Since a 3D scanner only captures a scene of a 3D object at a time, a 3D registration for multi-scene is the key issue of 3D modeling. This paper presents a novel and an efficient 3D registration method based on 2D local feature matching. The proposed method transforms the point clouds into 2D bearing angle images and then uses the 2D feature based matching method, SURF, to find matching pixel pairs between two images. The corresponding points of 3D point clouds can be obtained by those pixel pairs. Since the corresponding pairs are sorted by their distance between matching features, only the top half of the corresponding pairs are used to find the optimal rotation matrix by the least squares approximation. In this paper, the optimal rotation matrix is derived by orthogonal Procrustes method (SVD-based approach). Therefore, the 3D model of an object can be reconstructed by aligning those point clouds with the optimal transformation matrix. Experimental results show that the accuracy of the proposed method is close to the ICP, but the computation cost is reduced significantly. The performance is six times faster than the generalized-ICP algorithm. Furthermore, while the ICP requires high alignment similarity of two scenes, the proposed method is robust to a larger difference of viewing angle.

Convolutional neural network (CNN), one of the branches of deep neural networks, has been widely used in image recognition, natural language processing, and other related fields with great success recently. This paper proposes a novel framework with CNN to classify objects in a point cloud captured by LiDAR on urban streets. The proposed BA-CNN algorithm is composed of five steps: (i) removing ground points, (ii) clustering objects, (iii) transforming to bearing angle images, (iv) ROI selection, and (V) identifying objects by CNN. In the first step, ground points are removed by the multi-threshold-based ground detection to reduce the processing time. Then, a flood-fill-based clustering method is used for object segmentation. Those individual point cloud objects are converted to bearing angle (BA) images. Then, a well-trained CNN is used to classify objects with BA images. The main contribution of this paper is proposing an efficient recognition method that uses the information from point clouds only. In contrast, because most 3D object classifiers use the fusion of point clouds and color images, their models are very complicated and take a colossal amount of memory to store the parameters. Since the ground point detection and object clustering process all points along with the scanline-major order and layer-major order, the proposed algorithm performs better in terms of time consumption and memory consumption. In the experiment, three scenes from KITTI dataset are used for training and testing the proposed BA-CNN classifier, and the proposed BA-CNN achieves high classification accuracy.

A hierarchical memetic algorithm (MA) is proposed for the path planning and formation control of swarm robots. The proposed algorithm consists of a global path planner (GPP) and a local motion planner (LMP). The GPP plans a trajectory within the Voronoi diagram (VD) of the free space. An MA with a non-random initial population plans a series of configurations along the path given by the former stage. The MA locally adjusts the robot positions to search for better fitness along the gradient direction of the distance between the swarm robots and the intermediate goals (IGs). Once the optimal configuration is obtained, the best chromosomes are reserved as the initial population for the next generation. Since the proposed MA has a non-random initial population and local searching, it is more efficient and the planned path is faster compared to a traditional genetic algorithm (GA). The simulation results show that the proposed algorithm works well in terms of path smoothness and computation efficiency.

In this paper, a potential-based genetic algorithm is proposed for formation control of robot swarm. The proposed algorithm consists of a global path planner and a motion planner. The global path planning algorithm searches a path, which the center of robot swarm should follow, within a Voronoi diagram of the free space. The motion planning is a genetic algorithm based on artificial potential models. The potential functions are used as a repulsion to keep robots away from obstacles and as an attraction/repulsion to keep robot swarm within a certain distance. With Voronoi diagram and potential models, the algorithm plans safe paths efficiently and the formation of robot swarm is also maintained.

A novel collision avoidance algorithm based on the generalized potential model is proposed to solve the path‐planning problem of hyper‐redundant manipulators in 3‐D workspace. The approach computes repulsive force and torque between manipulator and obstacles by using the workspace information directly. A collision‐free path for a manipulator can then be obtained by locally adjusting the manipulator configuration to search for minimum potential configurations using these forces and torques. The proposed approach is efficient since these potential gradients are analytically tractable. Furthermore, the proposed algorithm is also extended to dual‐arm systems. Simulation results show that the proposed algorithm works well, in terms of computation time and collision avoidance.