Driver Distraction Recognition-driven Collision Avoidance Algorithm for Active Vehicle Safety

K. B. Devika; ASISH BERA; Venkata Ramani Yellapantula; ARDHENDU BEHERA; YONGHUAI LIU; Shankar C. Subramanian

Driver Distraction Recognition-driven Collision Avoidance Algorithm for Active Vehicle Safety

K. B. Devika, ASISH BERA, Venkata Ramani Yellapantula, ARDHENDU BEHERA^*, YONGHUAI LIU, Shankar C. Subramanian

^*Corresponding author for this work

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

79 Downloads (Pure)

Abstract

This paper integrates human driver factors with a model-based Collision Avoidance System (CAS) to enhance the safety of semi-autonomous vehicles. Driver Activity Recognition (DAR) through Driver Distraction States (DDS) has been used as the key component to trigger the CAS so that collisions can be averted. DDS has been generated using realistic normal driving scenarios and suitably integrated with a Full State Feedback (FSF) controller-based CAS. The integrated algorithm has been tested using a Hardware in Loop (HiL) setup, which is interfaced with the vehicle dynamics software IPG TruckMaker®. The performance of the algorithm has been evaluated for various on-road scenarios and found to be effective in avoiding rear-end collisions.

Original language	English
Title of host publication	Intelligent Transportation Systems. IEEE International Conference. 24th 2021.
Publisher	IEEE
Publication status	Accepted/In press - 15 Jun 2021

Keywords

Deep Learning
Convolutional Neural Network
Collision Avoidance
Driver distraction
Driver Activity Recognition
Hardware in Loop
Full State Feedback Controller

Access to Document

Author_Manuscript_ITSC_494Accepted author manuscript, 1.81 MBLicence: CC BY-NC-ND

Cite this

@inproceedings{6ea49e1653d8465188c3632e604d8b5a,

title = "Driver Distraction Recognition-driven Collision Avoidance Algorithm for Active Vehicle Safety",

abstract = "This paper integrates human driver factors with a model-based Collision Avoidance System (CAS) to enhance the safety of semi-autonomous vehicles. Driver Activity Recognition (DAR) through Driver Distraction States (DDS) has been used as the key component to trigger the CAS so that collisions can be averted. DDS has been generated using realistic normal driving scenarios and suitably integrated with a Full State Feedback (FSF) controller-based CAS. The integrated algorithm has been tested using a Hardware in Loop (HiL) setup, which is interfaced with the vehicle dynamics software IPG TruckMaker{\textregistered}. The performance of the algorithm has been evaluated for various on-road scenarios and found to be effective in avoiding rear-end collisions.",

keywords = "Deep Learning, Convolutional Neural Network, Collision Avoidance, Driver distraction, Driver Activity Recognition, Hardware in Loop, Full State Feedback Controller",

author = "Devika, {K. B.} and ASISH BERA and Yellapantula, {Venkata Ramani} and ARDHENDU BEHERA and YONGHUAI LIU and Subramanian, {Shankar C.}",

year = "2021",

month = jun,

day = "15",

language = "English",

booktitle = "Intelligent Transportation Systems. IEEE International Conference. 24th 2021.",

publisher = "IEEE",

}

TY - GEN

T1 - Driver Distraction Recognition-driven Collision Avoidance Algorithm for Active Vehicle Safety

AU - Devika, K. B.

AU - BERA, ASISH

AU - Yellapantula, Venkata Ramani

AU - BEHERA, ARDHENDU

AU - LIU, YONGHUAI

AU - Subramanian, Shankar C.

PY - 2021/6/15

Y1 - 2021/6/15

N2 - This paper integrates human driver factors with a model-based Collision Avoidance System (CAS) to enhance the safety of semi-autonomous vehicles. Driver Activity Recognition (DAR) through Driver Distraction States (DDS) has been used as the key component to trigger the CAS so that collisions can be averted. DDS has been generated using realistic normal driving scenarios and suitably integrated with a Full State Feedback (FSF) controller-based CAS. The integrated algorithm has been tested using a Hardware in Loop (HiL) setup, which is interfaced with the vehicle dynamics software IPG TruckMaker®. The performance of the algorithm has been evaluated for various on-road scenarios and found to be effective in avoiding rear-end collisions.

AB - This paper integrates human driver factors with a model-based Collision Avoidance System (CAS) to enhance the safety of semi-autonomous vehicles. Driver Activity Recognition (DAR) through Driver Distraction States (DDS) has been used as the key component to trigger the CAS so that collisions can be averted. DDS has been generated using realistic normal driving scenarios and suitably integrated with a Full State Feedback (FSF) controller-based CAS. The integrated algorithm has been tested using a Hardware in Loop (HiL) setup, which is interfaced with the vehicle dynamics software IPG TruckMaker®. The performance of the algorithm has been evaluated for various on-road scenarios and found to be effective in avoiding rear-end collisions.

KW - Deep Learning

KW - Convolutional Neural Network

KW - Collision Avoidance

KW - Driver distraction

KW - Driver Activity Recognition

KW - Hardware in Loop

KW - Full State Feedback Controller

UR - https://2021.ieee-itsc.org/

M3 - Conference proceeding (ISBN)

BT - Intelligent Transportation Systems. IEEE International Conference. 24th 2021.

PB - IEEE

ER -

Driver Distraction Recognition-driven Collision Avoidance Algorithm for Active Vehicle Safety

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this