Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures
Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)（计算机科学与人工智能实验室（CSAIL），麻省理工学院（MIT））
Ashkan Jasour, Xin Huang, Allen Wang, Brian C. Williams
备注：
Accepted at Autonomous Robots. Author version, with 11 pages, 5 figures, 2 tables. Journal extension of "Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures" (Wang et al. RSS 2020, arXiv:2005.13458)
This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.
Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps
Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA（加州大学伯克利分校土木与环境工程系）；D3 Analytics Innovation, Allstate Insurance Company, Northbrook, IL, USA（Allstate保险公司D3 Analytics创新部门）；Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA（加州大学伯克利分校电气工程与计算机科学系）
LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学网络安全学院）
Statistically Valid Variable Importance Assessment through Conditional Permutations
Inria（法国国家信息与自动化研究所）；Universite Paris Saclay（巴黎萨克雷大学）；CEA（法国原子能委员会）；Roche Pharma Research and Early Development（罗氏制药研究与早期开发部）；Neuroscience and Rare Diseases（神经科学与罕见病部门）；Roche Innovation Center Basel（罗氏巴塞尔创新中心）；F. Hoffmann–La Roche Ltd.（豪夫迈·罗氏有限公司）
Probabilistic Conformal Prediction with Approximate Conditional Validity
Lagrange Mathematics and Computing Research Center（拉格朗日数学与计算研究中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Ecole Polytechnique（巴黎综合理工学院）
Open Set Recognition with Conditional Probabilistic Generative Models
Nanyang Technological University（南洋理工大学）
深度神经网络在广泛的视觉理解任务中取得了突破。阻碍其现实应用的一个典型挑战是，在测试阶段可能会将未知样本输入系统，但传统的深度神经网络会错误地将这些未知样本识别为已知类别之一。开集识别（Open Set Recognition，OSR）是解决这一问题的一种有效方法，它要求开集分类器具有拒绝未知样本的灵活性，同时在已知类别中保持较高的分类精度。概率生成模型，如变分自编码器（VAE）和对抗性自编码器（AAE），是检测未知数的流行方法，但它们不能为已知分类提供判别表示。在本文中，我们提出了一个新的框架，称为条件概率生成模型（CPGM），开集识别。我们工作的核心见解是将判别信息添加到概率生成模型中，使得所提出的模型不仅可以检测未知样本，还可以通过强制不同的潜在特征近似条件高斯分布来分类已知类别。我们讨论了许多模型变体，并提供了全面的实验来研究它们的特性。在多个基准数据集上的实验结果表明，该方法的性能明显优于基线，达到了新的最先进的性能。
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
School of Computation, Information and Technology, Technical University of Munich（计算、信息与技术学院，慕尼黑技术大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Connecting Surrogate Safety Measures to Crash Probablity via Causal Probabilistic Time Series Prediction
University of California, Berkeley（加州大学伯克利分校）；Safe Transportation Research and Education Center（安全交通研究与教育中心）；Institute of Transportation Studies（交通研究所）
A Knowledge-Informed Large Language Model Framework for U.S. Nuclear Power Plant Shutdown Initiating Event Classification for Probabilistic Risk Assessment
University of Idaho（爱达荷大学）；Idaho National Laboratory（爱达荷国家实验室）
Probabilistic data quality assessment for structural monitoring data via outlier-resistant conditional diffusion model
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology（工业和信息化部智能防灾减灾重点实验室）；School of Civil Engineering, Harbin Institute of Technology（哈尔滨工业大学土木工程学院）；Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education（教育部结构动力行为与控制重点实验室）；Harbin Institute of Technology（哈尔滨工业大学）
Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
Graduate University of Advanced Studies & The Institute of Statistical Mathematics（高级研究大学及统计数学研究所）；East China Normal University（华东师范大学）；The Institute of Statistical Mathematics（统计数学研究所）
Spacecraft Collision Risk Assessment with Probabilistic Programming
University of Strathclyde（思克莱德大学）；University of Oxford（牛津大学）；Technische Universität Darmstadt（达姆施塔特工业大学）；IBM（国际商业机器公司（IBM））；Imperial College London（伦敦帝国学院）；European Space Agency（欧洲空间局）；University of Surrey（萨里大学）
