FRUC multiple sensor forest dataset including absolute, map-referenced localization

<strong>FRUC Datasets (Forest environment dataset)</strong> This dataset was collected as part of the work conducted by the Forestry Robotics @ University of Coimbra team (https://www.youtube.com/@forestryroboticsuc; part of the Institute of Systems and Robotics, https://www.isr.uc.pt/) within the scope of the Safety, Exploration and Maintenance of Forests with Ecological Robotics (SEMFIRE, ref. CENTRO-01-0247-FEDER-03269; http://semfire.ingeniarius.pt/) and the Semi-Autonomous Robotic System for Forest Cleaning and Fire Prevention (SafeForest, CENTRO-01-0247-FEDER-045931) research projects. Its purpose is to allow researchers in forestry robotics to have an in-depth analysis of a florests environment; obtain an a priori map for robot operations (e.g. path plannning, landscaping, etc…) and to train segmentation algorithms; The dataset in question includes data from multiple sensors and absolute, map-referenced localization which can be used to register the sensor data to a fixed coordinate system. It was collected at the Choupal National Woods, Coimbra, Portugal (40^◦13′13.3′′N;8^◦26′38.1′′W). The dataset was collected during a partly clouded day in a forest environment by performing <strong>two circular loop</strong> laps amounting to a total distance of approximately <strong>800m,</strong> with a total duration of <strong>14 minutes and 22 seconds</strong>. The scenario is rich in features relevant to forestry robotics applications, including trees, bushes, tree trunks, etc. To better handle the multimodal nature of the acquired data, the dataset is bundled into rosbags, a file format used by the ROS (Robot Operating System) to record and play back data. <strong>More specifically, the datasets include:</strong> <strong>RGB Images</strong> from an Intel Realsense D435i Aligned <strong>Depth Images</strong> from an Intel Realsense D435i Left and Right Mono Images from a Mynt Eye s1030 <strong>Point Clouds</strong> from a Livox Mid-70 LiDAR Unfiltered <strong>acceleration, gyroscopic and magnetic</strong> data from a Xsens MTi IMU Unfiltered <strong>acceleration, gyroscopic </strong>data from an Intel Realsense D435i <strong>GNSS Fix data</strong> from a Xiaomi Mi Mix 3 device <strong>Description of files:</strong> The dataset is contain in <strong>choupal.bag</strong>. The <strong>rosbag_info.txt </strong>contains the information of each rosbag; The <strong>sensor_box.urdf </strong>contains all the required transforms; The <strong>sensor_box.stl</strong> contains the 3D model of the apparatus; The <strong>choupal.launch </strong>publishes the sensor transforms and plays the dataset; The <strong>localization.bag</strong> contains the final graph of poses extracted with Cartographer republished as nav_msgs/odom at 4.98Hz. The <strong>localization_15Hz.bag</strong> contains a map-referenced localization extracted with Cartographer at a higher frequency, but the poses are interpolated. If you don't require a high frame rate, please use the <strong>localization.bag</strong> instead. <strong>Usage:</strong> Extract the <em>fruc_dataset_choupal_launch.zip </em>into a catkin workspace Install the necessary dependencies of the package: <pre><code class="language-bash">cd [/path/to/catkin_ws]</code></pre> <pre><code class="language-bash">rosdep install --from-paths src --ignore-src -y -r</code></pre> Copy the <strong>rosbags </strong>into the <em>fruc_dataset_choupal_launch/rosbag/</em> Edit the <em>fruc_dataset_choupal_launch/launch/choupal.launch </em>file to your use case: Change the <em>file_path </em>argument if the rosbags are not in the default location; Set <em>localization_file</em> to <em> </em>the path of the desired localization bag, leave it empty to run the dataset without localization. Compile the package and source the environment: <pre><code class="language-bash">catkin_make [/your_catkin_workspace/]</code></pre> <pre><code class="language-bash">source [/your_catkin_workspace/devel/setup.bash]</code></pre> Launch the files: <pre><code class="language-bash">roslaunch fruc_dataset_choupal_launch choupal.launch</code></pre>**FRUC数据集（森林环境数据集）** 本数据集由科英布拉大学林业机器人团队（隶属于系统与机器人研究所，https://www.isr.uc.pt/，相关YouTube频道：https://www.youtube.com/@forestryroboticsuc），在"基于生态机器人的森林安全、勘探与维护"（SEMFIRE，项目编号：CENTRO-01-0247-FEDER-03269；项目官网：http://semfire.ingeniarius.pt/）以及"用于森林清理与森林防火的半自主机器人系统"（SafeForest，项目编号：CENTRO-01-0247-FEDER-045931）两项研究课题框架下采集完成。其研发目的在于助力林业机器人领域研究者深入剖析森林环境；为机器人作业（如路径规划、景观美化等）获取先验地图，以及用于训练分割算法。本数据集包含多传感器数据以及绝对地图参考定位信息，可用于将传感器数据配准至固定坐标系中。 数据集采集于葡萄牙科英布拉的舒帕尔国家森林（40°13′13.3″N；8°26′38.1″W）。本次数据采集于局部多云的天气下，在森林环境中完成了**两圈环形巡测**，总行进距离约**800米**，总时长**14分22秒**。该场景包含丰富的林业机器人应用相关特征，如树木、灌丛、树干等。 为更好地处理采集得到的多模态数据，本数据集以rosbag格式打包存储——该格式是ROS（机器人操作系统，Robot Operating System）用于记录与回放机器人数据的专用文件格式。具体而言，本数据集包含以下内容： - 英特尔Realsense D435i采集的RGB图像与对齐深度图像 - Mynt Eye s1030采集的左右单目图像 - Livox Mid-70激光雷达（LiDAR）采集的点云数据 - Xsens MTi惯性测量单元（IMU，Inertial Measurement Unit）采集的未滤波加速度、陀螺与地磁数据 - 英特尔Realsense D435i采集的未滤波加速度与陀螺数据 - 小米Mi Mix 3设备采集的GNSS定位Fix数据 **文件说明** 数据集主体存储于`choupal.bag`文件中。`rosbag_info.txt`文件包含各rosbag的详细信息；`sensor_box.urdf`文件包含所有必要的坐标变换关系；`sensor_box.stl`文件包含整套采集设备的三维模型；`choupal.launch`文件用于发布传感器坐标变换并回放数据集；`localization.bag`文件包含由Cartographer算法提取的最终位姿图，并以`nav_msgs/odom`格式以4.98Hz的频率重发布；`localization_15Hz.bag`文件包含由Cartographer算法提取的地图参考定位数据，频率更高，但位姿数据经过插值处理。若无需高帧率，请优先使用`localization.bag`。 **使用方法** 1. 将`fruc_dataset_choupal_launch.zip`解压至Catkin工作空间，并安装该软件包所需的依赖项： bash cd [/path/to/catkin_ws] rosdep install --from-paths src --ignore-src -y -r 2. 将所有rosbag文件复制至`fruc_dataset_choupal_launch/rosbag/`目录下。 3. 根据实际需求编辑`fruc_dataset_choupal_launch/launch/choupal.launch`文件：若rosbag文件未放置于默认路径，请修改`file_path`参数；若需使用定位功能，请将`localization_file`设置为目标定位bag文件的路径，留空则不启用定位功能运行数据集。 4. 编译该软件包并配置环境变量： bash catkin_make [/your_catkin_workspace/] source [/your_catkin_workspace/devel/setup.bash] 5. 启动文件： bash roslaunch fruc_dataset_choupal_launch choupal.launch