Adaptive Hyperparameter Tuning for Black-box LiDAR Odometry

07/01/2021
by   Kenji Koide, et al.
0

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.

READ FULL TEXT

page 4

page 5

research
10/29/2022

Generalized LOAM: LiDAR Odometry Estimation with Trainable Local Geometric Features

This paper presents a LiDAR odometry estimation framework called General...
research
02/22/2021

Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator

We present unsupervised parameter learning in a Gaussian variational inf...
research
02/21/2019

Bayes Optimal Early Stopping Policies for Black-Box Optimization

We derive an optimal policy for adaptively restarting a randomized algor...
research
07/13/2022

Automatic Parameter Adaptation for Quadrotor Trajectory Planning

Online trajectory planners enable quadrotors to safely and smoothly navi...
research
05/21/2016

Adaptive Algorithm and Platform Selection for Visual Detection and Tracking

Computer vision algorithms are known to be extremely sensitive to the en...
research
02/01/2022

Globally Consistent and Tightly Coupled 3D LiDAR Inertial Mapping

This paper presents a real-time 3D mapping framework based on global mat...
research
10/01/2019

Adaptive Continuous Visual Odometry from RGB-D Images

In this paper, we extend the recently developed continuous visual odomet...

Please sign up or login with your details

Forgot password? Click here to reset