Honors College Thesis
 

Safe navigation in highway environment using behavioral cloning

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/honors_college_theses/bv73c797n

Descriptions

Attribute NameValues
Creator
Abstract
  • Over 37,000 people die each year in automobile accidents, with many of these fatalities resulting from collisions with emergency vehicles. The rise of autonomous cars creates the need for an accurate and failsafe method of detecting and responding to emergency vehicles safely and on time. This thesis investigates the ability of a behavioral cloning algorithm to safely and lawfully direct an autonomous vehicle’s response to emergency vehicles within a simulated highway environment containing traffic vehicles, emergency vehicles, and the autonomous vehicle. In particular, we investigate the use of behavioral cloning approaches to learn to control an autonomous vehicle’s actions in response to approaching emergency vehicles. We evaluate the performance of the algorithm using a comprehensive series of tests and analyzing the following metrics: autonomous systems’ response time, accuracy in detecting emergency vehicles, false positives, f1 score, and real-world costs of implementation of the algorithm.
  • Keywords: Behavior cloning, highway simulation, autonomous vehicle, reinforcement learning
Contributor
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Non-Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details DamleMalhar2023.pdf 2023-12-07 Public Download