Vision-based Navigation of Autonomous Vehicle in Roadway Environments with Unexpected Hazards

by   Mhafuzul Islam, et al.

Vision-based navigation of modern autonomous vehicles primarily depends on Deep Neural Network (DNN) based systems in which the controller obtains input from sensors/detectors such as cameras, and produces an output such as a steering wheel angle to navigate the vehicle safely in roadway traffic. Typically, these DNN-based systems are trained through supervised and/or transfer learning; however, recent studies show that these systems can be compromised by perturbation or adversarial input features on the trained DNN-based models. Similarly, this perturbation can be introduced into the autonomous vehicle DNN-based system by roadway hazards such as debris and roadblocks. In this study, we first introduce a roadway hazardous environment (both intentional and unintentional) that can compromise the DNN-based system of an autonomous vehicle, producing an incorrect vehicle navigational output such as a steering wheel angle, which can cause crashes resulting in fatality and injury. Then, we develop an approach based on object detection and semantic segmentation to mitigate the adverse effect of this hazardous environment, one that helps the autonomous vehicle to navigate safely around such hazards. This study finds the DNN-based model with hazardous object detection, and semantic segmentation improves the ability of an autonomous vehicle to avoid potential crashes by 21



There are no comments yet.



Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles

In recent years, many deep learning models have been adopted in autonomo...

Autonomous Cars: Vision based Steering Wheel Angle Estimation

Machine learning models, which are frequently used in self-driving cars,...

Gradient Policy on "CartPole" game and its' expansibility to F1Tenth Autonomous Vehicles

Policy gradient is an effective way to estimate continuous action on the...

Robust Vision-Based Cheat Detection in Competitive Gaming

Game publishers and anti-cheat companies have been unsuccessful in block...

How to Build a Curb Dataset with LiDAR Data for Autonomous Driving

Curbs are one of the essential elements of urban and highway traffic env...

Improving benchmarks for autonomous vehicles testing using synthetically generated images

Nowadays autonomous technologies are a very heavily explored area and pa...

The Stixel world: A medium-level representation of traffic scenes

Recent progress in advanced driver assistance systems and the race towar...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.