FeatSense -- A Feature-based Registration Algorithm with GPU-accelerated TSDF-Mapping Backend for NVIDIA Jetson Boards

TL;DR

FeatSense is a GPU-accelerated SLAM system that efficiently registers high-resolution LiDAR scans and generates large TSDF maps in real-time on embedded NVIDIA Jetson hardware, enabling advanced mapping capabilities in resource-constrained environments.

Contribution

The paper introduces a novel feature-based SLAM system that achieves real-time LiDAR registration and TSDF map generation on embedded GPU hardware, with significant speed improvements over prior methods.

Findings

Registers up to 128 scan lines at 10Hz on NVIDIA AGX Xavier.

Achieves 100x speedup in TSDF map generation compared to previous work.

Operates effectively in various structured and unstructured environments.

Abstract

This paper presents FeatSense, a feature-based GPU-accelerated SLAM system for high resolution LiDARs, combined with a map generation algorithm for real-time generation of large Truncated Signed Distance Fields (TSDFs) on embedded hardware. FeatSense uses LiDAR point cloud features for odometry estimation and point cloud registration. The registered point clouds are integrated into a global Truncated Signed Distance Field (TSDF) representation. FeatSense is intended to run on embedded systems with integrated GPU-accelerator like NVIDIA Jetson boards. In this paper, we present a real-time capable TSDF-SLAM system specially tailored for close coupled CPU/GPU systems. The implementation is evaluated in various structured and unstructured environments and benchmarked against existing reference datasets. The main contribution of this paper is the ability to register up to 128 scan lines of an Ouster OS1-128 LiDAR at 10Hz on a NVIDIA AGX Xavier while achieving a TSDF map generation speedup by a factor of 100 compared to previous work on the same power budget.