Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162460
Title: Demo abstract: real-time out-of-distribution detection on a mobile robot
Authors: Yuhas, Michael
Easwaran, Arvind
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Yuhas, M. & Easwaran, A. (2022). Demo abstract: real-time out-of-distribution detection on a mobile robot. IEEE Real-Time Systems Symposium - RTSS@Work 2022, 26-28.
Project: MOE2019-T2-2-040 
Conference: IEEE Real-Time Systems Symposium - RTSS@Work 2022
Abstract: In a cyber-physical system such as an autonomous vehicle (AV), machine learning (ML) models can be used to navigate and identify objects that may interfere with the vehicle’s operation. However, ML models are unlikely to make accurate decisions when presented with data outside their training distribution. Out-of-distribution (OOD) detection can act as a safety monitor for ML models by identifying such samples at run time. However, in safety critical systems like AVs, OOD detection needs to satisfy real-time constraints in addition to functional requirements. In this demonstration, we use a mobile robot as a surrogate for an AV and use an OOD detector to identify potentially hazardous samples. The robot navigates a miniature town using image data and a YOLO object detection network. We show that our OOD detector is capable of identifying OOD images in real-time on an embedded platform concurrently performing object detection and lane following. We also show that it can be used to successfully stop the vehicle in the presence of unknown, novel samples.
URI: https://hdl.handle.net/10356/162460
URL: http://2022.rtss.org/call-for-demo/
DOI (Related Dataset): 10.21979/N9/INOCLV
Schools: Interdisciplinary Graduate School (IGS) 
School of Computer Science and Engineering 
Research Centres: Energy Research Institute @ NTU (ERI@N) 
Rights: © 2022 The Author(s). Published by RTSS. All rights reserved.This paper was published in Proceedings of IEEE Real-Time Systems Symposium - RTSS@Work 2022 and is made available with permission of The Author(s).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:ERI@N Conference Papers
IGS Conference Papers
SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
RTSS_Demo___Duckietown.pdf9 MBAdobe PDFThumbnail
View/Open

Page view(s)

225
Updated on Nov 8, 2024

Download(s) 50

33
Updated on Nov 8, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.