mlsanityData to 7 Oct 2026

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

arXiv 2009.08311 ↗First posted 16 Sep 2020cs.LG cs.RO stat.MLcited by 54

Not on the map. Why?

Abstract (arXiv)

Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance. However, evaluating the robustness only under the worst-case scenarios based on known attacks is not comprehensive, not to mention that some of them even rarely occur in the real world. In addition, the distribution of safety-critical data is usually multimodal, while most traditional attacks and evaluation methods focus on a single modality. To solve the above challenges, we propose a flow-based multimodal safety-critical scenario generator for evaluating decisionmaking algorithms. The proposed generative model is optimized with weighted likelihood maximization and a gradient-based sampling procedure is integrated to improve the sampling efficiency. The safety-critical scenarios are generated by querying the task algorithms and the log-likelihood of the generated scenarios is in proportion to the risk level. Experiments on a self-driving task demonstrate our advantages in terms of testing efficiency and multimodal modeling capability. We evaluate six Reinforcement Learning algorithms with our generated traffic scenarios and provide empirical conclusions about their robustness.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 8; 2023: 13; 2024: 10; 2025: 10; 2026: 2.

54 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  2. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  3. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  4. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  5. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  6. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 95
  7. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehiclescited by 65
  8. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
  9. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
  10. 2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
  11. 2024Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?cited by 38
  12. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversariescited by 36
38 more
  1. 2023Rethinking Closed-loop Training for Autonomous Drivingcited by 29
  2. 2024SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Trafficcited by 27
  3. 2022Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Trainingcited by 26
  4. 2023SceneDM: Scene-level Multi-agent Trajectory Generation with Consistent Diffusion Modelscited by 24
  5. 2021Learn-to-Race: A Multimodal Control Environment for Autonomous Racingcited by 23
  6. 2021A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulationcited by 21
  7. 2021CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generationcited by 20
  8. 2024AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusioncited by 20
  9. 2021Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehiclescited by 19
  10. 2024Quantifying and Enhancing Multi-modal Robustness with Modality Preferencecited by 16
  11. 2021Diverse Critical Interaction Generation for Planning and Planner Evaluationcited by 15
  12. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priorscited by 15
  13. 2024FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversarialitycited by 13
  14. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectoriescited by 11
  15. 2025Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generationcited by 11
  16. 2022TAE: A Semi-supervised Controllable Behavior-aware Trajectory Generator and Predictorcited by 10
  17. 2023Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulationcited by 10
  18. 2025LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarioscited by 9
  19. 2021Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systemscited by 8
  20. 2025DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Modelscited by 7
  21. 2023(Re)2H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learningcited by 6
  22. 2023Adaptive Failure Search Using Critical States from Domain Expertscited by 4
  23. 2023CC-SGG: Corner Case Scenario Generation using Learned Scene Graphscited by 4
  24. 2025Make Full Use of Testing Information: An Integrated Accelerated Testing and Evaluation Method for Autonomous Driving Systemscited by 4
  25. 2025RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulationcited by 4
  26. 2021ARC: Adversarially Robust Control Policies for Autonomous Vehiclescited by 3
  27. 2024DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Drivingcited by 3
  28. 2025When Digital Twins Meet Large Language Models: Realistic, Interactive, and Editable Simulation for Autonomous Drivingcited by 3
  29. 2021Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Samplingcited by 2
  30. 2022Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learningcited by 2
  31. 2022ECSAS: Exploring Critical Scenarios from Action Sequence in Autonomous Drivingcited by 2
  32. 2021Semantically Adversarial Scenario Generation with Explicit Knowledge Guidancecited by 1
  33. 2024VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustnesscited by 1
  34. 2024LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantizationcited by 1
  35. 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safetycited by 1
  36. 2025Test Automation for Interactive Scenarios via Promptable Traffic Simulationcited by 1
  37. 2025Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Drivingcited by 1
  38. 2023Specification-Guided Data Aggregation for Semantically Aware Imitation Learningcited by 0

50 most cited of 54 All 54 (JSON)