农用机器人多模态数据集，助力精准定位与导航算法研究
The Rosario Dataset v2: Multimodal Dataset for Agricultural Robotics
- 融合多种传感器采集农田环境数据，含红外、可见光相机及高精度定位信息
- 覆盖光照变化、地形粗糙等挑战场景，支持长时序、高自由度轨迹建图
- 适用于农业机器人SLAM算法测试，适合相关领域研究人员使用
我们提出一个在大豆田中采集的多模态数据集，包含超过两小时的传感器数据，涵盖双目红外相机、彩色相机、加速度计、陀螺仪、磁力计、GNSS（单点定位、实时动态和后处理动态）以及轮式里程计。该数据集捕捉了农业环境中机器人面临的典型挑战，包括自然光照变化、运动模糊、崎岖地形以及长时间、感知混淆的序列。通过解决这些复杂性，数据集旨在支持农业机器人在定位、建图、感知和导航方面的先进算法开发与基准测试。平台与数据采集系统设计满足多模态SLAM系统评估的关键需求，包括传感器硬件同步、6-DOF真值及长轨迹回环。我们在数据集上运行了多种前沿多模态SLAM方法，揭示了现有算法在农业场景下的应用局限。数据集及相关工具已发布于 https://cifasis.github.io/rosariov2/。
原文摘要 · Abstract (English)
We present a multi-modal dataset collected in a soybean crop field, comprising over two hours of recorded data from sensors such as stereo infrared camera, color camera, accelerometer, gyroscope, magnetometer, GNSS (Single Point Positioning, Real-Time Kinematic and Post-Processed Kinematic), and wheel odometry. This dataset captures key challenges inherent to robotics in agricultural environments, including variations in natural lighting, motion blur, rough terrain, and long, perceptually aliased sequences. By addressing these complexities, the dataset aims to support the development and benchmarking of advanced algorithms for localization, mapping, perception, and navigation in agricultural robotics. The platform and data collection system is designed to meet the key requirements for evaluating multi-modal SLAM systems, including hardware synchronization of sensors, 6-DOF ground truth and loops on long trajectories. We run multimodal state-of-the art SLAM methods on the dataset, showcasing the existing limitations in their application on agricultural settings. The dataset and utilities to work with it are released on https://cifasis.github.io/rosariov2/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。