Can Domain Knowledge Make Deep Models Smarter? Expert-Guided PointPillar (EG-PointPillar) for Enhanced 3D Object Detection

This paper proposes a deep learning-based 3D LiDAR perception framework designed for applications such as autonomous robots and vehicles. To address the high dependency on large-scale annotated data—an inherent limitation of deep learning models—this study introduces a hybrid perception architecture that incorporates expert-driven LiDAR processing techniques into the deep neural network. Traditional 3D LiDAR processing methods typically remove ground planes and apply distance- or density-based clustering for object detection. In this work, such expert knowledge is encoded as feature-level inputs and fused with the deep network, thereby mitigating the data dependency issue of conventional learning-based approaches. Specifically, the proposed method combines two expert algorithms—Patchwork++ for ground segmentation and DBSCAN for clustering—with a PointPillars-based LiDAR detection network. We design four hybrid versions of the network depending on the stage and method of integrating expert features into the feature map of the deep model. Among these, Version 4 incorporates a modified neck structure in PointPillars and introduces a new Cluster 2D Pseudo-Map Branch that utilizes cluster-level pseudo-images generated from Patchwork++ and DBSCAN. This version achieved a +3.88% improvement mean Average Precision (mAP) compared to the baseline PointPillars. The results demonstrate that embedding expert-based perception logic into deep neural architectures can effectively enhance performance and reduce dependency on extensive training datasets, offering a promising direction for robust 3D LiDAR object detection in real-world scenarios.