Robotic Monitoring of Alpine Screes: a Dataset from the EU Natura2000 habitat 8110 in the Italian Alps

Data collected between the 19th and the 21rd of July 2022, in Valfurva, 23030 (SO), Italy, within the Stelvio National Park, located inside the Natura 2000 SPA IT2040044. The data acquisition has been conducted by a team composed of both robotic engineers and plant scientists. The platform used to collect the data is the ANYmal C quadrupedal robot. The dataset contains two different sets of data: 1) typical and early warning species data - videos of seven different typical species of the habitat 8110 and one early warning species. 2) monitoring mission data - video of the monitoring mission, robot status and point clouds, pictures and videos taken by the robot during the autonomous surveys. This dataset has a multidisciplinary scope and can be used by researchers in several fields. For instance, point clouds and information about the robot state could be used by robotic engineers to test or validate their own methods as well as benchmark the robot performance. On the other hand, plant videos and images recorded by the robot could be used by botanists to assess the quality of this information as well as the habitat's conditions, or by computer scientists interested in testing their AI algorithms for species detection and classification.本数据集采集于2022年7月19日至21日，采集地点为意大利(SO)23030邮编的瓦尔富尔瓦，地处斯泰尔维奥国家公园范围内，隶属于Natura 2000特别保护区域（SPA）IT2040044。本次数据采集由机器人工程与植物科学领域的联合团队完成，所用数据采集平台为ANYmal C四足机器人。本数据集包含两类核心数据：其一为典型物种与预警物种数据，涵盖栖息地8110的7种典型物种视频与1种预警物种视频；其二为监测任务数据，包含机器人自主巡检期间录制的监测任务视频、机器人状态数据、点云数据，以及机器人拍摄的图像与视频素材。本数据集具备多学科应用价值，可支撑多个研究领域的科研工作。例如，机器人工程师可借助点云数据与机器人状态信息，测试、验证自研算法，或开展机器人性能基准测试；植物学家可通过机器人录制的植物影像与图像，评估相关信息质量与栖息地环境状况；而计算机科学研究者则可利用该数据集，测试用于物种检测与分类的人工智能（AI）算法。