AgriLiRa4D: A Multi-Sensor UAV Dataset for Robust SLAM in Challenging Agricultural Fields

TL;DR

The paper introduces AgriLiRa4D, a multi-modal UAV dataset tailored for robust SLAM in challenging agricultural environments. It provides synchronized LiDAR, 4D Radar, IMU data, and centimeter-level FINS_RTK ground truth across flat, hilly, and terraced farms in boundary and coverage modes, enabling rigorous cross-modality benchmarking. The work benchmarks four state-of-the-art SLAM algorithms (LIO, RIO, RLIO) to reveal modality-specific strengths and weaknesses, highlighting the necessity of multi-sensor fusion in real farming scenarios. By offering comprehensive calibration data, diverse terrain, and detailed evaluation, AgriLiRa4D serves as a valuable resource for advancing autonomous navigation in agricultural UAVs.

Abstract

Multi-sensor Simultaneous Localization and Mapping (SLAM) is essential for Unmanned Aerial Vehicles (UAVs) performing agricultural tasks such as spraying, surveying, and inspection. However, real-world, multi-modal agricultural UAV datasets that enable research on robust operation remain scarce. To address this gap, we present AgriLiRa4D, a multi-modal UAV dataset designed for challenging outdoor agricultural environments. AgriLiRa4D spans three representative farmland types-flat, hilly, and terraced-and includes both boundary and coverage operation modes, resulting in six flight sequence groups. The dataset provides high-accuracy ground-truth trajectories from a Fiber Optic Inertial Navigation System with Real-Time Kinematic capability (FINS_RTK), along with synchronized measurements from a 3D LiDAR, a 4D Radar, and an Inertial Measurement Unit (IMU), accompanied by complete intrinsic and extrinsic calibrations. Leveraging its comprehensive sensor suite and diverse real-world scenarios, AgriLiRa4D supports diverse SLAM and localization studies and enables rigorous robustness evaluation against low-texture crops, repetitive patterns, dynamic vegetation, and other challenges of real agricultural environments. To further demonstrate its utility, we benchmark four state-of-the-art multi-sensor SLAM algorithms across different sensor combinations, highlighting the difficulty of the proposed sequences and the necessity of multi-modal approaches for reliable UAV localization. By filling a critical gap in agricultural SLAM datasets, AgriLiRa4D provides a valuable benchmark for the research community and contributes to advancing autonomous navigation technologies for agricultural UAVs. The dataset can be downloaded from: https://zhan994.github.io/AgriLiRa4D.

Figures (7)

• Figure 1: Sensor configuration on the TopXGun FP300E. The onboard setup integrates a RoboSense Airy LiDAR, a Mindcruise 4D Radar, and a FINS_RTK module for ground-truth reference (top), with the relative sensor positions and coordinate frames illustrated below (bottom).
• Figure 2: Visualization of the FoV configuration for the LiDAR and 4D Radar. The two viewpoints illustrate their respective sensing coverages, with the LiDAR rendered in blue and the 4D Radar in yellow.
• Figure 3: Visualization of the LiDAR and 4D Radar point clouds used to assess the extrinsic calibration. Height-colored LiDAR points and white 4D Radar points are visualized in a common frame following extrinsic alignment, with side and top-down views illustrating the spatial consistency across scenarios.
• Figure 4: Ground-truth reference frames used in this work. The UAV body frame (FRD) and the two frames relative to the take-off point, FLU and ENU, are shown for defining consistent trajectory coordinates.
• Figure 5: Visualization of the three representative farmland scenarios and their corresponding sensor data. Each column corresponds to a distinct terrain type: flat farmland, hilly farmland, and terraced farmland. From top to bottom, subfigures illustrate the real-world operation scenes, boundary (blue) and coverage (red) scanning paths, and the top-view height-colored LiDAR (Faster-LIO fasterlio) and 4D Radar (GaRLIO noh2025garlio) maps, with zoomed-in regions highlighting local geometric details.