A Robust LiDAR-Inertial Multi Constraint-Based Localization for Agricultural Environments
Narayan Longani, Gon-Woo Kim
AI summary
Problem
Autonomous agricultural robots struggle with accurate localization in large-scale, unstructured environments due to uneven terrain, sparse LiDAR features, and time-varying sensor noise causing cumulative drift.
Approach
The method fuses a Sage-Husa adaptive Kalman filter for real-time IMU odometry with a factor graph optimizer that leverages planar features and loop closures, exchanging only pose-level constraints to avoid redundancy.
Key results
- Hybrid tightly/loosely coupled LiDAR-Inertial framework tailored for unstructured terrain
- Sage-Husa adaptive Kalman filter dynamically compensates for time-varying IMU noise
- Planar features demonstrated to significantly outperform edge features in agricultural scans
- Robust performance validated on self-collected agricultural and GRACO/KITTI datasets
Why it matters
Enables reliable, GPS-denied autonomous navigation for farming machinery, directly advancing precision agriculture and field robotics.
Abstract
Accurate state estimation is essential for an autonomous agricultural robot’s reliable operations. The effectiveness of state estimation is influenced by a number of factors, such as sensor- fusion algorithms, the environment, and sensor quality. When the robot traverses in large-scale scenarios, the distance travelled and high-speed mobility produce a drift in the estimation process and should be carefully considered. Moreover, the time-varying noise in sensors affects odometry accuracy further; this is especially noticeable in long travel. This research work is related to the multi-constraints- based state estimation in large unstructured environments with uneven terrain, with a focus on agricultural applications. Using LiDAR-IMU based fusion, our goal is to provide a reliable & accurate localization solution in complex environments like agricultural fields. Furthermore, the agricultural environments become more challenging due to the uneven terrain and lack of features. Our research proposes a hybrid framework which combines factor graph-based optimization & adaptive Kalman filtering to address these challenges in complex environments. Furthermore, performance evaluation is conducted on self-collected datasets from agricultural environments as well as on open-access datasets such as GRACO & KITTI.