mlsanityData to 7 Oct 2026

ReMAV: Reward Modeling of Autonomous Vehicles for Finding Likely Failure Events

arXiv 2308.14550 ↗First posted 28 Aug 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous vehicles are advanced driving systems that are well known to be vulnerable to various adversarial attacks, compromising vehicle safety and posing a risk to other road users. Rather than actively training complex adversaries by interacting with the environment, there is a need to first intelligently find and reduce the search space to only those states where autonomous vehicles are found to be less confident. In this paper, we propose a black-box testing framework ReMAV that uses offline trajectories first to analyze the existing behavior of autonomous vehicles and determine appropriate thresholds to find the probability of failure events. To this end, we introduce a three-step methodology which i) uses offline state action pairs of any autonomous vehicle under test, ii) builds an abstract behavior representation using our designed reward modeling technique to analyze states with uncertain driving decisions, and iii) uses a disturbance model for minimal perturbation attacks where the driving decisions are less confident. Our reward modeling technique helps in creating a behavior representation that allows us to highlight regions of likely uncertain behavior even when the standard autonomous vehicle performs well. We perform our experiments in a high-fidelity urban driving environment using three different driving scenarios containing single- and multi-agent interactions. Our experiment shows an increase in 35, 23, 48, and 50% in the occurrences of vehicle collision, road object collision, pedestrian collision, and offroad steering events, respectively by the autonomous vehicle under test, demonstrating a significant increase in failure events. We compare ReMAV with two baselines and show that ReMAV demonstrates significantly better effectiveness in generating failure events compared to the baselines in all evaluation metrics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 28 Aug 2023.

Builds on

38 of 60 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  8. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  9. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  10. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  11. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  12. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
26 more
  1. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  2. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 70
  3. 2018On Offline Evaluation of Vision-based Driving Modelscited by 62
  4. 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 62
  5. 2019Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Drivingcited by 36
  6. 2020Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Drivingcited by 34
  7. 2022Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Drivingcited by 34
  8. 2019Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validationcited by 33
  9. 2019Attacking Vision-based Perception in End-to-End Autonomous Driving Modelscited by 31
  10. 2019Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Drivingcited by 30
  11. 2020Robustifying Reinforcement Learning Agents via Action Space Adversarial Trainingcited by 30
  12. 2019Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Studycited by 27
  13. 2021Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehiclescited by 19
  14. 2022DriveFuzz: Discovering Autonomous Driving Bugs through Driving Quality-Guided Fuzzingcited by 19
  15. 2022How Do We Fail? Stress Testing Perception in Autonomous Vehiclescited by 17
  16. 2020Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agentscited by 15
  17. 2018Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehiclescited by 14
  18. 2020Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositingcited by 10
  19. 2020A Declarative Metamorphic Testing Framework for Autonomous Drivingcited by 10
  20. 2021Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policiescited by 10
  21. 2022Lifelong Inverse Reinforcement Learningcited by 9
  22. 2019Yes, we GAN: Applying Adversarial Techniques for Autonomous Drivingcited by 7
  23. 2019Zero-Shot Autonomous Vehicle Policy Transfer: From Simulation to Real-World via Adversarial Learningcited by 7
  24. 2021Finding Failures in High-Fidelity Simulation using Adaptive Stress Testing and the Backward Algorithmcited by 7
  25. 2022Software Testing for Machine Learningcited by 5
  26. 2021Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-agent Urban Driving Environmentcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
  2. 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests
  3. 2024Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles
  4. 2023Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving
  5. 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios
  6. 2025Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
  7. 2026SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
  8. 2024A novel framework for adaptive stress testing of autonomous vehicles in multi-lane roads