Design of an intelligent feed forward controller system for vehicle obstacle avoidance using neural networks

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The design of a novel feed forward controller system for vehicle obstacle avoidance using the neural network methodology is proposed. Currently, most obstacle avoidance systems are designed based on a segmented procedure: a) parametric path planning; b) desired yaw moment computation based on a simplified model; c) yaw moment tracking; d) stable controller design. In this paper, a different strategy is followed. An intelligent 'autopilot', that has been trained using a set of optimised obstacle avoidance manoeuvres, decides how to avoid the obstacle. The obstacle avoidance manoeuvres have been optimised using a reformulation of the Pontryagin's Maximum Principle and global numerical optimisation techniques. The proposed controller has the advantage that it respects 'by design' the internal dynamics of the system and can be adjusted in order to account any model uncertainties. Furthermore, it is computationally very efficient. The performance of the intelligent system is evaluated by means of simulations in MATLAB for a number of test cases.
Original languageEnglish
Pages (from-to)55-87
Number of pages33
JournalInternational Journal of Vehicle Systems Modelling and Testing
Volume8
Issue number1
DOIs
Publication statusPublished - 6 Mar 2013

Fingerprint

Obstacle Avoidance
Collision avoidance
Feedforward
Neural Networks
Neural networks
Controller
Controllers
Moment
Autopilot
Pontryagin Maximum Principle
Maximum principle
Numerical Optimization
Model Uncertainty
Path Planning
Intelligent systems
Intelligent Systems
Motion planning
Numerical Techniques
Reformulation
Controller Design

Keywords

  • Intelligent feed forward controller
  • Neural networks
  • NNs
  • Vehicle obstacle avoidance

Cite this

@article{84728f49794f4bc7b92e2b2c7b67d75e,
title = "Design of an intelligent feed forward controller system for vehicle obstacle avoidance using neural networks",
abstract = "The design of a novel feed forward controller system for vehicle obstacle avoidance using the neural network methodology is proposed. Currently, most obstacle avoidance systems are designed based on a segmented procedure: a) parametric path planning; b) desired yaw moment computation based on a simplified model; c) yaw moment tracking; d) stable controller design. In this paper, a different strategy is followed. An intelligent 'autopilot', that has been trained using a set of optimised obstacle avoidance manoeuvres, decides how to avoid the obstacle. The obstacle avoidance manoeuvres have been optimised using a reformulation of the Pontryagin's Maximum Principle and global numerical optimisation techniques. The proposed controller has the advantage that it respects 'by design' the internal dynamics of the system and can be adjusted in order to account any model uncertainties. Furthermore, it is computationally very efficient. The performance of the intelligent system is evaluated by means of simulations in MATLAB for a number of test cases.",
keywords = "Intelligent feed forward controller, Neural networks, NNs, Vehicle obstacle avoidance",
author = "Stratis Kanarachos",
year = "2013",
month = "3",
day = "6",
doi = "10.1504/IJVSMT.2013.052242",
language = "English",
volume = "8",
pages = "55--87",
journal = "International Journal of Vehicle Systems Modelling and Testing",
issn = "1745-6436",
publisher = "Inderscience",
number = "1",

}

TY - JOUR

T1 - Design of an intelligent feed forward controller system for vehicle obstacle avoidance using neural networks

AU - Kanarachos, Stratis

PY - 2013/3/6

Y1 - 2013/3/6

N2 - The design of a novel feed forward controller system for vehicle obstacle avoidance using the neural network methodology is proposed. Currently, most obstacle avoidance systems are designed based on a segmented procedure: a) parametric path planning; b) desired yaw moment computation based on a simplified model; c) yaw moment tracking; d) stable controller design. In this paper, a different strategy is followed. An intelligent 'autopilot', that has been trained using a set of optimised obstacle avoidance manoeuvres, decides how to avoid the obstacle. The obstacle avoidance manoeuvres have been optimised using a reformulation of the Pontryagin's Maximum Principle and global numerical optimisation techniques. The proposed controller has the advantage that it respects 'by design' the internal dynamics of the system and can be adjusted in order to account any model uncertainties. Furthermore, it is computationally very efficient. The performance of the intelligent system is evaluated by means of simulations in MATLAB for a number of test cases.

AB - The design of a novel feed forward controller system for vehicle obstacle avoidance using the neural network methodology is proposed. Currently, most obstacle avoidance systems are designed based on a segmented procedure: a) parametric path planning; b) desired yaw moment computation based on a simplified model; c) yaw moment tracking; d) stable controller design. In this paper, a different strategy is followed. An intelligent 'autopilot', that has been trained using a set of optimised obstacle avoidance manoeuvres, decides how to avoid the obstacle. The obstacle avoidance manoeuvres have been optimised using a reformulation of the Pontryagin's Maximum Principle and global numerical optimisation techniques. The proposed controller has the advantage that it respects 'by design' the internal dynamics of the system and can be adjusted in order to account any model uncertainties. Furthermore, it is computationally very efficient. The performance of the intelligent system is evaluated by means of simulations in MATLAB for a number of test cases.

KW - Intelligent feed forward controller

KW - Neural networks

KW - NNs

KW - Vehicle obstacle avoidance

U2 - 10.1504/IJVSMT.2013.052242

DO - 10.1504/IJVSMT.2013.052242

M3 - Article

VL - 8

SP - 55

EP - 87

JO - International Journal of Vehicle Systems Modelling and Testing

JF - International Journal of Vehicle Systems Modelling and Testing

SN - 1745-6436

IS - 1

ER -