Reliability Validation of Learning Enabled Vehicle Tracking



Sun, Youcheng, Zhou, Yifan ORCID: 0000-0002-1477-5777, Maskell, Simon ORCID: 0000-0003-1917-2913, Sharp, James and Huang, Xiaowei ORCID: 0000-0001-6267-0366
(2020) Reliability Validation of Learning Enabled Vehicle Tracking. 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 00. pp. 9390-9396.

[img] Text
2002.02424v1.pdf - Author Accepted Manuscript

Download (2MB) | Preview

Abstract

This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components -- to process the imagery inputs -- and multiple symbolic (Kalman filter) components -- to analyse the processed information for vehicle tracking. It is known that neural networks suffer from adversarial examples, which make them lack robustness. However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability. By integrating a coverage-guided neural network testing tool, DeepConcolic, with the vehicle tracking system, we found that (1) the overall system can be resilient to some adversarial examples thanks to the existence of other components, and (2) the overall system presents an extra level of uncertainty which cannot be determined by analysing the deep learning components only. This research suggests the need for novel verification and validation methods for learning-enabled systems.

Item Type: Article
Uncontrolled Keywords: cs.CV, cs.CV, cs.RO
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 28 Sep 2021 15:58
Last Modified: 15 Mar 2024 11:31
DOI: 10.1109/icra40945.2020.9196932
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3138581