Artificial Intelligence for Obstacle Detection in Railways: Project SMART and Beyond

Author(s):  
Danijela Ristić-Durrant ◽  
Muhammad Abdul Haseeb ◽  
Marten Franke ◽  
Milan Banić ◽  
Miloš Simonović ◽  
...  

2021 ◽  
Author(s):  
Tamas Nemes

This work describes a new type of portable, self-regulating guidance system, which learns to recognize obstacles with the help of a camera, artificial intelligence, and various sensors and thus warn the wearer through audio signals. For obstacle detection, a MobileNetV2 model with an SSD attachment is used which was trained on a custom dataset. Moreover, the system uses the data of motion and distance sensors to improve accuracy. Experimental results confirm that the system can operate with 74.9% mAP accuracy and a reaction time of 0.15 seconds, meeting the performance standard for modern object detection applications. It will also be presented how those affected commented on the device and how the system could be transformed into a marketable product.



Author(s):  
Danijela Ristić-Durrant ◽  
Muhammad Abdul Haseeb ◽  
Milan Banić ◽  
Dušan Stamenković ◽  
Miloš Simonović ◽  
...  

This paper presents an on-board multi-sensor system which is able to detect obstacles and estimate their distances in railway scenes in different illumination conditions. The system was developed within the H2020 Shift2Rail project SMART (Smart Automation of Rail Transport) and aims at increasing the safety of rail transport by detecting obstacles on the rail tracks ahead of a moving train in order to reduce the number of collisions. The system hardware consists of cameras of different types integrated into a specially designed housing, mounted on the front of the train. Multiple vision sensors complement each other in order to handle different illumination and environmental conditions. The system software uses a novel machine learning-based method that is suited to a particular challenge of railway operations, the need for long-range obstacle detection and distance estimation. The development of this method used a long-range railway dataset, which was specifically generated for this project. Evaluation results of reliable obstacle detection in various environmental conditions using the SMART RGB camera in day light illumination conditions and using the SMART Night Vision sensor in poor (night) illumination conditions are presented. The results demonstrate both the potential of the on-board SMART obstacle detection system in the operational railway environment and the benefit of the use of different cameras to be more independent of light and environmental conditions.



2021 ◽  
Vol 2107 (1) ◽  
pp. 012030
Author(s):  
F S Kamaruddin ◽  
N H Mahmood ◽  
M A Abdul Razak ◽  
N A Zakaria

Abstract Visually impaired people usually have a lot of difficulties involved in interacting with their environment. Physical movement is a major challenge for them, because it can be tricky to make a distinction about where they are and how they can move from one place to another. In this project, smart assistive shoes with Internet of Things (IoT) implementation is designed. These shoes are equipped with ultrasonic sensors and vibration motors that can warn users about obstacles. Next, the IoT system is implemented using Adafruit IO and If This, Then That (IFTTT) to transfer data between Google Assistant and buzzer for shoes position finder purposes. NodeMCU allows the buzzer on shoes to be controlled by the Internet using its WiFi module which is connected to the mobile phone hotspots. As a result, shoes with an obstacle detection system which can detect obstacles within 20 cm distance and shoes position finder using Google Assistant are designed. In conclusion, hopefully these shoes will become one of the alternatives to aid the independent movement of the visually impaired people in the future.



2020 ◽  
Vol 5 (1) ◽  
pp. 10-17
Author(s):  
Jia-Shing Sheu ◽  
Chen-Yin Han

This study developed scene recognition and cloud computing technology for real-time environmental image-based regional planning using artificial intelligence. TensorFlow object detection functions were used for artificial intelligence technology. First, an image from the environment is transmitted to a cloud server for cloud computing, and all objects in the image are marked using a bounding box method. Obstacle detection is performed using object detection, and the associated technique algorithm is used to mark walkable areas and relative coordinates. The results of this study provide a machine vision application combined with cloud computing and artificial intelligence scene recognition that can be used to complete walking space activities planned by a cleaning robot or unmanned vehicle through real-time utilization of images from the environment.





Author(s):  
A. Medina-Santiago ◽  
Luis Alberto Morales-Rosales ◽  
Carlos Arturo Hernández-Gracidas ◽  
Ignacio Algredo-Badillo ◽  
Ana Dalia Pano-Azucena ◽  
...  

Obstacle-avoidance robots have become an essential field of study in recent years. This paper analyzes two cases that extend reactive systems focused on obstacle detection and its avoidance. The scenarios explored get data from their environments through sensors and generate information for the models based on artificial intelligence to obtain a reactive decision. The main contribution is focused on the discussion of aspects that allow comparing both approaches, such as the heuristic approach implemented, requirements, restrictions, response time, and performance. The first case presents a mobile robot that applies fuzzy logic to achieve soft turning basing its decision on depth image information. The second case introduces a mobile robot based on multi-layer perceptron and ultrasonic sensors to decide how to move in an uncontrolled environment. The analysis of both options offers perspectives to choose between reactive obstacle-avoidance systems based on ultrasonic or Kinect sensors, models that infer optimal decisions applying fuzzy logic or artificial neural networks, with key elements and methods to design mobile robots with wheels. Therefore, we show how AI or Fuzzy Logic techniques allow us to design mobile robots that learn from their “ experience ” by making them safe and adjustable for new tasks, unlike traditional robots that use large programs to perform a specific task.



2021 ◽  
Vol 11 (14) ◽  
pp. 6468
Author(s):  
A. Medina-Santiago ◽  
Luis Alberto Morales-Rosales ◽  
Carlos Arturo Hernández-Gracidas ◽  
Ignacio Algredo-Badillo ◽  
Ana Dalia Pano-Azucena ◽  
...  

Obstacle–Avoidance robots have become an essential field of study in recent years. This paper analyzes two cases that extend reactive systems focused on obstacle detection and its avoidance. The scenarios explored get data from their environments through sensors and generate information for the models based on artificial intelligence to obtain a reactive decision. The main contribution is focused on the discussion of aspects that allow for comparing both approaches, such as the heuristic approach implemented, requirements, restrictions, response time, and performance. The first case presents a mobile robot that applies a fuzzy inference system (FIS) to achieve soft turning basing its decision on depth image information. The second case introduces a mobile robot based on a multilayer perceptron (MLP) architecture, which is a class of feedforward artificial neural network (ANN), and ultrasonic sensors to decide how to move in an uncontrolled environment. The analysis of both options offers perspectives to choose between reactive Obstacle–Avoidance systems based on ultrasonic or Kinect sensors, models that infer optimal decisions applying fuzzy logic or artificial neural networks, with key elements and methods to design mobile robots with wheels. Therefore, we show how AI or Fuzzy Logic techniques allow us to design mobile robots that learn from their “experience” by making them safe and adjustable for new tasks, unlike traditional robots that use large programs to perform a specific task.



Author(s):  
A P Shuravin ◽  
S V Vologdin

The article substantiates the relevance of optimization algorithms research for solving various applied problems and for the science of artificial intelligence. The need to solve problems of optimizing the thermal-hydraulic modes of buildings (as part of the project "Smart City") is explained. The paper presents a mathematical formulation of the problem of optimizing the temperature mode of rooms using adjustable devices. Existing work provides two methods for solving the posed problem. They are the coordinates search method and the genetic algorithm. The article contains the description of the above mentioned algorithms (including the mathematical apparatus used). The results of the computational experiment (for the considered optimization methods) are presented. These experimental results show that the genetic algorithm provides better optimization results than the coordinates search method, but it has a large computational cost. The hypothesis was confirmed that in order to increase the efficiency of solving the considered class of problems it is necessary to combine the genetic algorithm and the coordinates search method.



Sign in / Sign up

Export Citation Format

Share Document