Fig 1: Overview of the proposed method.
In this paper, we present the Circular Accessible Depth (CAD), a robust traversability representation for an unmanned ground vehicle (UGV) to learn traversability in various scenarios containing irregular obstacles. To predict CAD, we propose a neural network, namely CADNet, with an attention-based multi-frame point cloud fusion module, Stability-Attention Module (SAM), to encode the spatial features from point clouds captured by LiDAR. CAD is designed based on the polar coordinate system and focuses on predicting the border of traversable area. Since it encodes the spatial information of the surrounding environment, which enables a semi-supervised learning for the CADNet, and thus desirably avoids annotating a large amount of data. Extensive experiments demonstrate that CAD outperforms baselines in terms of robustness and precision. We also implement our method on a real UGV and show that it performs well in real-world scenarios.
We propose Circular Accessible Depth, a robust traversability representation for UGV navigation. We present the CADNet, trained in a semi-supervised manner, to extract the features with regard to the spatial distribution of point clouds and predict CAD. In the CADNet, we design a Stability-Attention Module to tackle the interference of dynamic objects in the fusion of point clouds from multiple frames.