Mobile Robot System Research Articles

Algorithmic support of an adaptive control system for an autonomous mobile robot

Algorithmic support of an adaptive control system for an autonomous mobile robot

ЦИФРОВА ТРАНСФОРМАЦІЯ ТРАНСПОРТНОЇ СИСТЕМИ В УКРАЇНІ

The article is devoted to the study of the features and directions of digital transformation at the regional level in Ukraine. The purpose of the work is to study the concept of digital transformation; assessment of digital technologies in transport; analysis of Smart-city cases; development of measures for the digital transformation of the transport system of Ukraine at the regional level. In the process of research, the authors used dialectical and abstract-logical methods, which revealed the nature of digital transformation and identified its principles. The application of the logical method made it possible to enrich the scientific characteristics of the concept of "digital transformation". On the basis of systemic and synergistic approaches, directions for the implementation of digital technologies in transport were evaluated. Methods of analysis and synthesis were also applied to research the international practice of digitalization of the transport system at the regional level, as well as to develop proposals for the digital transformation of the transport sector in the regions of Ukraine. The concept of digital transformation in work is defined as a process based on a moving from traditional models, involves qualitative changes in business processes or ways of conducting economic activity, as a result of which digital technologies are implemented, which leads to significant socio-economic effects. The work noted that transport and logistics are the industries in which the economic effect of digital transformation is most tangible. The transport system is most receptive to the introduction of such digital technologies as: Internet of Things, unmanned and mobile technologies, identification technologies, blockchain, big data, paperless technologies, drones, robotic systems, artificial intelligence and neural networks. The cases of digital transformation of regions (EU and Canada) and the Smart City project, an integral component of which is transport, were analyzed in order to determine the possibilities of their implementation in Ukraine under martial law. A number of recommendations have been developed to ensure the digitization of the transport system of the regions of Ukraine and the directions for its implementation have been determined.

Особливості блока керування для кореляційного оброблення зображень

The widespread introduction of mobile robots in various areas of human activity requires their further improvement and modernization of basic systems in their composition. The most involved in this case are the means of technical vision in the onboard systems of mobile robots, as well as the associated control blocks. When the mobile robot functions in automatic mode, it is necessary to take into account several features and limitations that are due to the nature of the practical tasks. For the control block, first of all, it is to ensure the speed of operation and compactness of implementation with a focus on FPGA technology. In this paper, these aspects of the construction of the control block are considered in terms of the implementation of correlation processing of static digital (binary) images. As a specific example, an optoelectronic system with a correlation binary matrix and a matrix of LEDs to visualize the generated optical correlation relief was chosen. Such systems are most often part of onboard control systems for mobile robots and are designed to detect and identify objects. The structure of the control block is proposed, taking into account the peculiarities of correlation processing in the optoelectronic system. The control block contains three counters: a clock counter, an address counter for reading from the reference memory, an address counter for an offset in the correlation matrix, and a control device. The control device as a part of the control block as the microprogram automaton (MPA) with the use of features of synthesis of the R- automaton is constructed. A feature of the R-machine is the implementation of its storage part on the shift register (R) in contrast to the parallel registers (T) and counters (ST). Such an approach simplifies the combinational part of the MPA with the possibility of increasing its regular memory based on the shift register. This allows you to effectively implement such structures in a single chip with FPGA architecture.

Distributed Docking Station System for Mobile Robots

Distributed Docking Station System for Mobile Robots

Construction of 2D relative positioning accuracy evaluation experimental system for mobile robots for infrastructure inspection

Construction of 2D relative positioning accuracy evaluation experimental system for mobile robots for infrastructure inspection

Towards Lifelong Federated Learning in Autonomous Mobile Robots with Continuous Sim-to-Real Transfer

The role of deep learning (DL) in robotics has significantly deepened over the last decade. Intelligent robotic systems today are highly connected systems that rely on DL for a variety of perception, control and other tasks. At the same time, autonomous robots are being increasingly deployed as part of fleets, with collaboration among robots becoming a more relevant factor. From the perspective of collaborative learning, federated learning (FL) enables continuous training of models in a distributed, privacy-preserving way. This paper focuses on vision-based obstacle avoidance for mobile robot navigation. On this basis, we explore the potential of FL for distributed systems of mobile robots enabling continuous learning via the engagement of robots in both simulated and real-world scenarios. We extend previous works by studying the performance of different image classifiers for FL, compared to centralized, cloud-based learning with a priori aggregated data. We also introduce an approach to continuous learning from mobile robots with extended sensor suites able to provide automatically labelled data while they are completing other tasks. We show that higher accuracies can be achieved by training the models in both simulation and reality, enabling continuous updates to deployed models.

Long-term operation of a remote control system for mobile robots using a smartphone application by any user

Long-term operation of a remote control system for mobile robots using a smartphone application by any user

Multi-modal communication system for mobile robot

This paper presents a cloud-based multi-modal human-robot interaction architecture. The architecture consists of parts running on the edge (mobile) platform and cluster services. Software on the mobile platform is represented primarily by a Robot Operating System, an MQTT broker and the client side of the SpeechCloud architecture, which provides the communication with the computing cluster. Its detailed description is a part of the paper. The main contribution of the paper is a design of an architecture based on standard frameworks, protocols, and validated JSON messages. The paper also focuses on the description of a tested mobile platform equipped with an NVIDIA Jetson family computer and information about tasks that the robot will be able to perform using the proposed architecture.

Analysis of the aerodynamic performance of a twin-propelled wall-climbing robot based on computational fluid dynamics method

We present a twin-propelled wall-climbing robot that can stably adsorb and move quickly on a vertical wall by exploiting the propeller’s reverse thrust as the adsorption force and the wheel as the movement method. This paper derives and theoretically analyses the aerodynamic characteristics of the twin-propelled wall-climbing mobile robot system exploiting the momentum inflow model and blade element theory and measures the reverse thrust of a single propeller through real-world experiments. Additionally, Computational Fluid Dynamics simulation software analyzes the influence of structural parameters, such as the lateral spacing of the twin-propeller fixed plate, the width of the fixed-rotor plate, and the inclination angle of the double-rotor on the airflow around the robot. Experiments on the adsorption and movement performance of the dual-rotor wall-climbing robot on a vertical wall demonstrate that the designed twin-propelled wall-climbing robot can stably adsorb and move on a vertical wall.

Development of a Remote-Controlled Wheeled Mobile Robot System with a Mechanical Safety Brake by Using Eye Movements

Development of a Remote-Controlled Wheeled Mobile Robot System with a Mechanical Safety Brake by Using Eye Movements

Autonomous distributed mobile robotic system for various off-road environments

Autonomous distributed mobile robotic system for various off-road environments

A novel design of a smart interactive guiding robot for busy airports

Abstract The COVID-19 pandemic has had a massive impact on the global aviation industry. As a result, the airline industry has been forced to embrace new technologies and procedures in order to provide a more secure and bio-safe travel. Currently, the role of smart technology in airport systems has expanded significantly as a result of the contemporary Industry 4.0 context. The article presents a novel construction of an intelligent mobile robot system to guide passengers to take the plane at the departure terminals at busy airports. The robot provides instructions to the customer through the interaction between the robot and the customer utilizing voice communications. The usage of the Google Cloud Speech-to-Text API combined with technical machine learning to analyze and understand the customer's requirements are deployed. In addition, we use a face detection technique based on Multi-task Cascaded Convolutional Networks (MTCNN) to predict the distance between the robot and passengers to perform the function. The robot can guide passengers to desired areas in the terminal. The results and evaluation of the implementation process are also mentioned in the article and show promise.

Development of Mobile Robot System Based on Nano-scale Micro-surface Measurement

Absrtact. The system development of the mobile robot mainly includes two parts: one is to build a laser interference system based on piezoelectric ceramic dynamic carrier; The other part is the image processing of the interference fringe pattern collected by the interference system. The laser interference system can be installed on the front-end manipulator of the robot as an integral structure. The shape information of the measured micro-surface can be obtained by processing the interference fringes collected by the image acquisition card on the interference system, so as to achieve the purpose of high-precision surface roughness measurement.

A combined calibration method of a mobile robotic measurement system for large-sized components

Product quality control of large-sized components with complex supports requires automatic and accurate 3D shape measurement. For accurate and efficient measurements of key local features (KLFs) on the mounting surface of multiple supports, we propose a flexible measurement method combining a laser tracker, a 3D scanner, and a mobile robot system. As for improving the overall measurement accuracy, we also introduce a calibration method based on a multidimensional combined collaboration target (MCCT) to establish correlation constraints between global and local calibration. Specifically, a global calibration method based on multidimensional geometric constraints provides a global measurement field. Additionally, a local calibration method derived from combination optimization model achieves accurate calibration of extrinsic parameters. We constructed the corresponding mobile robotic measurement system (MRMS) and conducted experiments. The experimental results demonstrate that the maximum and mean calibration errors are reduced from 0.045/0.0261 mm to 0.0231/0.0122 mm within 7 m, which features high accuracy.

Development of a Design Methodology for Cloud Distributed Control Systems of Mobile Robots

This article addresses the problem of cloud distributed control systems development for mobile robots. The authors emphasize the lack of a design methodology to guide the process of the development in accordance with specific technical and economic requirements for the robot. On the analysis of various robots architectures, the set of the nine most significant parameters are identified to direct the development stage by stage. Based on those parameters, the design methodology is proposed to build a scalable three-level cloud distributed control system for a robot. The application of the methodology is demonstrated on the example of AnyWalker open source robotics platform. The developed methodology is also applied to two other walking robots illustrated in the article.

“Is there anybody out there?” Using a telepresence robot to engage in face time at the office

PurposeThe purpose of this paper is to study the impact of mobile robotic telepresence systems on face time – which refers to people “seeing and being seen” – and analyse whether they allow overcoming the challenges associated with telecommuting.Design/methodology/approachThis research is based on a qualitative methodology in two French high-tech companies using interviews to better understand how the use of a telepresence robot is experienced by teleworkers, co-workers and their managers.FindingsThe results demonstrate that telepresence robots do offset the absence of teleworkers by allowing them to engage in face time, even remotely. It shows how the telepresence robot's affordances impact the different dimensions of face time and examine the processes through which teleworkers and co-workers anthropomorphize the robot and manage their privacy needs.Originality/valueThis article further elaborates the concept of face time and offers six dimensions to study in a digitally driven environment, including two newly identified dimensions. It also discusses the surveillance and privacy needs issues raised by the use of mobile robotic telepresence (MRP) systems.

Design of Secure Microcontroller-Based Systems: Application to Mobile Robots for Perimeter Monitoring.

This paper describes an original methodology for the design of microcontroller-based physical security systems and its application for the system of mobile robots. The novelty of the proposed methodology lies in combining various design algorithms on the basis of abstract and detailed system representations. The suggested design approach, which is based on the methodology, is modular and extensible, takes into account the security of the physical layer of the system, works with the abstract system representation and is looking for a trade-off between the security of the final solution and the resources expended on it. Moreover, unlike existing solutions, the methodology has a strong focus on security. It is aimed at ensuring the protection of the system against attacks at the design stage, considers security components as an integral part of the system and checks if the system can be designed in accordance with given requirements and limitations. An experimental evaluation of the methodology was conducted with help of its software implementation that consists of Python script, PostgreSQL database, Tkinter interface and available for download on our GitHub. As a use case, the system of mobile robots for perimeter monitoring was chosen. During the experimental evaluation, the design time was measured depending on the parameters of the attacker against which system security must be ensured. Moreover, the software implementation of the methodology was analyzed in compliance with requirements and compared with analogues. The advantages and disadvantages of the methodology as well as future work directions are indicated.

2D-to-3D Projection for Monocular and Multi-View 3D Multi-class Object Detection in Indoor Scenes

In this paper, we propose a novel method of joint 3D object detection and room layout estimation. The proposed method surpasses all existing methods of 3D object detection from monocular images on the indoor SUN RGB-D dataset. Moreover, the proposed method shows competitive results on the ScanNet dataset in multi-view mode. Both these datasets are collected in various residential, administrative, educational and industrial spaces, and altogether they cover almost all possible use cases. Moreover, we are the first to formulate and solve a problem of multi-class 3D object detection from multi-view inputs in indoor scenes. The proposed method can be integrated into the controlling systems of mobile robots. The results of this study can be used to address a navigation task, as well as path planning, capturing and manipulating scene objects, and semantic scene mapping.

КОМПЛЕКСИРОВАНИЕ ДАННЫХ СИСТЕМЫ УПРАВЛЕНИЯ МОБИЛЬНЫМ ГУСЕНИЧНЫМ РОБОТОМ

Integration of information – the process of combining data to determine or predict the state of an object. The integration provides an increase in the robustness of the robot control and the accuracy of machine perception of information. The paper discusses one of the methods for integrating of the robot onboard data using the example of the mobile tracked robot data. One of the aim is showing how to obtain the Jacobi matrix of the process function and the Jacobi matrix of the observation function of the mobile robot system for subsequent data integration by the state observer, built on the basis of the Kalman filter, that can convert the robot onboard data into the elements of the state vector of the mobile robot system. Each nonzero element of the Jacobi matrix of the observation function of the system is a weight coefficient. It determines the contribution of an element of the output vector of the system corresponding to this weight coefficient to the result of information integration calculated by the Kalman filter – the state observer. The Kalman filter is a sequential recurrent algorithm for filtering information from discrete dynamical systems specified in the state space. A feature of the Kalman filter as an observer of the state of the system is the assumption that the observed system has the effect of white Gaussian noise (characterized by zero mathematical expectation) on its state.

EVOLUTIONS OF GROUP MANAGEMENT DEVELOPMENT OF MOBILE ROBOTIC PLATFORMS IN WAREHOUSING 4.0.

The subject of this research is the technology of management of mobile robot groups in the concept of Industry 4.0 and its composition. The purpose of this article is to find ways to implement an effective strategy for building and managing mobile robotic platforms in Warehousing, as a key tool of Lean Production. To achieve this goal, it is necessary to solve the following tasks: to analyze the management of supply chains in Smart Manufacturing, within Industry 4.0 and its impact on achieving the goals of Lean Production; to study the evolution of technologies used in Warehousing in the dynamics of the Industrial Revolution; to analyze the evolution of Warehouse Management Systems (WMS) as one of the most important components on the basis of which the requirements for automation of Warehousing automation in Smart Manufacturing with group management of mobile robotic platforms are implemented and achieved; to compare the impact of the technologies used by Warehousing 4.0 and Warehouse Management Systems on the key indicators of Lean Production. Results: One of the promising ways to achieve the effectiveness of the implementation of Lean Production tools in WMS systems is the use of Collaborative Robot System technology, which makes it possible to ensure a high density of product storage in Warehousing. However, modern mobile robotic platforms have their limitations both in the methods of loading and unloading products, and in the design. Therefore, the authors see the task in improving the design of mobile robotic platforms, which will develop a new intelligent group method of loading and unloading products, increasing the storage density for a variety of goods. Conclusions: The paper compares the impact of Warehousing 4.0 and Warehouse Management Systems on key Lean Production tools, which shows how the introduction of new group management technologies for robotic platforms in Warehousing 4.0 and Warehouse Management Systems (WMS) affects the effectiveness of Lean Production tools such as Heijunka, Just-in-time, 5S. This suggests that the introduction of new models and methods of managing complex warehouses with high density and chaotic storage of products, through the use of mobile robotic autonomous systems, will significantly optimize the process of supply chain management in Smart Manufacturing.