3D Object Recognition and Localization with a Dense LiDAR Scanner

Abstract

Dense scanning is an effective solution for refined geometrical modeling applications. The previous studies in dense environment modeling mostly focused on data acquisition techniques without emphasizing autonomous target recognition and accurate 3D localization. Therefore, they lacked the capability to output semantic information in the scenes. This article aims to make complementation in this aspect. The critical problems we solved are mainly in two aspects: (1) system calibration to ensure detail-fidelity for the 3D objects with fine structures, (2) fast outlier exclusion to improve 3D boxing accuracy. A lightweight fuzzy neural network is proposed to remove most background outliers, which was proven in experiments to be effective for various objects in different situations. With precise and clean data ensured by the two abovementioned techniques, our system can extract target objects from the original point clouds, and more importantly, accurately estimate their center locations and orientations.

Pose optimization for mobile manipulator grasping based on hybrid manipulability

“…For each experiment, the perception system would scan the environment first. As shown in Figure 9(b), the position of the target object can be measured by the robotic perception system according to our previous research (Geng et al , 2022). Based on the target object’s position, the optimal mobile platform pose for grasping can be calculated, as well as the obstacle avoidance trajectory to this pose.…”

Indoor–Outdoor Point Cloud Alignment Using Semantic–Geometric Descriptor

“…To solve the first problem, we used the projected 2D image of the point cloud for 3D segmentation with deep learning neural networks [30]. The details are found in our previous work in [17]. There are inevitable outliers on the 2D segmentation edges, which induce extra points in the background.…”

“…In this paper, we proposed an indoor/outdoor point cloud alignment algorithm with a semantic feature matching method, as shown in Figure 1. The 3D window and door instances are recognized, segmented and localized from the indoor and outdoor point clouds, with a similar approach to our previous work [17]. We designed a semanticgeometric descriptor (SGD) to include both the objects' semantic information and spatial distribution pattern.…”