Files in this item

FilesDescriptionFormat

application/pdf

application/pdfSP21-ECE499-Thesis-Datta, Arnab.pdf (8MB)
(no description provided)PDF

Description

Title:Performance Evaluation of an Automated Testing Pipeline for Autonomous Driving Systems
Author(s):Datta, Arnab
Contributor(s):Mitra, Sayan
Degree:B.S. (bachelor's)
Genre:Thesis
Subject(s):Vehicle Simulation Testing
Autonomous Systems
Abstract:In this project we explore how controllers for vehicles in a simulation-based race can be evaluated automatically. Different controllers for different vehicles will have to be evaluated in different track settings. This is a challenging software testing exercise, and we explore how a massive number of such tests can be performed automatically. The work will be carried out in the context of a racing competition where contestants shall submit code for a controller module that will be run on a vehicle simulated on a test racing track with unique scenarios throughout. The scenarios aim to replicate real-world traffic situations and provide for further testing of the controller code. We explore how to design scoring metrics and how to evaluate the metrics on different submissions through an automated testing pipeline. The testing pipeline is evaluated based on its CPU and memory usage over multiple races and scenarios. The results display the limitations and potential of the pipeline to be adjusted for future races of the GRAIC competition.
Issue Date:2021-05
Genre:Dissertation / Thesis
Type:Text
Language:English
URI:http://hdl.handle.net/2142/110314
Date Available in IDEALS:2021-08-11


This item appears in the following Collection(s)

Item Statistics