Doppelgänger test generation for revealing bugs in autonomous driving software

Y Huai, Y Chen, S Almanee, T Ngo… - 2023 IEEE/ACM 45th …, 2023 - ieeexplore.ieee.org
Vehicles controlled by autonomous driving software (ADS) are expected to bring many
social and economic benefits, but at the current stage not being broadly used due to …

scenoRITA: Generating Diverse, Fully-Mutable, Test Scenarios for Autonomous Vehicle Planning

Y Huai, S Almanee, Y Chen, X Wu… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Autonomous Vehicles (AVs) leverage advanced sensing and networking technologies (eg,
camera, LiDAR, RADAR, GPS, DSRC, 5G, etc.) to enable safe and efficient driving without …

Discovering adversarial driving maneuvers against autonomous vehicles

R Song, MO Ozmen, H Kim, R Muller, ZB Celik… - 32nd USENIX Security …, 2023 - usenix.org
Over 33% of vehicles sold in 2021 had integrated autonomous driving (AD) systems. While
many adversarial machine learning attacks have been studied against these systems, they …

Twin scenarios establishment for autonomous vehicle digital twin empowered sotif assessment

Z Hou, S Wang, H Liu, Y Yang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The scenario-based tests have been an important means of improving the safety and
reliability of autonomous vehicles (AVs). Moreover, ensuring the fidelity of generated …

ComOpT: Combination and optimization for testing autonomous driving systems

C Li, CH Cheng, T Sun, Y Chen… - … Conference on Robotics …, 2022 - ieeexplore.ieee.org
ComOpT is an open-source research tool for coverage-driven testing of autonomous driving
systems, focusing on planning and control. Starting with (i) a meta-model characterizing …

3D Environment Modeling for Falsification and Beyond with Scenic 3.0

E Vin, S Kashiwa, M Rhea, DJ Fremont, E Kim… - … on Computer Aided …, 2023 - Springer
We present a major new version of Scenic, a probabilistic programming language for writing
formal models of the environments of cyber-physical systems. Scenic has been successfully …

Parallel and Multi-objective Falsification with Scenic and VerifAI

K Viswanadha, E Kim, F Indaheng, DJ Fremont… - … Conference, RV 2021 …, 2021 - Springer
Falsification has emerged as an important tool for simulation-based verification of
autonomous systems. In this paper, we present extensions to the Scenic scenario …

A scenario-based platform for testing autonomous vehicle behavior prediction models in simulation

F Indaheng, E Kim, K Viswanadha, J Shenoy… - arXiv preprint arXiv …, 2021 - arxiv.org
Behavior prediction remains one of the most challenging tasks in the autonomous vehicle
(AV) software stack. Forecasting the future trajectories of nearby agents plays a critical role …

Risk Scenario Generation for Autonomous Driving Systems based on Scenario Evaluation Model

T Wang, X Kuang, H Deng, T Gu… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
The development of deep learning-based au-tonomous driving systems is becoming
increasingly prevalent in recent times, however, several safety concerns have emerged. In …

Watch Out for the Safety-Threatening Actors: Proactively Mitigating Safety Hazards

S Jha, S Cui, Z Kalbarczyk, RK Iyer - arXiv preprint arXiv:2206.00886, 2022 - arxiv.org
Despite the successful demonstration of autonomous vehicles (AVs), such as self-driving
cars, ensuring AV safety remains a challenging task. Although some actors influence an …