mlsanityData to 14 Oct 2026

GENESIS-RL: GEnerating Natural Edge-cases with Systematic Integration of Safety considerations and Reinforcement Learning

arXiv 2403.19062 ↗First posted 27 Mar 2024eess.SY cs.RO cs.SYcited by 3

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

In the rapidly evolving field of autonomous systems, the safety and reliability of the system components are fundamental requirements. These components are often vulnerable to complex and unforeseen environments, making natural edge-case generation essential for enhancing system resilience. This paper presents GENESIS-RL, a novel framework that leverages system-level safety considerations and reinforcement learning techniques to systematically generate naturalistic edge cases. By simulating challenging conditions that mimic the real-world situations, our framework aims to rigorously test entire system's safety and reliability. Although demonstrated within the autonomous driving application, our methodology is adaptable across diverse autonomous systems. Our experimental validation, conducted on high-fidelity simulator underscores the overall effectiveness of this framework.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 27 of its 37 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

27 of 37 references.

References · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  6. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  9. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  10. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  11. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 532
  12. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 137
15 more
  1. 2021Adversarial purification with Score-based generative modelscited by 134
  2. 2018Scenic: A Language for Scenario Specification and Scene Generationcited by 83
  3. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 75
  4. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 68
  5. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 57
  6. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 56
  7. 2020Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluationcited by 55
  8. 2021Auto-Tuned Sim-to-Real Transfercited by 49
  9. 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 47
  10. 2019Liability, Ethics, and Culture-Aware Behavior Specification using Rulebookscited by 43
  11. 2020Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarioscited by 43
  12. 2021DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learningcited by 11
  13. 2022Responsibility-Sensitive Safety: an Introduction with an Eye to Logical Foundations and Formalizationcited by 6
  14. 2022Learning When to Use Adaptive Adversarial Image Perturbations against Autonomous Vehiclescited by 3
  15. 2023Is Scenario Generation Ready for SOTIF? A Systematic Literature Reviewcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perceptioncited by 2
  2. 2024Incorporating System-level Safety Requirements in Perception Models via Reinforcement Learningcited by 0
  3. 2026LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
  2. 2025Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
  3. 2026World Engine: Towards the Era of Post-Training for Autonomous Driving
  4. 2026ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
  5. 2025AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
  6. 2026SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous Driving
  7. 2023Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving
  8. 2022How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies