisory term, that ensures stability of the closed system loop. The control algorithm works on-line and does not require a preliminary learning phase of the neural network weights. Performance of the control algorithm was verified using the physical system controlled by the dSpace digital signal processing board.

Sign in / Sign up

Export Citation Format

Share Document