Umeå University's logo

umu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Efficient performance prediction of end-to-end autonomous driving under continuous distribution shifts based on anomaly detection
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.ORCID-id: 0000-0003-4228-2774
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China.
2023 (engelsk)Inngår i: Journal of Signal Processing Systems, ISSN 1939-8018, E-ISSN 1939-8115, Vol. 95, nr 12, s. 1455-1468Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

A Deep Neural Network (DNN)’s prediction may be unreliable outside of its training distribution despite high levels of accuracy obtained during model training. The DNN may experience different degrees of accuracy degradation for different levels of distribution shifts, hence it is important to predict its performance (accuracy) under distribution shifts. In this paper, we consider the end-to-end approach to autonomous driving of using a DNN to map from an input image to the control action such as the steering angle. For each input image with possible perturbations that cause distribution shifts, we design a Performance Prediction Module to compute its anomaly score, and use it to predict the DNN’s expected prediction error, i.e., its expected deviation from the ground truth (optimal) control action, which is not available after deployment. If the expected prediction error is too large, then the DNN’s prediction may no longer be trusted, and remedial actions should be taken to ensure safety. We consider different methods for computing the anomaly score for the input image, including using the reconstruction error of an Autoencoder, or applying an Anomaly Detection algorithm to a hidden layer of the DNN. We present performance evaluation of the different methods in terms of both prediction accuracy and execution time on different hardware platforms, in order to provide a useful reference for the designer to choose among the different methods.

sted, utgiver, år, opplag, sider
Springer, 2023. Vol. 95, nr 12, s. 1455-1468
Emneord [en]
Machine learning, Deep learning, Distribution shifts, Performance prediction, End-to-end autonomous driving
HSV kategori
Identifikatorer
URN: urn:nbn:se:umu:diva-214350DOI: 10.1007/s11265-023-01893-5Scopus ID: 2-s2.0-85177063760OAI: oai:DiVA.org:umu-214350DiVA, id: diva2:1796394
Forskningsfinansiär
The Kempe Foundations
Merknad

Originally included in thesis in manuscript form. 

Tilgjengelig fra: 2023-09-12 Laget: 2023-09-12 Sist oppdatert: 2024-04-29bibliografisk kontrollert
Inngår i avhandling
1. Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
Åpne denne publikasjonen i ny fane eller vindu >>Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
2023 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

We consider real-time safety-critical systems that feature closed-loop interactions between the embedded computing system and the physical environment with a sense-compute-actuate feedback loop. Deep Learning (DL) with Deep Neural Networks (DNNs) has achieved success in many application domains, but there are still significant challenges in its application in real-time safety-critical systems that require high levels of safety certification under significant hardware resource constraints. This thesis considers the following overarching research goal: How to achieve safe and efficient application of DNNs in resource-constrained Real-Time Embedded (RTE) systems in the context of safety-critical application domains such as Autonomous Driving? Towards reaching that goal, this thesis presents a set of algorithms and techniques that aim to address three Research Questions (RQs): RQ1: How to achieve accurate and efficient Out-of-Distribution (OOD) detection for DNNs in RTE systems? RQ2: How to predict the performance of DNNs under continuous distribution shifts? RQ3: How to achieve efficient inference of Deep Reinforcement Learning (DRL) agents in RTE systems?

For RQ1, we present a framework for OOD detection based on outlier detection in one or more hidden layers of a DNN with either Isolation Forest (IF) or Local Outlier Factor (LOF). We also perform a comprehensive and systematic benchmark study of multiple well-known OOD detection algorithms in terms of both accuracy and execution time on different hardware platforms, in order to provide a useful reference for the practical deployment of OOD detection algorithms in RTE systems. For RQ2, we present a framework for predicting the performance of DNNs for end-to-end Autonomous Driving under continuous distribution shifts with two approaches: using an Autoencoder that attempts to reconstruct the input image; and applying Anomaly Detection algorithms to the hidden layer(s) of the DNN. For RQ3, we present a framework for model compression of the policy network of a DRL agent for deployment in RTE systems by leveraging the relevance scores computed by Layer-wise Relevance Propagation (LRP) to rank and prune the convolutional filters, combined with fine-tuning using policy distillation.

The algorithms and techniques developed in this thesis have been evaluated on standard datasets and benchmarks. To summarize our findings, we have developed novel OOD detection algorithms with high accuracy and efficiency; identified OOD detection algorithms with relatively high accuracy and low execution times through benchmarking; developed a framework for DNN performance prediction under continuous distribution shifts, and identified most effective Anomaly Detection algorithms for use in the framework; developed a framework for model compression of DRL agents that is effective in reducing model size and inference time for deployment in RTE systems. The research results are expected to assist system designers in the task of safe and efficient application of DNNs in resource-constrained RTE systems.

sted, utgiver, år, opplag, sider
Umeå: Umeå University, 2023. s. 49
Emneord
Machine Learning/Deep Learning, Real-Time Embedded systems, Out-of-Distribution Detection, Distribution Shifts, Deep Reinforcement Learning, Model Compression, Policy Distillation.
HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-214365 (URN)978-91-8070-161-7 (ISBN)978-91-8070-160-0 (ISBN)
Disputas
2023-10-09, Triple Helix, Samverkanshuset, Umeå, 13:00 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2023-09-18 Laget: 2023-09-12 Sist oppdatert: 2023-09-13bibliografisk kontrollert

Open Access i DiVA

fulltext(1627 kB)535 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 1627 kBChecksum SHA-512
02f0c848ad8144edbf73d36f211caf639eb42f76513b76ae225170fb69c217bb7d8b6fbb1f1d130392aa1560de556d8f1859d020b98118ba8eb3685d7eeae4f7
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Person

Luan, SiyuGu, Zonghua

Søk i DiVA

Av forfatter/redaktør
Luan, SiyuGu, Zonghua
Av organisasjonen
I samme tidsskrift
Journal of Signal Processing Systems

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 567 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 617 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf