Filters








10 Hits in 2.9 sec

Single and Multi-objective Test Cases Prioritization for Self-driving Cars in Virtual Environments [article]

Christian Birchler, Sajad Khatiri, Pouria Derakhshanfar, Sebastiano Panichella, Annibale Panichella
2022 arXiv   pre-print
Testing with simulation environments helps to identify critical failing scenarios for self-driving cars (SDCs).  ...  Simulation-based tests are safer than in-field operational tests and allow detecting software defects before deployment.  ...  From a high-level point of view, AsFault combines procedural content generation and search-based testing in order to automatically create virtual scenarios for testing the lane-keeping behavior in SDC  ... 
arXiv:2107.09614v2 fatcat:zhdvmm2wczhcvnmm6zr563mlu4

A Search-Based Framework for Automatic Generation of Testing Environments for Cyber-Physical Systems [article]

Dmytro Humeniuk, Foutse Khomh, Giuliano Antoniol
2022 arXiv   pre-print
In this paper, we aim to design a search based framework, named AmbieGen, for generating diverse fault revealing test scenarios for autonomous cyber physical systems.  ...  We compared three configurations of AmbieGen: based on a single objective genetic algorithm, multi objective, and random search.  ...  Examples include drone swarms, self driving cars, cave or underwater exploring robots.  ... 
arXiv:2203.12138v1 fatcat:2r6kpk3tobgxlfmjiwilr6dlnq

Misbehaviour Prediction for Autonomous Driving Systems [article]

Andrea Stocco, Michael Weiss, Marco Calzana, Paolo Tonella
2019 arXiv   pre-print
SelfOracle uses autoencoder and time-series-based anomaly detection to reconstruct the driving scenarios seen by the car, and determine the confidence boundary of normal/unsupported conditions.  ...  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.  ...  [13] propose AsFault, a search-based test generator for autonomous vehicles based on procedural content generation.  ... 
arXiv:1910.04443v1 fatcat:rp3o6lp3fvcgtbsagnw7hn4d2e

Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review

Nijat Rajabli, Francesco Flammini, Roberto Nardone, Valeria Vittorini
2020 IEEE Access  
Autonomous, or self-driving, cars are emerging as the solution to several problems primarily caused by humans on roads, such as accidents and traffic congestion.  ...  In fact, due to the possibly unpredictable nature of Artificial Intelligence (AI), its use in autonomous cars creates concerns that need to be addressed using appropriate V&V processes that can address  ...  The tool uses a searchbased procedural content generation technique and is demonstrated by tests performed on lane-keeping functionality in an autonomous car program.  ... 
doi:10.1109/access.2020.3048047 fatcat:7mgx34zscvfavenyznqmbul7cm

Testing, Validation, and Verification of Robotic and Autonomous Systems: A Systematic Review

Hugo Araujo, Mohammad Reza Mousavi, Mahsa Varshosaz
2022 ACM Transactions on Software Engineering and Methodology  
First, we made use of a set of 26 seed papers (selected by domain experts) and the SERP-TEST taxonomy to design our search query and (domain-specific) taxonomy.  ...  Our survey is performed based on a rigorous methodology structured in three phases.  ...  The tool combines procedural content generation and search-based testing in order to automatically create challenging virtual scenarios for testing self-driving car software.  ... 
doi:10.1145/3542945 fatcat:b6hshtzmrfep3ba7t6brl6kfbu

Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles [article]

Ziyuan Zhong, Gail Kaiser, Baishakhi Ray
2022 arXiv   pre-print
Self-driving cars and trucks, autonomous vehicles (AVs), should not be accepted by regulatory bodies and the public until they have much higher confidence in their safety and reliability -- which can most  ...  To address these limitations, we propose a new fuzz testing technique, called AutoFuzz, which can leverage widely-used AV simulators' API grammars to generate semantically and temporally valid complex  ...  INTRODUCTION The rapid growth of autonomous driving technologies has made self-driving cars around the corner.  ... 
arXiv:2109.06126v4 fatcat:auiyji7xqbahzikqoawf7hnwsa

Confidence‐driven weighted retraining for predicting safety‐critical failures in autonomous driving systems

Andrea Stocco, Paolo Tonella
2021 Journal of Software: Evolution and Process  
We evaluate our framework to improve a misbehavior predictor from the literature on the Udacity simulator for self-driving cars. Our results show  ...  Our framework guides adaptive retraining using a novel combination of in-field confidence metric selection and reconstruction error-based weighing.  ...  autonomous vehicles based on procedural content generation.  ... 
doi:10.1002/smr.2386 fatcat:zzjiqx42bjh6zcpktszf36hgzu

Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study [article]

Fitash Ul Haq, Donghwan Shin, Shiva Nejati, Lionel Briand
2019 arXiv   pre-print
We distinguish two general modes of testing for DNNs: Offline testing where DNNs are tested as individual units based on test datasets obtained independently from the DNNs under test, and online testing  ...  Though these questions are generally relevant to all autonomous systems, we study them in the context of automated driving systems where, as study subjects, we use DNNs automating end-to-end control of  ...  [30] 2019 Online Lane keeping Automatic virtual road network generation using search-based Procedural Content Generation (PCG) Kim et al.  ... 
arXiv:1912.00805v1 fatcat:ktf5py26ljc5rjvjjtzuyefcs4

Single and multi-objective test cases prioritization for self-driving cars in virtual environments

Christian Birchler, Sajad Khatiri, Pouria Derakhshanfar, Sebastiano Panichella, Annibale Panichella
2022
Testing with simulation environments helps to identify critical failing scenarios for self-driving cars (SDCs).  ...  CCS Concepts: • Software and its engineering → Search-based software engineering; Software testing and debugging.  ...  From a high-level point of view, AsFault combines procedural content generation and search-based testing in order to automatically create virtual scenarios for testing the lane-keeping behavior in SDC  ... 
doi:10.21256/zhaw-25590 fatcat:wyv2wcpggjaa5ecs6lo5koua24

A Survey on Mobile Crowdsensing Systems: Challenges, Solutions and Opportunities

Andrea Capponi, Claudio Fiandrino, Burak Kantarci, Luca Foschini, Dzmitry Kliazovich, Pascal Bouvry
2019 IEEE Communications Surveys and Tutorials  
Usually, cellular connectivity is used when a sensing campaign requires data delivery with bounds on latency that WiFi does not guarantee because of its unavailability in many places and contention-based  ...  Safestreet is an application that aggregates data from several smartphones to monitor the condition of the road surface for a safer driving and less risk of car accidents [144] .  ... 
doi:10.1109/comst.2019.2914030 fatcat:psvt24nrjbcldpixw6b7stzm3a