# Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems

arXiv: https://arxiv.org/abs/2008.10581 · HTML: https://mlsanity.com/paper/2008.10581/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 30 of 35)

- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [Density Ratio Estimation via Infinitesimal Classification](https://mlsanity.com/paper/2111.11010/) (2021)
- [From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence](https://mlsanity.com/paper/2110.15245/) (2021)
- [A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation](https://mlsanity.com/paper/2112.00964/) (2021)
- [Density Ratio Estimation with Conditional Probability Paths](https://mlsanity.com/paper/2502.02300/) (2025)
- [A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis](https://mlsanity.com/paper/2112.05745/) (2021)
- [Learning to Drive via Asymmetric Self-Play](https://mlsanity.com/paper/2409.18218/) (2024)
- [End-to-End Supervised Multilabel Contrastive Learning](https://mlsanity.com/paper/2307.03967/) (2023)
- [Testing Rare Downstream Safety Violations via Upstream Adaptive Sampling of Perception Error Models](https://mlsanity.com/paper/2209.09674/) (2022)
- [FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing](https://mlsanity.com/paper/2310.16073/) (2023)
- [Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2406.14761/) (2024)
- [Projection Pursuit Density Ratio Estimation](https://mlsanity.com/paper/2506.00866/) (2025)
- [A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation](https://mlsanity.com/paper/2110.02739/) (2021)
- [Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms](https://mlsanity.com/paper/2210.16575/) (2022)
- [Model-based Validation as Probabilistic Inference](https://mlsanity.com/paper/2305.09930/) (2023)
- [Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments](https://mlsanity.com/paper/2407.15839/) (2024)
- [Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling](https://mlsanity.com/paper/2411.17826/) (2024)
- [ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs](https://mlsanity.com/paper/2106.05325/) (2021)
- [Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios](https://mlsanity.com/paper/2110.02892/) (2021)
- [A Deep Reinforcement Learning Approach to Rare Event Estimation](https://mlsanity.com/paper/2211.12470/) (2022)
- [Identifying the Hazard Boundary of ML-enabled Autonomous Systems Using Cooperative Co-Evolutionary Search](https://mlsanity.com/paper/2301.13807/) (2023)
- [Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learning](https://mlsanity.com/paper/2402.19275/) (2024)
- [Hybrid Systems Neural Control with Region-of-Attraction Planner](https://mlsanity.com/paper/2303.10327/) (2023)
- [Attacking Motion Planners Using Adversarial Perception Errors](https://mlsanity.com/paper/2311.12722/) (2023)
- [Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows](https://mlsanity.com/paper/2501.03394/) (2025)
- [Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?](https://mlsanity.com/paper/2502.21110/) (2025)
- [Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey](https://mlsanity.com/paper/2111.14324/) (2021)
- [GANISP: a GAN-assisted Importance SPlitting Probability Estimator](https://mlsanity.com/paper/2112.15444/) (2021)
- [Adaptive Splitting of Reusable Temporal Monitors for Rare Traffic Violations](https://mlsanity.com/paper/2405.15771/) (2024)
- [Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions](https://mlsanity.com/paper/2505.12327/) (2025)

## Abstract (arXiv)

Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-world testing is prohibitively expensive and unscalable. In this work, we employ a probabilistic approach to safety evaluation in simulation, where we are concerned with computing the probability of dangerous events. We develop a novel rare-event simulation method that combines exploration, exploitation, and optimization techniques to find failure modes and estimate their rate of occurrence. We provide rigorous guarantees for the performance of our method in terms of both statistical and computational efficiency. Finally, we demonstrate the efficacy of our approach on a variety of scenarios, illustrating its usefulness as a tool for rapid sensitivity analysis and model comparison that are essential to developing and testing safety-critical autonomous systems.