Robustness Evaluation and Improvement for Vision-Based Advanced Driver Assistance Systems

Hospach, Dennis; Bringmann, Oliver; Gerlach, Joachim

doi:10.1109/itsc.2015.427

Cited by 12 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adversarial Input Generation. Adversarial input generation approaches aim at generating inputs that trigger inconsistencies between multiple autonomous driving systems [34], or between the original and transformed driving scenarios [30,44,55]. These works exploit the well-known fragility of DNNs to adversarial examples.…”

Section: Related Workmentioning

confidence: 99%

“…Despite the different goal (test generation vs misbehaviour prediction), we share with these works the problem of how to empirically validate the proposed technique in the absence of a precise oracle that defines the expected behaviour of a self-driving car. The prevalent choice in test generators [30,34,44,55] is to address the oracle problem by differential testing, i.e., by comparing the behaviours of multiple DNNs, or by metamorphic testing, i.e., by comparing the behaviour before and after applying a metamorphic transformation to the input. Approaches based on verification are also being under investigation [19].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Misbehaviour prediction for autonomous driving systems

Stocco

Weiß

Calzana

et al. 2020

Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering

119

131

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) are the core component of modern autonomous driving systems. To date, it is still unrealistic that a DNN will generalize correctly to all driving conditions. Current testing techniques consist of offline solutions that identify adversarial or corner cases for improving the training phase. In this paper, we address the problem of estimating the confidence of DNNs in response to unexpected execution contexts with the purpose of predicting potential safety-critical misbehaviours and enabling online healing of DNN-based vehicles. Our approach SelfOracle is based on a novel concept of self-assessment oracle, which monitors the DNN confidence at runtime, to predict unsupported driving scenarios in advance. SelfOracle uses autoencoderand time series-based anomaly detection to reconstruct the driving scenarios seen by the car, and to determine the confidence boundary between normal and unsupported conditions. In our empirical assessment, we evaluated the effectiveness of different variants of SelfOracle at predicting injected anomalous driving contexts, using DNN models and simulation environment from Udacity. Results show that, overall, SelfOracle can predict 77% misbehaviours, up to six seconds in advance, outperforming the online input validation approach of DeepRoad. CCS CONCEPTS • Software and its engineering → Software testing and debugging.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Misbehaviour prediction for autonomous driving systems

Stocco

Weiß

Calzana

et al. 2020

Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering

119

131

View full text Add to dashboard Cite

show abstract

“…Oracles in Test Generation. In the offline setting, several approaches generate input images that trigger steering angle inconsistencies between multiple autonomous driving systems [31], or between the original and transformed driving driving scenarios [41,43,30]. The oracle used in such works consists of measuring whether the deviation between actual and reference steering angles is higher than a given threshold.…”

Section: Related Workmentioning

confidence: 99%

Quality Metrics and Oracles for Autonomous Vehicles Testing

Jahangirova

Stocco

Tonella

2021

2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST)

View full text Add to dashboard Cite

The race for deploying AI-enabled autonomous vehicles (AVs) on public roads is based on the promise that such self-driving cars will be as safe as or safer than human drivers. Numerous techniques have been proposed to test AVs, which however lack oracle definitions that account for the quality of driving, due to the lack of a commonly used set of metrics. Towards filling this gap, we first performed a systematic analysis of the literature concerning the assessment of the quality of driving of human drivers and extracted 126 metrics. Then, we measured the correlation between such metrics and the human perception of driving quality when AVs are driving. Lastly, we performed a study based on mutation analysis to assess whether the 26 metrics that best capture the quality of AV driving according to the human study can be used as functional oracles. Our results, targeting the Udacity platform, indicate that our automated oracles can kill a high proportion of mutants at a zero or very low false alarm rate, and therefore can be used as effective functional oracles for the quality of driving of AVs.

show abstract

“…[12][158] showed similar observations and indicate that using such images as data augmentation can boost robustness against adversarial examples. Note that [158] used synthetic transformation of ADAS based images, evaluated through robustness landscape, which shows such a concept can be applied in transportation related settings. In fact, similar perturbations were shown to be useful in defending against adversarial examples [42], by pre-processing potentially adversarial examples with those transformations or by using adversarial re-training [109].…”

Section: Non-adversarial Perturbationsmentioning

confidence: 99%

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Tambon,

Laberge,

et al. 2021

Preprint

View full text Add to dashboard Cite

Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called "safety-critical" systems such as automotive or aeronautic has proven to be very challenging, since the shift in paradigm that ML brings completely changes traditional certification approaches.Objective: This paper aims to elucidate challenges related to the certification of ML-based safety-critical systems, as well as the solutions that are proposed in the literature to tackle them, answering the question "How to Certify Machine Learning Based Safety-critical Systems?".Method: We conduct a Systematic Literature Review (SLR) of research papers published between 2015 to 2020, covering topics related to the certification of ML systems. In total, we identified 217 papers covering topics considered to be the main pillars of ML certification: Robustness, Uncertainty, Explainability, Verification, Safe Reinforcement Learning, and Direct Certification. We analyzed the main trends and problems of each sub-field and provided summaries of the papers extracted.Results: The SLR results highlighted the enthusiasm of the community for this subject, as well as the lack of diversity in term of datasets and type of ML models. It also emphasized the need to further develop connections between academia and industries to deepen the domain study. Finally, it also illustrated This work is supported by the DEEL project CRDPJ 537462-18 funded by the National Science and Engineering Research Council of Canada (NSERC) and the Consortium for Research and Innovation in Aerospace in Québec (CRIAQ), together with its industrial partners Thales Canada inc, Bell Textron Canada Limited, CAE inc and Bombardier inc.

show abstract

Robustness Evaluation and Improvement for Vision-Based Advanced Driver Assistance Systems

Cited by 12 publications

References 6 publications

Misbehaviour prediction for autonomous driving systems

Misbehaviour prediction for autonomous driving systems

Quality Metrics and Oracles for Autonomous Vehicles Testing

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Contact Info

Product

Resources

About