ALFA: A Dataset for UAV Fault and Anomaly Detection

The recent growth in the use of Autonomous Aerial Vehicles (AAVs) has increased concerns about the safety of the autonomous vehicles, the people, and the properties around the flight path and onboard the vehicle. Much research is being done on new regulations, more robust systems are designed to address the concerns, and new methods and algorithms are introduced to detect the potential hardware and software issues. This dataset presents several fault types in control surfaces of a fixed-wing Unmanned Aerial Vehicle (UAV) for use in Fault Detection and Isolation (FDI) and Anomaly Detection (AD) research. Currently, the dataset includes processed data for 47 autonomous flights with 23 sudden full engine failure scenarios and 24 scenarios for seven other types of sudden control surface (actuator) faults, with a total of 66 minutes of flight in normal conditions and 13 minutes of post-fault flight time. It additionally includes many hours of raw data of fully-autonomous, autopilot-assisted and manual flights with tens of fault scenarios. The ground truth of the time and type of faults is provided in each scenario to enable the evaluation of new methods using the dataset. We have also provided the helper tools in several programming languages to load and work with the data and to help the evaluation of a detection method using the dataset. A set of metrics is proposed to help to compare different methods using the dataset. Most of the current fault detection methods are evaluated in simulation and as far as we know, this dataset is the only one providing the real flight data with faults in such capacity. We hope it will help advance the state-of-the-art in Anomaly Detection or FDI research for Autonomous Aerial Vehicles and mobile robots to enhance the safety of autonomous and remote flight operations further. <br>Hardware: The platform used for collecting the dataset is a custom modification of the Carbon Z T-28 model plane. The plane has 2 meters of wingspan, a single electric engine in the front, ailerons, flaperons, an elevator, and a rudder. We equipped the aircraft with a Holybro PX4 2.4.6 autopilot, a Pitot Tube, a GPS module, and an Nvidia Jetson TX2 onboard computer. In addition to the receiver, we also equipped it with a radio for communication with the ground station.<br>Software: The Pixhawk autopilot uses a custom version of Ardupilot/ArduPlane firmware to control the plane in both manual and autonomous modes and to create the simulations. The original firmware is modified from ArduPlane v3.9.0beta1 to allow disabling control surfaces during the flight. The onboard computer uses Robot Operating System(ROS) Kinetic Kame on Linux Ubuntu 16.04 (Xenial) to read the flight and state information from the Pixhawk using MAVROS package (the MAVLink node for ROS). <br>More Information and Supplemental Tools<br>Please visit http://theairlab.org/alfa-dataset for more information. It includes the description of each flight sequence, alternative download locations to view and download each individual flight sequence, correct citations to the relevant publications, supplemental code, and an open-source published method using the dataset.<br>The corresponding paper explaining the dataset in more detail is currently under review in the International Journal of Robotics Research (IJRR). The pre-print (arXiv) of the paper can be accessed from our website at http://theairlab.org/alfa-dataset .<br>The supplemental tools for reading and working with the dataset in C++, MATLAB and Python languages can be accessed from https://github.com/castacks/alfa-dataset. The repository also includes a C++ ROS-based tool for evaluating the new methods and all the ROS message type definitions for working directly with the ROS bags. <br><b><br></b>Citing the Work<br>Please refer to our website at http://theairlab.org/alfa-dataset to find the correct citation(s) if you are using this dataset.

近年来，自主飞行器（Autonomous Aerial Vehicles, AAVs）的应用规模持续扩张，由此引发了人们对自主飞行器自身、飞行路径周边人员及机载资产安全的高度关注。当前学界正围绕全新监管规范展开大量研究，同时致力于设计更可靠的系统以应对上述安全隐患，并开发新型方法与算法以排查潜在的软硬件故障。本数据集收录了固定翼无人机（Unmanned Aerial Vehicle, UAV）操纵面的多种故障类型，可供故障检测与隔离（Fault Detection and Isolation, FDI）及异常检测（Anomaly Detection, AD）相关研究使用。
目前，数据集包含47次自主飞行的预处理数据，其中涵盖23种突发全引擎失效场景，以及7类共计24种突发操纵面（执行器）故障场景；数据集包含正常飞行状态下总计66分钟的飞行数据，以及故障发生后13分钟的飞行数据。此外，数据集还包含大量时长超数小时的原始数据，覆盖全自主飞行、自动驾驶辅助飞行及手动飞行场景，内含数十种故障工况。每个场景均标注了故障发生时刻与故障类型的地面真值，便于研究者基于本数据集评估新型检测方法。我们还提供了多种编程语言的辅助工具，用于加载并处理数据，同时辅助完成检测方法的效果评估。此外，我们提出了一套评估指标，以助力不同检测方法间的横向对比。当前绝大多数故障检测方法均在仿真环境中完成验证，据我们所知，本数据集是目前唯一一款提供此类规模真实带故障飞行数据的公开数据集。我们期望本数据集能够推动自主飞行器及移动机器人领域异常检测或故障检测与隔离研究的前沿进展，进一步提升自主与远程飞行作业的安全性。
硬件：本数据集采集所用平台为经过定制改装的Carbon Z T-28型模型飞机。该机型翼展达2米，搭载前部单电动引擎，配套副翼、襟副翼、升降舵及方向舵。我们为该飞行器搭载了Holybro PX4 2.4.6自动驾驶仪、皮托管（Pitot Tube）、GPS模块，以及机载英伟达Jetson TX2计算平台。除接收机外，我们还加装了用于与地面站通信的无线电设备。
软件：Pixhawk自动驾驶仪搭载定制版Ardupilot/ArduPlane固件，可在手动及自主模式下控制飞机，并支持仿真场景构建。该固件基于ArduPlane v3.9.0beta1版本修改而来，支持飞行过程中禁用操纵面。机载计算机搭载运行于Linux Ubuntu 16.04（Xenial）系统的机器人操作系统（Robot Operating System, ROS）Kinetic Kame版本，通过MAVROS包（ROS平台的MAVLink节点）从Pixhawk读取飞行与状态信息。
更多信息与补充工具：请访问http://theairlab.org/alfa-dataset 获取更多详情，该页面包含各飞行序列的说明、各单飞行序列的查看与下载替代链接、相关出版物的正确引用格式、补充代码，以及基于本数据集开发的开源方法。详细阐述本数据集的相关论文目前已提交至《国际机器人研究期刊》（International Journal of Robotics Research, IJRR）审稿，论文的预印本（arXiv）可通过我们的网站http://theairlab.org/alfa-dataset 获取。支持C++、MATLAB及Python语言的数据集读写辅助工具可从https://github.com/castacks/alfa-dataset 下载，该代码仓库还包含一款基于C++ ROS的新型方法评估工具，以及用于直接处理ROS包的所有ROS消息类型定义。
引用该成果：若您使用本数据集，请访问我们的网站http://theairlab.org/alfa-dataset 获取正确的引用格式。