No abstract

Environment perception is essential for autonomous mobile robots in human-robot coexisting outdoor environments. One of the important tasks for such intelligent robots is to autonomously detect the traversable region in an unstructured 3D real world. The main drawback of most existing methods is that of high computational complexity. Hence, this paper proposes a binocular vision-based, real-time solution for detecting traversable region in the outdoors. In the proposed method, an appearance model based on multivariate Gaussian is quickly constructed from a sample region in the left image adaptively determined by the vanishing point and dominant borders. Then, a fast, self-supervised segmentation scheme is proposed to classify the traversable and non-traversable regions. The proposed method is evaluated on public datasets as well as a real mobile robot. Implementation on the mobile robot has shown its ability in the real-time navigation applications.

Abstract:The ancient Great Wall of China has long suffered from damage due to natural factors and human activities. A small low-cost unmanned helicopter system with a laser scanner and a digital camera is developed to efficiently visualize the status of the huge Great Wall area. The goal of the system is to achieve 3D digitisation of the large-scale Great Wall using a combination of fly-hover-scan and flying-scan modes. However, pose uncertainties of the unmanned helicopter could cause mismatching among point clouds acquired by each hovering-scan. This problem would become more severe as the target area becomes larger and more unstructured. Therefore, a hierarchical optimization framework is proposed in this paper to achieve 3D digitisation of the large-scale unstructured Great Wall with unpredictable pose uncertainties of the unmanned helicopter. In this framework, different optimization methodologies are proposed for the fly-hover-scan and flying-scan modes, respectively, because different scan modes would result in different features of point clouds. Moreover, a user-friendly interface based on WebGL has been developed for 3D model visualization and comparison. Experimental results demonstrate the feasibility of the proposed framework for 3D digitisation of the Great Wall segments.

No abstract

Cloud robotics is the application of cloud computing concepts to robotic systems. It utilizes modern cloud computing infrastructure to distribute computing resources and datasets. Cloud‐based real‐time outsourcing localization architecture is proposed in this paper to allow a ground mobile robot to identify its location relative to a road network map and reference images in the cloud. An update of the road network map is executed in the cloud, as is the extraction of the robot‐terrain inclination (RTI) model as well as reference image matching. A particle filter with a network‐delay‐compensation localization algorithm is executed on the mobile robot based on the local RTI model and the recognized location both of which are sent from the cloud. The proposed methods are tested in different challenging outdoor scenarios with a ground mobile robot equipped with minimal onboard hardware, where the longest trajectory was 13.1 km. Experimental results show that this method could be applicable to large‐scale outdoor environments for autonomous robots in real time.