SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

As shown by recent studies, machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts. This has raised great concerns about deploying machine learning algorithms for real-world applications, especially in safety-critical domains such as autonomous driving (AD). On the other hand, traditional AD testing on naturalistic scenarios requires hundreds of millions of driving miles due to the high dimensionality and rareness of the safety-critical scenarios in the real world. As a result, several approaches for autonomous driving evaluation have been explored, which are usually, however, based on different simulation platforms, types of safety-critical scenarios, scenario generation algorithms, and driving route variations. Thus, despite a large amount of effort in autonomous driving testing, it is still challenging to compare and understand the effectiveness and efficiency of different testing scenario generation algorithms and testing mechanisms under similar conditions. In this paper, we aim to provide the first unified platform SafeBench to integrate different types of safety-critical testing scenarios, scenario generation algorithms, and other variations such as driving routes and environments. Meanwhile, we implement 4 deep reinforcement learning-based AD algorithms with 4 types of input (e.g., bird's-eye view, camera) to perform fair comparisons on SafeBench. We find our generated testing scenarios are indeed more challenging and observe the trade-off between the performance of AD agents under benign and safety-critical testing scenarios. We believe our unified platform SafeBench for large-scale and effective autonomous driving testing will motivate the development of new testing scenario generation and safe AD algorithms. SafeBench is available at https://safebench.github.io.

[1]  Bolei Zhou,et al.  MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jie Tan,et al.  On the Robustness of Safe Reinforcement Learning under Observational Perturbations , 2022, ICLR.

[3]  D. Rojas-Gualdrón.  Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril. National Academy of Medicine. Una reseña , 2022, CES Medicina.

[4]  Qi Alfred Chen,et al.  On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Igor Gilitschenski,et al.  VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles , 2021, 2022 International Conference on Robotics and Automation (ICRA).

[6]  Daniel McDuff,et al.  CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning , 2021, CLeaR.

[7]  Victor Talpaert,et al.  Deep Reinforcement Learning for Autonomous Driving: A Survey , 2020, IEEE Transactions on Intelligent Transportation Systems.

[8]  Masayoshi Tomizuka,et al.  Interpretable End-to-End Urban Autonomous Driving With Latent Deep Reinforcement Learning , 2020, IEEE Transactions on Intelligent Transportation Systems.

[9]  Kristofer D. Kusano,et al.  Waymo simulated driving behavior in reconstructed fatal crashes within an autonomous vehicle operating domain. , 2021, Accident; analysis and prevention.

[10]  Matthias Althoff,et al.  CommonRoad-RL: A Configurable Reinforcement Learning Environment for Motion Planning of Autonomous Vehicles , 2021, 2021 IEEE International Intelligent Transportation Systems Conference (ITSC).

[11]  Xi Ganga.  Educational Artificial Intelligence (EAI) Connotation, Key Technology and Application Trend -Interpretation and analysis of the two reports entitled “Preparing for the Future of Artificial Intelligence” and “The National Artificial Intelligence Research and Development Strategic Plan” , 2021, 2021 International Conference on Intelligent Computing, Automation and Applications (ICAA).

[12]  Ruigang Yang,et al.  Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks , 2021, 2021 IEEE Symposium on Security and Privacy (SP).

[13]  Bingqing Chen,et al.  Learn-to-Race: A Multimodal Control Environment for Autonomous Racing , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Tanmay Vilas Samak,et al.  AutoDRIVE Simulator: A Simulator for Scaled Autonomous Vehicle Research and Education , 2021, CCRIS.

[15]  Henry X. Liu,et al.  Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment , 2021, Nature Communications.

[16]  R. Urtasun,et al.  AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Wenhao Ding,et al.  Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation , 2020, IEEE Robotics and Automation Letters.

[18]  Bhavya Kailkhura,et al.  TSS: Transformation-Specific Smoothing for Robustness Certification , 2020, CCS.

[19]  Wenhao Ding,et al.  Semantically Controllable Scene Generation with Guidance of Explicit Knowledge , 2021, ArXiv.

[20]  Christian Knies,et al.  Data-Driven Test Scenario Generation for Cooperative Maneuver Planning on Highways , 2020, Applied Sciences.

[21]  Dong Chen,et al.  SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving , 2020, ArXiv.

[22]  Paolo Arcaini,et al.  Generating Avoidable Collision Scenarios for Testing Autonomous Driving Systems , 2020, 2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST).

[23]  Hayder Radha,et al.  CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Xinge Zhu,et al.  Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation , 2020, ArXiv.

[25]  Wenhao Ding,et al.  Deep Probabilistic Accelerated Evaluation: A Certifiable Rare-Event Simulation Methodology for Black-Box Autonomy , 2020, ArXiv.

[26]  Kyungeun Cho,et al.  A scenario generation pipeline for autonomous vehicle simulators , 2020, Human-centric Computing and Information Sciences.

[27]  Arno Blaas,et al.  BayesOpt Adversarial Attack , 2020, ICLR.

[28]  Bichen Wu,et al.  SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation , 2020, ECCV.

[29]  Philip David,et al.  PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Wenhao Ding,et al.  Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[31]  David Hsu,et al.  SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic , 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Wenhao Ding,et al.  CMTS: A Conditional Multiple Trajectory Synthesizer for Generating Safety-Critical Driving Scenarios , 2019, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Huei Peng,et al.  Developing Robot Driver Etiquette Based on Naturalistic Human Driving Behavior , 2018, IEEE Transactions on Intelligent Transportation Systems.

[34]  Conducting the Mcity ABC Test: A Testing Method for Highly Automated Vehicles , 2020 .

[35]  Sameer Singh,et al.  Universal Adversarial Triggers for Attacking and Analyzing NLP , 2019, EMNLP.

[36]  Pierre Baldi,et al.  Solving the Rubik’s cube with deep reinforcement learning and search , 2019, Nature Machine Intelligence.

[37]  Masayoshi Tomizuka,et al.  Model-free Deep Reinforcement Learning for Urban Autonomous Driving , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[38]  Cyrill Stachniss,et al.  SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[39]  Chong Xiang,et al.  Generating 3D Adversarial Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Dario Amodei,et al.  Benchmarking Safe Exploration in Deep Reinforcement Learning , 2019 .

[41]  Demis Hassabis,et al.  A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play , 2018, Science.

[42]  Ding Zhao,et al.  RARE-EVENT SIMULATION WITHOUT STRUCTURAL INFORMATION: A LEARNING-BASED APPROACH , 2018, 2018 Winter Simulation Conference (WSC).

[43]  Bo Li,et al.  SECOND: Sparsely Embedded Convolutional Detection , 2018, Sensors.

[44]  Russ Tedrake,et al.  Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation , 2018, NeurIPS.

[45]  Wenshuo Wang,et al.  A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters , 2018 .

[46]  Ding Zhao,et al.  Synthesis of Different Autonomous Vehicles Test Approaches , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[47]  Eric Thorn,et al.  A Framework for Automated Driving System Testable Cases and Scenarios , 2018 .

[48]  Annibale Panichella,et al.  Testing Autonomous Cars for Feature Interaction Failures using Many-Objective Search , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).

[49]  Herke van Hoof,et al.  Addressing Function Approximation Error in Actor-Critic Methods , 2018, ICML.

[50]  Yue Zhao,et al.  CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition , 2018, USENIX Security Symposium.

[51]  David A. Wagner,et al.  Audio Adversarial Examples: Targeted Attacks on Speech-to-Text , 2018, 2018 IEEE Security and Privacy Workshops (SPW).

[52]  Sergey Levine,et al.  Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor , 2018, ICML.

[53]  Yaohui Guo,et al.  A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods , 2017, 2018 Annual American Control Conference (ACC).

[54]  Markus Maurer,et al.  Ontology based Scene Creation for the Development of Automated Vehicles , 2017, 2018 IEEE Intelligent Vehicles Symposium (IV).

[55]  Ding Zhao,et al.  Accelerated Evaluation of Automated Vehicles in Car-Following Maneuvers , 2016, IEEE Transactions on Intelligent Transportation Systems.

[56]  Germán Ros,et al.  CARLA: An Open Urban Driving Simulator , 2017, CoRL.

[57]  Simon Oh,et al.  SimMobility Short-Term: An Integrated Microscopic Mobility Simulator , 2017 .

[58]  Atul Prakash,et al.  Robust Physical-World Attacks on Machine Learning Models , 2017, ArXiv.

[59]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[60]  Ding Zhao,et al.  Sequential experimentation to efficiently test automated vehicles , 2017, 2017 Winter Simulation Conference (WSC).

[61]  Brigitte d'Andréa-Novel,et al.  The kinematic bicycle model: A consistent model for planning feasible trajectories for autonomous vehicles? , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[62]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[63]  Etienne Perot,et al.  Deep Reinforcement Learning framework for Autonomous Driving , 2017, Autonomous Vehicles and Machines.

[64]  Sandy H. Huang,et al.  Adversarial Attacks on Neural Network Policies , 2017, ICLR.

[65]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[66]  Ding Zhao,et al.  Accelerated Evaluation of Automated Vehicles. , 2016 .

[67]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[68]  Ding Zhao,et al.  Accelerated evaluation of automated vehicles using extracted naturalistic driving data , 2016 .

[69]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[70]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[71]  Dirk Merkel,et al.  Docker: lightweight Linux containers for consistent development and deployment , 2014 .

[72]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[73]  Blaine Nelson,et al.  Adversarial machine learning , 2019, AISec '11.

[74]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[75]  Gerardo Rubino,et al.  Introduction to Rare Event Simulation , 2009, Rare Event Simulation using Monte Carlo Methods.

[76]  Wassim G. Najm,et al.  Pre-Crash Scenario Typology for Crash Avoidance Research , 2007 .

[77]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[78]  To all authors , 1995 .

[79]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.