Abstract
Machine learning (ML) is actively finding its way into modern cyber-physical systems (CPS), many of which are safety-critical real-time systems. It is well known that ML outputs are not reliable when testing data are novel with regards to model training and validation data, i.e., out-of-distribution (OOD) test data. We implement an unsupervised deep neural network-based OOD detector on a real-time embedded autonomous Duckiebot and evaluate detection performance. Our OOD detector produces a success rate of 87.5% for emergency stopping a Duckiebot on a braking test bed we designed. We also provide case analysis on computing resource challenges specific to the Robot Operating System (ROS) middleware on the Duckiebot.
| Original language | English |
|---|---|
| Title of host publication | Destion 2021 - Proceedings of the 2021 Design Automation for CPS and IoT |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 13-18 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781450383165 |
| DOIs | |
| Publication status | Published - May 18 2021 |
| Externally published | Yes |
| Event | 2021 Workshop on Design Automation for CPS and IoT, Destion 2021 - Virtual, Online, United States Duration: May 18 2021 → … |
Publication series
| Name | Destion 2021 - Proceedings of the 2021 Design Automation for CPS and IoT |
|---|
Conference
| Conference | 2021 Workshop on Design Automation for CPS and IoT, Destion 2021 |
|---|---|
| Country/Territory | United States |
| City | Virtual, Online |
| Period | 5/18/21 → … |
Bibliographical note
Publisher Copyright:© 2021 ACM.
ASJC Scopus Subject Areas
- Computer Networks and Communications
- Computer Science Applications
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Modelling and Simulation