Publication Type

Journal Article

Version

acceptedVersion

Publication Date

3-2026

Abstract

Robust and efficient deep LiDAR odometry models are crucial for accurate localization and 3D reconstruction, but typically require extensive and diverse training data to adapt to diverse environments, leading to inefficiencies. To tackle this, we introduce an active training framework designed to selectively extract training data from diverse environments, thereby reducing the training load and enhancing model generalization. Our framework is based on two key strategies: Initial Training Set Selection (ITSS) and Active Incremental Selection (AIS). ITSS begins by breaking down motion sequences from general weather into nodes and edges for detailed trajectory analysis, prioritizing diverse sequences to form a rich initial training dataset for training the base model. For complex sequences that are difficult to analyze, especially under challenging snowy weather conditions, AIS uses scene reconstruction and prediction inconsistency to iteratively select training samples, refining the model to handle a wide range of real-world scenarios. Experiments across datasets and weather conditions validate our approach’s effectiveness. Notably, our method matches the performance of full-dataset training with just 52% of the sequence volume, demonstrating the training efficiency and robustness of our active training paradigm. By optimizing the training process, our approach sets the stage for more agile and reliable LiDAR odometry systems, capable of navigating diverse environmental conditions with greater precision.

Keywords

LiDAR odometry, inefficiencies, initial training set selection, active incremental selection

Discipline

Artificial Intelligence and Robotics | Electrical and Computer Engineering

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

IEEE Transactions on Intelligent Transportation Systems

Volume

27

Issue

8

First Page

10057

Last Page

10068

ISSN

1524-9050

Identifier

10.1109/TITS.2026.3675356

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TITS.2026.3675356

Download

Share

COinS