Diffusion-based Deep Generative Models for Assessing Safety in Autonomous Vehicles.

用于评估自动驾驶汽车安全性的基于扩散的深度生成模型。

• 批准号: 2608246
• 金额: --
• 依托单位: Lancaster University
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2608246
• 关键词: Diffusion; based; Deep; Generative; Models

It is hoped that the use of autonomous vehicles will significantly reduce the number of road accidents due to human error. However, extensive testing will be necessary to demonstrate that they satisfy a high standard of safety before they can be introduced. Much of this testing must be carried out in simulated environments, which allow for a far greater degree of safety and flexibility than road testing. This is done by testing the vehicle AI on a set of predetermined scenarios. Examples of scenarios include recovering from a loss of control due to road conditions, performing manoeuvres in the presence of oncoming traffic, and responding to a sudden deceleration by a leading vehicle. A key issue in autonomous vehicle safety is the need for a huge, diverse set of scenarios that reflect both normal driving conditions and difficult situations. This project aims to develop methods for automating scenario generation, both by reconstructing conditions from real life driving datasets, and by creating completely new scenarios using statistical generative modelling techniques from the statistical AI literature, such as generative adversarial networks and variational auto encoders.The problem with current generative modelling techniques is to generate realistic scenarios from the same underlying distribution as a given dataset. Diffusion-based models are a recent advance in generative modelling, which use stochastic differential equations to gradually transform random noise into data via a diffusion process. This is learned by training a neural network to remove small amounts of noise from existing data. They are efficient to train and have been shown to be effective at generating diverse samples from complex, high-dimensional distributions. This research project will focus on the statistical properties of diffusion models and how they can be adapted for the scenario generation problem to generate realistic new scenarios given an existing database.In partnership with Transport Research Laboratory.

人们希望自动驾驶汽车的使用将大大减少由于人为错误造成的道路事故。然而，在引进这些设备之前，必须进行广泛的测试，以证明它们符合高标准的安全性。大部分测试必须在模拟环境中进行，这比道路测试具有更高的安全性和灵活性。这是通过在一组预定场景下测试车辆AI来完成的。场景的示例包括从由于道路状况而失去控制的情况下恢复，在迎面而来的车辆存在的情况下执行机动，以及对领先车辆的突然减速做出响应。自动驾驶汽车安全的一个关键问题是需要一个巨大的，多样化的场景集，既反映正常的驾驶条件和困难的情况。该项目旨在开发自动生成场景的方法，既通过从真实的生活驾驶数据集重建条件，又通过使用统计人工智能文献中的统计生成建模技术创建全新的场景，例如生成对抗网络和变分自动编码器。当前生成建模技术的问题是从与给定的数据集。基于扩散的模型是生成建模的最新进展，它使用随机微分方程通过扩散过程逐渐将随机噪声转换为数据。这是通过训练神经网络从现有数据中去除少量噪声来学习的。它们的训练效率很高，并且已被证明可以有效地从复杂的高维分布中生成不同的样本。该研究项目将集中在扩散模型的统计特性，以及如何将其应用于场景生成问题，以在现有数据库的基础上生成现实的新场景。