IEEE Transactions on Robotics · 2023 · 19 citations · 35 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningAutonomous NavigationDepth EstimationEnvironment RepresentationObstacle DetectionPoint Cloud ProcessingRobot NavigationAccessible Spatial InformationPoint Cloud Representation LearningPolar Coordinate SystemsPolar Coordinate TransformationsSpatial Information ExtractionSpatial Information ModelingTraversability AnalysisUnmanned Ground Vehicles
In this article, 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 multiframe 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 semisupervised 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.
35
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Yin Zhou, Oncel Tuzel · 2018 · 4.6K citations
Multi-view 3D Object Detection Network for Autonomous Driving
Xiaozhi Chen, Huimin Ma, Ji Wan et al. · 2017 · 3.4K citations
SECOND: Sparsely Embedded Convolutional Detection
Yan Yan, Yuxing Mao, Bo Li · Sensors · 2018 · 3.2K citations · Full text
Generative Image Inpainting with Contextual Attention
Jiahui Yu, Zhe Lin, Xiaohui Shen et al. · 2018 · 2.5K citations