Performance Evaluation of an Automated Testing Pipeline for Autonomous Driving Systems
Datta, Arnab
Loading…
Permalink
https://hdl.handle.net/2142/110314
Description
Title
Performance Evaluation of an Automated Testing Pipeline for Autonomous Driving Systems
Author(s)
Datta, Arnab
Contributor(s)
Mitra, Sayan
Issue Date
2021-05
Keyword(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.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
