Hierarchical Pose Estimation and Mapping with Multi-Scale Neural Feature Fields

TL;DR

This paper introduces a hierarchical neural field-based approach for large-scale pose estimation and mapping in robotics, effectively handling unknown sensor poses and sequential LiDAR data to improve accuracy and stability.

Contribution

It proposes a novel hierarchical pose estimation method with a neural network architecture tailored for large-scale implicit maps in SLAM.

Findings

Achieves accurate pose estimation on KITTI and MaiCity datasets.

Outperforms baseline methods in mapping with unknown poses.

Attains state-of-the-art localization accuracy.

Abstract

Robotic applications require a comprehensive understanding of the scene. In recent years, neural fields-based approaches that parameterize the entire environment have become popular. These approaches are promising due to their continuous nature and their ability to learn scene priors. However, the use of neural fields in robotics becomes challenging when dealing with unknown sensor poses and sequential measurements. This paper focuses on the problem of sensor pose estimation for large-scale neural implicit SLAM. We investigate implicit mapping from a probabilistic perspective and propose hierarchical pose estimation with a corresponding neural network architecture. Our method is well-suited for large-scale implicit map representations. The proposed approach operates on consecutive outdoor LiDAR scans and achieves accurate pose estimation, while maintaining stable mapping quality for both short and long trajectories. We built our method on a structured and sparse implicit representation suitable for large-scale reconstruction and evaluated it using the KITTI and MaiCity datasets. Our approach outperforms the baseline in terms of mapping with unknown poses and achieves state-of-the-art localization accuracy.