University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Safe Deep Neural Network-driven Autonomous Vehicles Using Software Safety Cages

Kuutti, Sampo, Bowden, Richard, Joshi, Harita, de Temple, Robert and Fallah, Saber (2019) Safe Deep Neural Network-driven Autonomous Vehicles Using Software Safety Cages In: 20th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2019), 14-16 Nov 2019, The University of Manchester, UK.

[img]
Preview
Text
Safe Deep Neural Network-driven Autonomous Vehicles Using SoftwareSafety Cages.pdf - Accepted version Manuscript

Download (495kB) | Preview

Abstract

Deep learning is a promising class of techniques for controlling an autonomous vehicle. However, functional safety validation is seen as a critical issue for these systems due to the lack of transparency in deep neural networks and the safety-critical nature of autonomous vehicles. The black box nature of deep neural networks limits the effectiveness of traditional verification and validation methods. In this paper, we propose two software safety cages, which aim to limit the control action of the neural network to a safe operational envelope. The safety cages impose limits on the control action during critical scenarios, which if breached, change the control action to a more conservative value. This has the benefit that the behaviour of the safety cages is interpretable, and therefore traditional functional safety validation techniques can be applied. The work here presents a deep neural network trained for longitudinal vehicle control, with safety cages designed to prevent forward collisions. Simulated testing in critical scenarios shows the effectiveness of the safety cages in preventing forward collisions whilst under normal highway driving unnecessary interruptions are eliminated, and the deep learning control policy is able to perform unhindered. Interventions by the safety cages are also used to re-train the network, resulting in a more robust control policy.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Mechanical Engineering Sciences
Authors :
NameEmailORCID
Kuutti, Sampos.j.kuutti@surrey.ac.uk
Bowden, RichardR.Bowden@surrey.ac.uk
Joshi, Harita
de Temple, Robert
Fallah, Sabers.fallah@surrey.ac.uk
Date : 2019
Funders : Engineering and Physical Sciences Research Council (EPSRC), Jaguar Land Rover
DOI : 10.1007/978-3-030-33607-3
Copyright Disclaimer : © 2019 Springer Nature Switzerland AG
Uncontrolled Keywords : Automatic Control; Autonomous Vehicles; Cyber-physical Systems; Deep Learning; Safety
Related URLs :
Depositing User : Clive Harris
Date Deposited : 05 Nov 2019 11:10
Last Modified : 14 Nov 2019 02:08
URI: http://epubs.surrey.ac.uk/id/eprint/853035

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800