Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares

Manuel Acosta, Stratis Kanarachos

Research output: Contribution to journalArticle

6 Citations (Scopus)
196 Downloads (Pure)

Abstract

This paper presents a novel hybrid observer structure to estimate the lateral tire forces and road grip potential without using any tire–road friction model. The observer consists of an Extended Kalman Filter structure, which incorporates the available prior knowledge about the vehicle dynamics, a feedforward Neural Network structure, which is used to estimate the highly nonlinear tire behavior, and a Recursive Least Squares block, which predicts the road grip potential. The proposed observer was evaluated under a wide range of aggressive maneuvers and different road grip conditions using a validated vehicle model, validated tire model, and sensor models in the simulation environment IPG CarMaker®. The results confirm its good and robust performance.

Original languageEnglish
Pages (from-to)3445–3465
Number of pages21
JournalNeural Computing and Applications
Volume30
Issue number11
Early online date13 Mar 2017
DOIs
Publication statusPublished - Dec 2018

Fingerprint

Extended Kalman filters
Tires
Identification (control systems)
Neural networks
Feedforward neural networks
Friction
Sensors

Bibliographical note

The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-017-2932-9

Keywords

  • Grip potential estimation
  • Hybrid observer
  • Neural Networks
  • Tire force estimation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

@article{47cfff8950a14bd5987216731edd87fa,
title = "Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares",
abstract = "This paper presents a novel hybrid observer structure to estimate the lateral tire forces and road grip potential without using any tire–road friction model. The observer consists of an Extended Kalman Filter structure, which incorporates the available prior knowledge about the vehicle dynamics, a feedforward Neural Network structure, which is used to estimate the highly nonlinear tire behavior, and a Recursive Least Squares block, which predicts the road grip potential. The proposed observer was evaluated under a wide range of aggressive maneuvers and different road grip conditions using a validated vehicle model, validated tire model, and sensor models in the simulation environment IPG CarMaker{\circledR}. The results confirm its good and robust performance.",
keywords = "Grip potential estimation, Hybrid observer, Neural Networks, Tire force estimation",
author = "Manuel Acosta and Stratis Kanarachos",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-017-2932-9",
year = "2018",
month = "12",
doi = "10.1007/s00521-017-2932-9",
language = "English",
volume = "30",
pages = "3445–3465",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer Verlag",
number = "11",

}

TY - JOUR

T1 - Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares

AU - Acosta, Manuel

AU - Kanarachos, Stratis

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-017-2932-9

PY - 2018/12

Y1 - 2018/12

N2 - This paper presents a novel hybrid observer structure to estimate the lateral tire forces and road grip potential without using any tire–road friction model. The observer consists of an Extended Kalman Filter structure, which incorporates the available prior knowledge about the vehicle dynamics, a feedforward Neural Network structure, which is used to estimate the highly nonlinear tire behavior, and a Recursive Least Squares block, which predicts the road grip potential. The proposed observer was evaluated under a wide range of aggressive maneuvers and different road grip conditions using a validated vehicle model, validated tire model, and sensor models in the simulation environment IPG CarMaker®. The results confirm its good and robust performance.

AB - This paper presents a novel hybrid observer structure to estimate the lateral tire forces and road grip potential without using any tire–road friction model. The observer consists of an Extended Kalman Filter structure, which incorporates the available prior knowledge about the vehicle dynamics, a feedforward Neural Network structure, which is used to estimate the highly nonlinear tire behavior, and a Recursive Least Squares block, which predicts the road grip potential. The proposed observer was evaluated under a wide range of aggressive maneuvers and different road grip conditions using a validated vehicle model, validated tire model, and sensor models in the simulation environment IPG CarMaker®. The results confirm its good and robust performance.

KW - Grip potential estimation

KW - Hybrid observer

KW - Neural Networks

KW - Tire force estimation

U2 - 10.1007/s00521-017-2932-9

DO - 10.1007/s00521-017-2932-9

M3 - Article

VL - 30

SP - 3445

EP - 3465

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 11

ER -