nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems

November 16, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, .gitmodules, GTSRB_AdditionalMetrics.ipynb, GTSRB_Neuron2ProjectionCoverage_TestGen.ipynb, GTSRB_RuntimeMonitoring.ipynb, KITTI_Scenario_Coverage.ipynb, LICENSE, MNIST_Neuron2ProjectionCoverage_TestGen.ipynb, MNIST_RuntimeMonitoring.ipynb, README.md, SSD_InterpretationPrecision.ipynb, Scenario_Coverage_A9.ipynb, Scenario_Coverage_simple.ipynb, TargetVehicleProcessingNetwork_FormalVerification.ipynb, data, img, kitti_scenario_creator.py, manual_latex, models, nn_dependability_kit_manual.pdf, nndependability, requirements.txt, util.py

Authors Chih-Hong Cheng, Chung-Hao Huang, Georg Nührenberg arXiv ID 1811.06746 Category cs.LG: Machine Learning Cross-listed stat.ML Citations 11 Venue arXiv.org Repository https://github.com/dependable-ai/nn-dependability-kit ⭐ 34 Last Checked 1 month ago

Abstract

Can engineering neural networks be approached in a disciplined way similar to how engineers build software for civil aircraft? We present nn-dependability-kit, an open-source toolbox to support safety engineering of neural networks for autonomous driving systems. The rationale behind nn-dependability-kit is to consider a structured approach (via Goal Structuring Notation) to argue the quality of neural networks. In particular, the tool realizes recent scientific results including (a) novel dependability metrics for indicating sufficient elimination of uncertainties in the product life cycle, (b) formal reasoning engine for ensuring that the generalization does not lead to undesired behaviors, and (c) runtime monitoring for reasoning whether a decision of a neural network in operation is supported by prior similarities in the training data. A proprietary version of nn-dependability-kit has been used to improve the quality of a level-3 autonomous driving component developed by Audi for highway maneuvers.