Simulation based safety assessment of autonomous vehicles

Automated Vehicles (AV) that are currently being developed, have to be assessed whether they are able to conform to the general traffic rules and whether they can ensure functional, behavioral safety during their operation. However, physical testing on the road or on a test circuit has several limit...

Full description

Saved in:
Bibliographic Details
Main Author: Jeyaraj, Sherine
Other Authors: Justin Dauwels
Format: Theses and Dissertations
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/78434
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Automated Vehicles (AV) that are currently being developed, have to be assessed whether they are able to conform to the general traffic rules and whether they can ensure functional, behavioral safety during their operation. However, physical testing on the road or on a test circuit has several limitations including the potential risk of causing damage to life and property. This brings out the need for scenario-based virtual testing of critical situations that can be reproduced in a realistic simulation environment, where the AV software can be allowed to operate independently in different conditions. The work in this thesis focuses on developing a co-simulation framework which connects a third-party driver model to another simulation environment. Safety is analyzed by recording the vehicle behaviour data using simulations and calculating some crucial parameters. For different configurations of the afore-mentioned, the simulation data is analyzed.