This study aims to develop a practical LiDAR–inertial Simultaneous Localization and Mapping (SLAM) system for industrial mobile robots operating in dynamic, repetitive and resource-constrained warehouse environments by formulating dynamic-object handling as a continuous uncertainty-propagation process spanning front-end perception, state estimation and graph optimization.
Abstract
This study aims to develop a practical LiDAR–inertial Simultaneous Localization and Mapping (SLAM) system for industrial mobile robots operating in dynamic, repetitive and resource-constrained warehouse environments. Rather than treating dynamic object handling as isolated point removal, the proposed system formulates it as dynamic uncertainty propagation across perception, state estimation and back-end optimization.
The method integrates a point-cloud dynamic mask for feature-level hard rejection, temporal 3D-Intersection over Union (IoU) covariance modulation for uncertainty-aware LiDAR updates and a PSA-ICP two-stage loop-registration module within multifactor graph optimization. Dynamic information is first used to reject high-risk point-cloud features, then encoded in the Iterated Error‑state Kalman Filter (IESKF) measurement covariance and finally propagated to graph optimization through covariance-aware odometry factors and dynamically filtered loop-registration inputs.
With the dynamic threshold set to t = 0.5, the proposed dynamic-object evaluation achieves an F1 score of 0.886. On hall_02, street_04 and street_08, the proposed method obtains absolute pose error root‑mean‑square error (RMSE) values of 0.145 , 0.376 and 0.163 m, respectively, reducing RMSE by 8.23%, 7.16% and 7.39% compared with the strongest dynamic baseline on each sequence. Additional self-collected warehouse experiments and Jetson Nano profiling further demonstrate improved map consistency and embedded feasibility.
Unlike conventional dynamic SLAM approaches that treat dynamic-object removal as an isolated preprocessing operation, the proposed method formulates dynamic-object handling as a continuous uncertainty-propagation process spanning front-end perception, state estimation and graph optimization.
Experiments on KITTI, M2DGR, and custom UAV datasets show that the proposed framework improves global trajectory accuracy and mapping consistency in the tested dynamic-interference scenarios, and results indicate that aggressive dynamic feature removal may weaken short-term constraints in loop-free sequences.
Meng Tian, Shu-Fan He, Zheng-Cheng Dong et al.· Measurement science and tech...· 0 citations
This work proposes a novel method for constructing point-wise observation confidence by integrating geometric consistency, free-space reasoning, and temporal stability, which retains the observability of geometric constraints while effectively mitigating the impact of dynamic interference, thereby enhancing mapping acc...
Yu-Feng Yang, Chen-Yang Jing· International Conference on...· 0 citations
In robotic operation scenarios, LiDAR-Inertial SLAM systems based on factor graph optimization often lack sufficient adaptability. Common issues include backend optimization latency leading to odometry state divergence, and performance degradation in the scan-to-map matching mechanism due to local map bloat when operat...
Baocun Wang, Quan-Yu Wu, Xiao-Dong Lu et al.· International Journal of Com...· 0 citations
With the rapid development of industrial automation and intelligent logistics, the autonomous navigation and localization accuracy of automated guided vehicles (AGVs), as core equipment in automated transport systems, directly affects logistics efficiency and operational safety. To address insufficient AGV localization...
Overall, the results demonstrate a tunnel-specific, graph-efficient backend that improves native-output global trajectory agreement, substantially reduces graph redundancy, and maintains competitive density-controlled trajectory consistency on the evaluated underground route.
The synthesis indicates that LiDAR remains a strong perceptual backbone for UAV autonomy, but that state-of-the-art systems increasingly combine it with inertial, visual, radar, and learning-based components rather than relying on LiDAR in isolation.
Svitlana Pavlova, V. Chepizhenko, Fu-Zhong Li et al.· Applied Sciences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.