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

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.)

arXiv comment8 pages, 7 figures, accepted by IEEE Robotics and Automation Letters

References in corpus (4)

• Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning
• TAMOLS: Terrain-Aware Motion Optimization for Legged Systems
• Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learning
• Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation

Cited by in corpus (2)

• Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments
• Learning Fast, Tool aware Collision Avoidance for Collaborative Robots