Development and use of a convolutional neural network for hierarchical appearance-based localization

This paper reports and evaluates the adaption and re-training of a Convolutional Neural Network (CNN) with the aim of tackling the visual localization of a mobile robot by means of a hierarchical approach. The proposed method addresses the localization problem from the information captured by a catadioptric vision sensor mounted on the mobile robot. A CNN is adapted and evaluated with a twofold purpose. First, to perform a rough localization step (room retrieval) by means of the output layer. Second, to refine this localization in the retrieved room (fine localization step) by means of holistic descriptors obtained from intermediate layers of the same CNN. The robot estimates its position within the selected room/s through a nearest neighbour search by comparing the obtained holistic descriptor with the visual model of the retrieved room/s. Additionally, this method takes advantage of the likelihood information provided by the output layer of the CNN. This likelihood is helpful to determine which rooms should be considered in the fine localization process. This novel hierarchical localization method constitutes an efficient and robust solution, as shown in the experimental section even in presence of severe changes of the lighting conditions.

A Novel coarse-to-fine Localization Algorithm for Automated Vickers Hardness Measurement

Vickers hardness testing is one of the most useful methods to determine the hardness of materials. To calculate the hardness of materials, the key is to measure the diagonal length of the Vickers indentation on the surface accurately. However, since this length is extremely minuscule, there are many challenges to achieve accurate measurement. Especially, when the indentation corner is cracked, the precise position of the corner cannot be obtained by conventional methods. In this paper, we proposed a method of coarse-to-fine localization to accurately locate the indentation corner. The coarse localization process can be used to determine the position and size of the indentation. During fine localization, the linear equations of the indentation edges are calculated by the line fitting method. The capabilities of the proposed method are compared to manual measurement and results are presented.

Affine ICP for Fine Localization of Smart-AGVs in Smart Factories

With the emergence of the concept of Industry 4.0, smart factories have started to be planned in which the production paradigm will change. Automated Guided Vehicles, abbreviated as AGV, that will perform load carrying and similar tasks in smart factories, Smart-AGVs, will try to reach their destinations on their own route instead of predetermined routes like in today’s factories. Moreover, since they will not reach their targets in a single way, they have to dock a target with their fine localization algorithms. In this paper, an affine Iterative Closest Point, abbreviated as ICP, based fine localization method is proposed, and applied on Smart-AGV docking problem in smart factories. ICP is a point set registration method but it is also used for localization applications due to its high precision. Affine ICP is an ICP variant which finds affine transformation between two point sets. In general, the objective function of ICP is constructed based on least square metric. In this study, we use affine ICP with correntropy metric. Correntropy is a similarity measure between two random variables, and affine ICP with correntropy tries to maximize the similarity between two point sets. Affine ICP has never been utilized in fine localization problem. We make an update on affine ICP by means of polar decomposition to reach transformation between two point sets in terms of rotation matrix and translation vector. The performance of the algorithm proposed is validated in simulation and the efficiency of it is demonstrated on MATLAB by comparing with the docking performance of the traditional ICP.

An Improved Hierarchical WLAN Positioning Method Based on Apriori Knowledge

The hierarchical-based structure is recognized as a favorable structure for wireless local area network (WLAN) positioning. It is comprised of two positioning phases: the coarse localization phase and the fine localization phase. In the coarse localization phase, the users’ positions are firstly narrowed down to smaller regions or clusters. Then, a fingerprint matching algorithm is adopted to estimate the users’ positions within the clusters during the fine localization phase. Currently the clustering strategies in the coarse localization phase can be divided into received signal strength (RSS) clustering and 3D clustering. And the commonly seen positioning algorithms in the fine localization phase include k nearest neighbors (kNN), kernel based and compressive sensing-based. This paper proposed an improved WLAN positioning method using the combination: 3D clustering for the coarse localization phase and the compressive sensing-based fine localization. The method have three favorable features: (1) By using the previously estimated positions to define the sub-reference fingerprinting map (RFM) in the first coarse localization phase, the method can adopt the prior information that the users’ positions are continuous during walking to improve positioning accuracy. (2) The compressive sensing theory is adopted in the fine localization phase, where the positioning problem is transformed to a signal reconstruction problem. This again can improve the positioning accuracy. (3) The second coarse localization phase is added to avoid the global fingerprint matching in traditional 3D clustering-based methods when the stuck-in-small-area problem is encountered, thus, sufficiently lowered the maximum positioning latency. The proposed improved hierarchical WLAN positioning method is compared with two traditional methods during the experiments section. The resulting positioning accuracy and positioning latency have shown that the performance of the proposed method has better performance in both aspects.

A Robust Indoor Localization System Integrating Visual Localization Aided by CNN-Based Image Retrieval with Monte Carlo Localization

This paper proposes a novel multi-sensor-based indoor global localization system integrating visual localization aided by CNN-based image retrieval with a probabilistic localization approach. The global localization system consists of three parts: coarse place recognition, fine localization and re-localization from kidnapping. Coarse place recognition exploits a monocular camera to realize the initial localization based on image retrieval, in which off-the-shelf features extracted from a pre-trained Convolutional Neural Network (CNN) are adopted to determine the candidate locations of the robot. In the fine localization, a laser range finder is equipped to estimate the accurate pose of a mobile robot by means of an adaptive Monte Carlo localization, in which the candidate locations obtained by image retrieval are considered as seeds for initial random sampling. Additionally, to address the problem of robot kidnapping, we present a closed-loop localization mechanism to monitor the state of the robot in real time and make adaptive adjustments when the robot is kidnapped. The closed-loop mechanism effectively exploits the correlation of image sequences to realize the re-localization based on Long-Short Term Memory (LSTM) network. Extensive experiments were conducted and the results indicate that the proposed method not only exhibits great improvement on accuracy and speed, but also can recover from localization failures compared to two conventional localization methods.