AI Lund Lunch seminar: Critical scenario identification for testing of autonomous driving systems

Seminarium

From: 2022-05-18 12:00 to 13:15
Place: Online - link by registration
Contact: Jonas [dot] Wisbrant [at] cs [dot] lth [dot] se
Save event to your calendar

Recording: ai.lu.se/2022-05-18  

Title: Critical scenario identification for testing of autonomous driving systems

Speaker:  Qunying Song, WASP PhD Student, Department of Computer Science Lund University

When: 18 May at 12.00-13.15

Where: Online 

Spoken language: English

Abstract

Testing of autonomous driving systems is a prerequisite to verify the safety and reliability of such systems. Current approaches for testing autonomous driving systems that rely on substantial real-world testing, or collecting real traffic data at scale, are considered both inefficient and ineffective as it is expensive, time-consuming, and may still not cover the rare-occurring traffic situations.
 
During the seminar, I will introduce an approach for testing autonomous driving systems based on critical scenario identification. Specifically, I will go through some tools and a workflow for generating critical test scenarios, and I will also demonstrate the effectiveness of the said approach using two real autonomous driving systems from industry.