Skip to content

A low-power approach analysis on image-based steering wheel angle prediction models.

Notifications You must be signed in to change notification settings

nopesir/aiml-project

Repository files navigation

A low-power approach analysis on image-based steering wheel angle prediction models

Alessandro Bozzella

Politecnico di Torino
[email protected]

Luigi Ferrettino

Politecnico di Torino
[email protected]

Rinaldo Clemente

Politecnico di Torino
[email protected]

Abstract

Self-driving vehicles have spread dramatically over the last few years. ADAS control system would have to de- termine steering wheel angle, brakes and acceleration in any driving environment. The navigation technology in autonomous vehicles is an artificial intelligence application which remains partially unsolved and has been significantly explored by the automotive and technological industries. Many image processing and computer vision techniques allow significant improvements on such recent technologies. In recent years, autonomous driving algorithms, using lowcost vehicle-mounted cameras, have attracted increasing endeavors from both academia and industry. There are multiple fronts to these endeavors, including object detection on roads, 3-D reconstruction etc., but in this work we focus on a cameras-based model that directly maps raw input images to steering angles using deep networks. This represents a nascent research topic in computer vision.

About

A low-power approach analysis on image-based steering wheel angle prediction models.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published