Adaptive Hyperparameter Tuning for Black-box LiDAR Odometry

TL;DR

This paper introduces an adaptive, data-driven hyperparameter tuning framework for black-box 3D LiDAR odometry algorithms that enhances accuracy across diverse environments without needing internal algorithm details.

Contribution

It presents a novel offline surrogate modeling and online adaptive parameter selection framework for improving black-box LiDAR odometry accuracy.

Findings

Improves odometry accuracy in simulated environments.

Enhances performance on the KITTI dataset.

Does not require internal algorithm information.

Abstract

This study proposes an adaptive data-driven hyperparameter tuning framework for black-box 3D LiDAR odometry algorithms. The proposed framework comprises offline parameter-error function modeling and online adaptive parameter selection. In the offline step, we run the odometry estimation algorithm for tuning with different parameters and environments and evaluate the accuracy of the estimated trajectories to build a surrogate function that predicts the trajectory estimation error for the given parameters and environments. Subsequently, we select the parameter set that is expected to result in good accuracy in the given environment based on trajectory error prediction with the surrogate function. The proposed framework does not require detailed information on the inner working of the algorithm to be tuned, and improves its accuracy by adaptively optimizing the parameter set. We first demonstrate the role of the proposed framework in improving the accuracy of odometry estimation across different environments with a simulation-based toy example. Further, an evaluation on the public dataset KITTI shows that the proposed framework can improve the accuracy of several odometry estimation algorithms in practical situations.