# A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods

arXiv: https://arxiv.org/abs/1710.00283 · HTML: https://mlsanity.com/paper/1710.00283/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2017.

## Built on by (most cited first, 5 of 5)

- [SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles](https://mlsanity.com/paper/2206.09682/) (2022)
- [A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation](https://mlsanity.com/paper/2112.00964/) (2021)
- [Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments](https://mlsanity.com/paper/2407.15839/) (2024)
- [Verifying Inverse Model Neural Networks](https://mlsanity.com/paper/2202.02429/) (2022)
- [Test Against High-Dimensional Uncertainties: Accelerated Evaluation of Autonomous Vehicles with Deep Importance Sampling](https://mlsanity.com/paper/2204.02351/) (2022)

## Abstract (arXiv)

Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critical failures via smartly-sampled test cases. The distribution used in sampling is pivotal to the performance of the method, but building a suitable distribution requires case-by-case analysis. This paper proposes a versatile approach for constructing sampling distribution using kernel method. The approach uses statistical learning tools to approximate the critical event sets and constructs distributions based on the unique properties of Gaussian distributions. We applied the method to evaluate the automated vehicles. Numerical experiments show proposed approach can robustly identify the rare failures and significantly reduce the evaluation time.