Abstract | ||
---|---|---|
Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to determine when a model will make a safe decision and when it will make an erroneous, perhaps life-threatening one. Prior work on novelty detection deal with highly structured data and do not translate well to dynamic, real-world situations. This paper proposes a multi-step framework for the detection of novel scenarios in vision-based autonomous systems by leveraging information learned by the trained prediction model and a new image similarity metric. We demonstrate the efficacy of this method through experiments on a real-world driving dataset as well as on our in-house indoor racing environment. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/DSN-W.2019.00018 | 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) |
Keywords | DocType | Volume |
Deep learning,novelty detection,network saliency,autonomous systems | Conference | abs/1906.03685 |
ISSN | ISBN | Citations |
2325-6648 | 978-1-7281-3031-6 | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Valerie Chen | 1 | 2 | 1.72 |
Man Ki Yoon | 2 | 16 | 2.36 |
Zhong Shao | 3 | 897 | 68.80 |