Convolutional Neural Networks Based Active SLAM and Exploration

Mobile robots are high-performance robots that are used to perform a specific function in environments such as land, air and water, with free movement options and are equipped with many sensors for different processing capabilities. Today, it is used in many tasks such as object detection, tracking and mapping. Mobile robots used in mapping implementations are usually guided by user inputs. However, in some cases, this guidance is autonomously implemented through exploration algorithms that are examined under the active Simultaneous Localization and Mapping (SLAM) keyword. These algorithms are usually based on Laser Imaging Detection and Ranging (LIDAR) sensor. Since this sensor has a bulky structure and occupancy grid maps require heavy computing time, it is needed to develop new kinds of algorithms. In this study, we propose a novel Convolutional Neural Network (CNN) based algorithm that can create a map of an environment with a mobile robot that is independent of user inputs and move autonomously. For the first stage, the CNN structure is trained using the data set consisting of the environment image and the wheel angles related to these images so that the CNN model learns how to guide the robot. For the second stage, the robot is navigated autonomously through the trained network in an environment which is different from the first one, and the map of the environment is acquired simultaneously. Training and testing processes have been realized on a real-time implementation and the advantages of the developed method have been verified.

Link: https://doi.org/10.31590/ejosat.862953

Video Link: https://youtu.be/7oeuW-3OoEk

LSTM and Filter Based Comparison Analysis for Indoor Global Localization in UAVs

Deep learning (DL) based localization and Simultaneous Localization and Mapping (SLAM) has recently gained considerable attention demonstrating remarkable results. Instead of constructing hand-crafted algorithms through geometric theories, DL based solutions provide a data-driven solution to the problem. Taking advantage of large amounts of training data and computing capacity, these approaches are increasingly developing into a new field that offers accurate and robust localization systems. In this work, the problem of global localization for unmanned aerial vehicles (UAVs) is analyzed by proposing a sequential, end-to-end, and multimodal deep neural network based monocular visual-inertial localization framework. More specifically, the proposed neural network architecture is three-fold; a visual feature extractor convNet network, a small IMU integrator bi-directional long short-term memory (LSTM), and a global pose regressor bi-directional LSTM network for pose estimation. In addition, by fusing the traditional IMU filtering methods instead of LSTM with the convNet, a more time-efficient deep pose estimation framework is presented. It is worth pointing out that the focus in this study is to evaluate the precision and efficiency of visual-inertial (VI) based localization approaches concerning indoor scenarios. The proposed deep global localization is compared with the various state-of-the-art algorithms on indoor UAV datasets, simulation environments and real-world drone experiments in terms of accuracy and time-efficiency. In addition, the comparison of IMU-LSTM and IMU-Filter based pose estimators is also provided by a detailed analysis. Experimental results show that the proposed filter-based approach combined with a DL approach has promising performance in terms of accuracy and time efficiency in indoor localization of UAVs.

Prepared by Abdullah Yusefi, Akif Durdu, M. Fatih Aslan and Cemil Sungur

Link: https://doi.org/10.1109/ACCESS.2021.3049896

Video Link: https://youtu.be/CJeX0lFX1do

CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection

Coronavirus disease 2019 (COVID-2019), which emerged in Wuhan, China in 2019 and has spread rapidly all over the world since the beginning of 2020, has infected millions of people and caused many deaths. For this pandemic, which is still in effect, mobilization has started all over the world, and various restrictions and precautions have been taken to prevent the spread of this disease. In addition, infected people must be identified in order to control the infection. However, due to the inadequate number of Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, Chest computed tomography (CT) becomes a popular tool to assist the diagnosis of COVID-19. In this study, two deep learning architectures have been proposed that automatically detect positive COVID-19 cases using Chest CT X-ray images. Lung segmentation (preprocessing) in CT images, which are given as input to these proposed architectures, is performed automatically with Artificial Neural Networks (ANN). Since both architectures contain AlexNet architecture, the recommended method is a transfer learning application. However, the second proposed architecture is a hybrid structure as it contains a Bidirectional Long Short-Term Memories (BiLSTM) layer, which also takes into account the temporal properties. While the COVID-19 classification accuracy of the first architecture is 98.14%, this value is 98.70% in the second hybrid architecture. The results prove that the proposed architecture shows outstanding success in infection detection and, therefore this study contributes to previous studies in terms of both deep architectural design and high classification success.

Prepared by Muhammet Fatih Aslan, Muhammed Fahri Unlersen, Kadir Sabanci, Akif Durdu

Link: https://doi.org/10.1016/j.asoc.2020.106912