# Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulations

arXiv: https://arxiv.org/abs/2301.01594 · HTML: https://mlsanity.com/paper/2301.01594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 3 Jan 2023.

## Builds on (most cited first, 11 of 11)

- [Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior](https://mlsanity.com/paper/2112.05077/) (2021)
- [Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data](https://mlsanity.com/paper/1810.10093/) (2018)
- [Scenic: A Language for Scenario Specification and Scene Generation](https://mlsanity.com/paper/1809.09310/) (2018)
- [Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation](https://mlsanity.com/paper/1811.00145/) (2018)
- [Constrained Efficient Global Optimization of Expensive Black-box Functions](https://mlsanity.com/paper/2211.00162/) (2022)
- [Scenarios for Development, Test and Validation of Automated Vehicles](https://mlsanity.com/paper/1801.08598/) (2018)
- [Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World](https://mlsanity.com/paper/2003.07739/) (2020)
- [Compositional Falsification of Cyber-Physical Systems with Machine Learning Components](https://mlsanity.com/paper/1703.00978/) (2017)
- [Waymo's Safety Methodologies and Safety Readiness Determinations](https://mlsanity.com/paper/2011.00054/) (2020)
- [Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models](https://mlsanity.com/paper/2101.10747/) (2021)
- [Verifying Controllers Against Adversarial Examples with Bayesian Optimization](https://mlsanity.com/paper/1802.08678/) (2018)

## Abstract (arXiv)

The increase in complexity of autonomous systems is accompanied by a need of data-driven development and validation strategies. Advances in computer graphics and cloud clusters have opened the way to massive parallel high fidelity simulations to qualitatively address the large number of operational scenarios. However, exploration of all possible scenarios is still prohibitively expensive and outcomes of scenarios are generally unknown apriori. To this end, the authors propose a method based on bayesian optimization to efficiently learn generative models on scenarios that would deliver desired outcomes (e.g. collisions) with high probability. The methodology is integrated in an end-to-end framework, which uses the OpenSCENARIO standard to describe scenarios, and deploys highly configurable digital twins of the scenario participants on a Virtual Test Bed cluster.