Fast Traversability Estimation for Wild Visual Navigation

Frey, Jonas; Mattamala, Matias; Chebrolu, Nived; Cadena, Cesar; Fallon, Maurice; Hutter, Marco

doi:10.15607/rss.2023.xix.054

Cited by 27 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…during traversing) and obstacles for downstream tasks such as motion planning [6], [7], traversability assessment [8], [9], and trajectory planning [10], [11]. However, these conventional approaches are based on the assumption that the world is rigid, i.e., the robot will step on the terrain or collide with the obstacles rather than moving or deforming them.…”

Section: Camera Image Raw Pointcloud Filtered Pointcloudmentioning

confidence: 99%

Seeing Through the Grass: Semantic Pointcloud Filter for Support Surface Learning

Li,

Yang,

Frey

et al. 2023

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Mobile ground robots require perceiving and understanding their surrounding support surface to move around autonomously and safely. The support surface is commonly estimated based on exteroceptive depth measurements, e.g., from LiDARs. However, the measured depth fails to align with the true support surface in the presence of high grass or other penetrable vegetation. In this work, we present the semantic pointcloud filter (SPF), a convolutional neural network (CNN) that learns to adjust LiDAR measurements to align with the underlying support surface. The SPF is trained in a semi-self-supervised manner and takes as an input a LiDAR pointcloud and RGB image. The network predicts a binary segmentation mask that identifies the specific points requiring adjustment, along with estimating their corresponding depth values. To train the segmentation task, 464 distinct images are manually labeled into rigid and non-rigid terrain. The depth estimation task is trained in a self-supervised manner by utilizing the future footholds of the robot to estimate the support surface based on a Gaussian process. Our method can correctly adjust the support surface prior to interacting with the terrain and is extensively tested on the quadruped robot ANYmal. We show the qualitative benefits of SPF in natural environments for elevation mapping and traversability estimation compared to using raw sensor measurements and existing smoothing methods. Quantitative analysis is performed in various natural environments, and an improvement by 48% RMSE is achieved within a meadow terrain.

show abstract

Section: Camera Image Raw Pointcloud Filtered Pointcloudmentioning

confidence: 99%

Seeing Through the Grass: Semantic Pointcloud Filter for Support Surface Learning

Li,

Yang,

Frey

et al. 2023

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

ForestTrav: 3D LiDAR-Only Forest Traversability Estimation for Autonomous Ground Vehicles

Ruetz,

Lawrance,

Hernández

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Autonomous navigation in unstructured vegetated environments remains an open challenge.To successfully operate in these settings, autonomous ground vehicles (AGVs) must assess the environment and determine which vegetation is pliable enough to safely traverse. In this paper, we propose ForestTrav (Forest Traversability) : a novel lidar-only (geometric), online traversability estimation (TE) method that can accurately generate a per-voxel traversability estimate for densely vegetated environments, shown for dense subtropical forests. The method leverages a salient, probabilistic 3D voxel representation, continuously fusing in lidar measurements to maintain multiple, per-voxel ray statistics, in combination with the structural context and compactness of sparse convolutional neural networks (SCNNs) to perform accurate TE in densely vegetated environments. The proposed method is real-time capable and is shown to outperform state-of-the-art volumetric and 2.5D TE methods by a significant margin (0.62 vs. 0.41 Matthews correlation coefficient (MCC) score at 0.1 m voxel resolution) in challenging scenes and to generalize to unseen environments. ForestTrav demonstrates that lidar-only (geometric) methods can provide accurate, online TE in complex, densely-vegetated environments. This capability has not been previously demonstrated in the literature in such complex environments. Further, we analyze the response of the TE methods to the temporal and spatial evolution of the probabilistic map as a function of information accumulated over time during scene exploration. It shows that our method performs well even with limited information in the early stages of exploration, and this provides an additional tool to assess the expected performance during deployment. Finally, to train and assess TE methods in highly-vegetated environments, we collected and labeled a novel, real-world data set and provide it to the community as an open-source resource.

show abstract