ANTI-CARLA: An Adversarial Testing Framework for Autonomous Vehicles in CARLA
Authors:
- 8 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2620-2627
Abstract
Despite recent advances in autonomous driving systems, accidents such as the fatal Uber crash in 2018 show these systems are still susceptible to edge cases. Such systems must be thoroughly tested and validated before being deployed in the real world to avoid such events. Testing in open-world scenarios can be difficult, time-consuming, and expensive. These challenges can be addressed by using driving simulators such as CARLA instead. A key part of such tests is adversarial testing, in which the goal is to find scenarios that lead to failures of the given system. While several independent efforts in testing have been made, a well-established testing framework that enables adversarial testing has yet to be made available for CARLA. We therefore propose ANTI-CARLA, an automated testing framework in CARLA for simulating adversarial weather conditions (e.g., heavy rain) and sensor faults (e.g., camera occlusion) that fail the system. The operating conditions in which a given system should be tested are specified in a scenario description language. The framework offers an efficient search mechanism that searches for adversarial operating conditions that will fail the tested system. In this way, ANTI-CARLA extends the CARLA simulator with the capability of performing adversarial testing on any given driving pipeline. We use ANTI-CARLA to test the driving pipeline trained with Learning By Cheating (LBC) approach. The simulation results demonstrate that ANTI-CARLA can effectively and automatically find a range of failure cases despite LBC reaching an accuracy of 100% in the CARLA benchmark.Keywords
All Related Versions
Funding Information
- DARPA
- Air Force Research Laboratory
This publication has 26 references indexed in Scilit:
- Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Components2018
- Sim-ATAV2018
- AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles2017
- Accelerated Evaluation of Automated Vehicles in Car-Following ManeuversIEEE Transactions on Intelligent Transportation Systems, 2017
- TextX: A Python tool for Domain-Specific Languages implementationKnowledge-Based Systems, 2017
- Utilizing S-TaLiRo as an automatic test generation framework for autonomous vehicles2016
- The Automotive Standard ISO 26262, the Innovative Driver for Enhanced Safety Assessment & Technology for Motor CarsProcedia Engineering, 2012
- The Managed Adapter Pattern: Facilitating Glue Code Generation for Component ReuseLecture Notes in Computer Science, 2009
- Generating MC/DC adequate test sequences through model checking2004
- On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integralsNumerische Mathematik, 1960