综述自动驾驶数据闭环
-
自动驾驶的数据驱动模型; -
云计算平台的基建和大数据处理技术; -
训练数据标注工具; -
大型模型训练平台; -
模型测试和检验; -
相关的机器学习技术。
1 自动驾驶的数据驱动模型
-
感知:图像/激光雷达/毫米波雷达 -
地图+定位 -
预测(感知-预测) -
规划决策(预测-规划) -
控制(规划-控制) -
传感器预处理 -
模拟仿真
2 云计算平台的基建和大数据处理技术
-
使用 AWS Outposts (运行本地 AWS 基础设施和服务)从车队中提取数据以进行本地数据处理。 -
使用 AWS IoT Core (将 IoT 设备连接到 AWS 云,而无需配置或管理服务器)和 Amazon Kinesis Data Firehose (将流数据加载到数据湖、数据存储和分析服务中)实时提取车辆T-box数据,该服务可以捕获和转换流数据并将其传输给 Amazon S3(AWS全球数据存储服务)、Amazon Redshift(用标准 SQL 在数据仓库、运营数据库和数据湖中查询和合并 EB 级结构化和半结构化数据)、Amazon Elasticsearch Service(部署、保护和运行 Elasticsearch,是一种在 Apache Lucene 上构建的开源 RESTful 分布式搜索和分析引擎)、通用 HTTP 终端节点和服务提供商(如 Datadog、New Relic、MongoDB 和 Splunk),这里Amazon Kinesis 提供的功能Data Analytics, 可通过 SQL 或 Apache Flink (开源的统一流处理和批处理框架,其核心是分布流处理数据引擎)的实时处理数据流。 -
删除和转换低质量数据。 -
使用 Apache Airflow (开源工作流管理工具)安排提取、转换和加载 (ETL) 作业。 -
基于 GPS 位置和时间戳,附加天气条件来丰富数据。 -
使用 ASAM OpenSCENARIO (一种驾驶和交通模拟器的动态内容文件格式)提取元数据,并存储在Amazon DynamoDB (NoSQL 数据库服务)和 Amazon Elasticsearch Service中。 -
在 Amazon Neptune (图形数据库服务,用于构建查询以有效地导航高度互连数据集)存储数据序列,并且使用 AWS Glue Data Catalog(管理ETL服务的AWS Glue提供数据目录功能)对数据建立目录。 -
处理驾驶数据并深度验证信号。 -
使用 Amazon SageMaker Ground Truth (构建训练数据集的标记工具用于机器学习,包括 3D 点云、视频、图像和文本)执行自动数据标记,而Amazon SageMaker 整合ML功能集,提供基于 Web 的统一可视化界面,帮助数据科学家和开发人员快速准备、构建、训练和部署高质量的机器学习 (ML) 模型。 -
AWS AppSync 通过处理与 AWS DynamoDB、AWS Lambda(事件驱动、自动管理代码运行资源的计算服务平台) 等数据源之间连接任务来简化数据查询/操作GraphQL API 的开发,在此使用是为特定场景提供搜索功能。
3 训练数据标注工具
-
“Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision“
-
“Auto-Annotation of 3D Objects via ImageNet“
-
“Offboard 3D Object Detection from Point Cloud Sequences“
4 大型模型训练平台
-
DataParallel -
distributedataparallel
5 模型测试和检验
-
Carla
-
AirSim
-
LGSVL
-
“LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World“
-
”S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling“
-
”SceneGen: Learning to Generate Realistic Traffic Scenes“
-
”TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors“
-
”GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving“
-
“AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles“
-
”SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving“
6 相关的机器学习技术
-
主动学习 -
OOD检测和Corner Case检测 -
数据增强/对抗学习 -
迁移学习/域自适应 -
自动机器学习(AutoML )/元学习(学习如何学习) -
半监督学习 -
自监督学习 -
少样本/ 零样本学习 -
持续学习/开放世界
-
“Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector“
-
“Consistency-based Active Learning for Object Detection“
-
“Towards Corner Case Detection for Autonomous Driving“
-
“Out-of-Distribution Detection for Automotive Perception“
-
“Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches“
-
“AutoAugment: Learning Augmentation Strategies from Data“
-
“Classmix: Segmentation-based Data Augmentation For Semi-supervised Learning“
-
“Data Augmentation for Object Detection via Differentiable Neural Rendering“
-
“LiDAR-Aug: A General Rendering-based Augmentation Framework for 3D Object Detection“
-
“Adaptive Object Detection with Dual Multi-Label Prediction“
-
“Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation“
-
“Multi-Target Domain Adaptation via Unsupervised Domain Classification for Weather Invariant Object Detection“
-
“Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation“
-
“SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection“
-
“LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation“
-
1)用于配置评估(对于评估者); -
2)用于配置生成(用于优化器); -
3) 用于动态配置的自适应。
-
“Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks” -
“Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results“ -
“Self-training with Noisy Student improves ImageNet classification“
-
“Unbiased Teacher for Semi-Supervised Object Detection“
-
“Pseudoseg: Designing Pseudo Labels For Semantic Segmentation“
-
“Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learning“
-
“ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection“
-
“3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection“
-
“SimCLR-A Simple framework for contrastive learning of visual representations“ -
“Momentum Contrast for Unsupervised Visual Representation Learning“ -
“Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning“ -
“Deep Clustering for Unsupervised Learning of Visual Features“ -
“Unsupervised Learning of Visual Features by Contrasting Cluster Assignments“
-
“DetCo: Unsupervised Contrastive Learning for Object Detection“
-
“PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding“
-
“MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation“
-
“Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels“
-
“Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection“
-
“Zero-Shot Semantic Segmentation“
-
“Zero-Shot Learning on 3D Point Cloud Objects and Beyond“
-
“Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild“
-
“Self-Supervised Few-Shot Learning on Point Clouds“
-
“Few-shot 3D Point Cloud Semantic Segmentation“
-
“Lifelong Object Detection“
-
“Incremental Few-Shot Object Detection“
-
“Towards Open World Object Detection“
-
"OpenGAN: Open-Set Recognition via Open Data Generation"
-
“Large-Scale Long-Tailed Recognition in an Open World“
-
数据的模式(摄像头/激光雷达/雷达,无/导航/高清地图,姿态定位精度,时间同步标记); -
数据驱动模型(模块/端到端); -
模型的架构(AutoML); -
模型训练的策略(数据选择)。