Automatic parking controller with a twin artificial neural network architecture

Jaeyoung Moon, Il Bae, Shiho Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We propose an artificial deep neural network-(ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for automatic parking through supervised learning from a training database generated by computer-Aided optimizations or real experiments. By learning the relationships between the instantaneous vehicle states and the corresponding maneuver parameters, the proposed twin controller yields lateral and longitudinal maneuvering parameters for executing automatic parking tasks in confined spaces. The proposed automatic parking controller exhibits a twin architecture comprising a main agent and its cloned agent. Before the main agent assumes a maneuvering action, the cloned agent predicts the consequences of the maneuvering action through a Collision Checking and Adjustment (CCA) system. The proposed parking agent operates like a human driver in a manner that is characterized by an unplanned trajectory. In addition, the kinematics of the subject vehicle is not exactly modelled for parking control. The simulation results demonstrate that the proposed twin agent emulates the attributes of a human driver such as adaptive control and determines the consequences of the tentative maneuvering action under varying kinematic models of the subject vehicle. We validate the proposed parking controller by simulating the software-in-The-loop architecture using a PreScan simulator in which the dynamics of the virtual vehicle's behavior resemble a real vehicle.

Original languageEnglish
Article number4801985
JournalMathematical Problems in Engineering
Volume2019
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Parking
Network Architecture
Network architecture
Artificial Neural Network
Neural networks
Controller
Controllers
Driver
Kinematics
Kinematic Model
Supervised Learning
Supervised learning
Adaptive Control
Instantaneous
Lateral
Adjustment
Simulator
Collision
Attribute
Trajectory

All Science Journal Classification (ASJC) codes

  • Mathematics(all)
  • Engineering(all)

Cite this

@article{bb7510e472944fdcbf54aec09688570c,
title = "Automatic parking controller with a twin artificial neural network architecture",
abstract = "We propose an artificial deep neural network-(ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for automatic parking through supervised learning from a training database generated by computer-Aided optimizations or real experiments. By learning the relationships between the instantaneous vehicle states and the corresponding maneuver parameters, the proposed twin controller yields lateral and longitudinal maneuvering parameters for executing automatic parking tasks in confined spaces. The proposed automatic parking controller exhibits a twin architecture comprising a main agent and its cloned agent. Before the main agent assumes a maneuvering action, the cloned agent predicts the consequences of the maneuvering action through a Collision Checking and Adjustment (CCA) system. The proposed parking agent operates like a human driver in a manner that is characterized by an unplanned trajectory. In addition, the kinematics of the subject vehicle is not exactly modelled for parking control. The simulation results demonstrate that the proposed twin agent emulates the attributes of a human driver such as adaptive control and determines the consequences of the tentative maneuvering action under varying kinematic models of the subject vehicle. We validate the proposed parking controller by simulating the software-in-The-loop architecture using a PreScan simulator in which the dynamics of the virtual vehicle's behavior resemble a real vehicle.",
author = "Jaeyoung Moon and Il Bae and Shiho Kim",
year = "2019",
month = "1",
day = "1",
doi = "10.1155/2019/4801985",
language = "English",
volume = "2019",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

Automatic parking controller with a twin artificial neural network architecture. / Moon, Jaeyoung; Bae, Il; Kim, Shiho.

In: Mathematical Problems in Engineering, Vol. 2019, 4801985, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic parking controller with a twin artificial neural network architecture

AU - Moon, Jaeyoung

AU - Bae, Il

AU - Kim, Shiho

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose an artificial deep neural network-(ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for automatic parking through supervised learning from a training database generated by computer-Aided optimizations or real experiments. By learning the relationships between the instantaneous vehicle states and the corresponding maneuver parameters, the proposed twin controller yields lateral and longitudinal maneuvering parameters for executing automatic parking tasks in confined spaces. The proposed automatic parking controller exhibits a twin architecture comprising a main agent and its cloned agent. Before the main agent assumes a maneuvering action, the cloned agent predicts the consequences of the maneuvering action through a Collision Checking and Adjustment (CCA) system. The proposed parking agent operates like a human driver in a manner that is characterized by an unplanned trajectory. In addition, the kinematics of the subject vehicle is not exactly modelled for parking control. The simulation results demonstrate that the proposed twin agent emulates the attributes of a human driver such as adaptive control and determines the consequences of the tentative maneuvering action under varying kinematic models of the subject vehicle. We validate the proposed parking controller by simulating the software-in-The-loop architecture using a PreScan simulator in which the dynamics of the virtual vehicle's behavior resemble a real vehicle.

AB - We propose an artificial deep neural network-(ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for automatic parking through supervised learning from a training database generated by computer-Aided optimizations or real experiments. By learning the relationships between the instantaneous vehicle states and the corresponding maneuver parameters, the proposed twin controller yields lateral and longitudinal maneuvering parameters for executing automatic parking tasks in confined spaces. The proposed automatic parking controller exhibits a twin architecture comprising a main agent and its cloned agent. Before the main agent assumes a maneuvering action, the cloned agent predicts the consequences of the maneuvering action through a Collision Checking and Adjustment (CCA) system. The proposed parking agent operates like a human driver in a manner that is characterized by an unplanned trajectory. In addition, the kinematics of the subject vehicle is not exactly modelled for parking control. The simulation results demonstrate that the proposed twin agent emulates the attributes of a human driver such as adaptive control and determines the consequences of the tentative maneuvering action under varying kinematic models of the subject vehicle. We validate the proposed parking controller by simulating the software-in-The-loop architecture using a PreScan simulator in which the dynamics of the virtual vehicle's behavior resemble a real vehicle.

UR - http://www.scopus.com/inward/record.url?scp=85072974963&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072974963&partnerID=8YFLogxK

U2 - 10.1155/2019/4801985

DO - 10.1155/2019/4801985

M3 - Article

AN - SCOPUS:85072974963

VL - 2019

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 4801985

ER -