Machine Learning Algorithm for Automotive Collision Avoidance University of Texas-Arlington

Format:

Book

Conference/Event

Author/Creator:

Koganti, Ramakrishna, author.

Contributor:

Jha, Shambhavi

Polisetti, Sai Pranathi

Rajib, Md

Sikkem, Saichandra

They, Michael

Yang, Emma Yiran

Conference Name:

SAE WCX Digital Summit (2021-04-13 : Live Online, Pennsylvania, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2021

Summary:

Automotive collision avoidance system is a measure of enhanced safety. Car collisions have claimed the lives of many, and the advancement of science and technology has made collision avoidance a reality. Traditionally, collision avoidance systems are designed with the aim to avoid rear end collision, but in this paper, we are going to look at the collision avoidance with respect to fast approaching automobiles from a blind turn, making use of the navigation system. Here, we reviewed two levels of probability for collision. The first case is with high probability of probable collision and another case is with high probability of imminent collision. If the probability of probable collision is high, the driver is warned and requested to control the speed of the car. If the probability of imminent collision is high, the driver is warned, and autonomous braking takes effect. To achieve this, they made use of Bayesian Network which is built for the two speeds, one for host automobile and another for the fast approaching automobile. The recommendation is to use Machine Learning (ML) models for better robust models to prevent collisions

Notes:

Vendor supplied data

Publisher Number:

2021-01-0244

Access Restriction:

Restricted for use by site license