Real-time Neural Dense Elevation Mapping for Urban Terrain with Uncertainty Estimations

TL;DR

This paper introduces a real-time neural framework for dense urban terrain mapping that integrates uncertainty estimation, enhancing robot navigation and locomotion over complex terrains.

Contribution

It presents a novel neural reconstruction method with uncertainty estimation that operates efficiently in real-time using sparse LiDAR data.

Findings

High-quality dense elevation maps generated in real-time

Robustness to sparse and noisy LiDAR data demonstrated

Improved downstream robot navigation performance

Abstract

Having good knowledge of terrain information is essential for improving the performance of various downstream tasks on complex terrains, especially for the locomotion and navigation of legged robots. We present a novel framework for neural urban terrain reconstruction with uncertainty estimations. It generates dense robot-centric elevation maps online from sparse LiDAR observations. We design a novel pre-processing and point features representation approach that ensures high robustness and computational efficiency when integrating multiple point cloud frames. A Bayesian-GAN model then recovers the detailed terrain structures while simultaneously providing the pixel-wise reconstruction uncertainty. We evaluate the proposed pipeline through extensive simulation and real-world experiments. It demonstrates efficient terrain reconstruction with high quality and real-time performance on a mobile platform, which further benefits the downstream tasks of legged robots. (See https://kin-zhang.github.io/ndem/ for more details.)