This paper proposes a convolutional neural network model for distinguishing areas occupied by obstacles from a LiDAR image converted from a 3D point cloud. The channels of a LiDAR image used as input consist of the distances to 3D points, the reflectivities of 3D points, and the heights of 3D points from the ground. The proposed model uses a LiDAR image as an input and outputs a result of a segmented LiDAR image. The proposed model adopts refinement modules with skip connections to segment a LiDAR image. The refinement modules with skip connections in the proposed model make it possible to construct a complex structure with a small number of parameters than a convolutional neural network model with a linear structure. Using the proposed model, it is possible to distinguish areas in a LiDAR image occupied by obstacles such as vehicles, pedestrians, and bicyclists. The proposed model can be applied to recognize surrounding obstacles and to search for safe paths.

This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.

거친 바다를 운항하는 선박의 경우 횡 동요로 인해 선박 내의 장비운영 문제 및 탑승객들에게 큰 불편함을 초래한다. 따라서 횡동요 감쇠를 위한 목적으로 빌지 킬, 핀 안정기, 자이로스코프, ART(Anti-Rolling Tank), 타, 플랩 등 다양한 횡 동요 감쇠장치들이 사용되고 있다. 콴다효과는 콴다제트가 곡면의 표면을 따라 흐르며 주위 유동의 순환을 증가시켜 양력을 효과적으로 발생시키는 방법으로 핀의 양력성능을 향상시킬 수 있다. 본 연구에서는 모형시험 및 수치계산을 통해 콴다효과를 적용한 고정식 핀 안정기의 사용가능성을 검토하였다. 그 결과 받음각이 0˚에서, 제트모멘텀을 Cj = 0.25 만큼 공급할 때, 기준 핀의 최대 작동각(26˚)에서 발생되는 양력과 동일하게 발생되는 것으로 나타났다. 즉 받음각을 변화시키는 기존의 핀 안정기와 달리 받음각을 고정하고, 콴다효과를 통한 제트유동제어만으로 선박의 횡 동요를 능동적으로 제어 할 수 있을 것으로 보인다.

Representing an environment as the probabilistic grids is effective to sense outlines of the environment in the mobile robot area. Outlines of an environment can be expressed factually by using the probabilistic grids especially if sonar sensors would be supposed to build an environment map. However, the difficult problem of a sonar such as a specular reflection phenomenon should be overcome to build a grid map through sonar observations. In this paper, the NRF(Neighborhood Recognition Factor) was developed for building a grid map in which the specular reflection effect is minimized. Also the reproduction rate of the gird map built by using NRF was analyzed with respect to a true map. The experiment was conducted in a home environment to verify the proposed technique.