Development Of Unmanned Systems Research Articles

Investigation of the effect of object size on accuracy of human localisation in images acquired from unmanned aerial vehicles

The use of unmanned aerial vehicles is gaining wide popularity in various areas of research and information acquisition. More and more often, unmanned aerial vehicles are used to obtain various types of images of the Earth’s surface for its study. In particular, such data can be used in law enforcement, localization of crowds, etc. Typically, such systems operate independently of humans and provide information about objects in an automatic mode, with humans working only under the control of the aircraft. One of the main components of such systems is a neural network for localization and classification of objects, the parameters of which determine both the accuracy of the system as a whole and the design of the aircraft for shooting. In particular, the accuracy of the neural network determines the profitability of such a system, because if the accuracy is insufficient, the use of such systems will not make sense. Therefore, the main subject of research in this paper is a neural network for object localization, in particular YOLO v5, and its accuracy parameters on images obtained from unmanned aerial vehicles. The main focus of this paper is on the parameters of the neural network and the study of its metrics, which are important parameters of a trained neural network. Another important parameter for the further use of a neural network is its training parameters, as well as the data used for training. This study also pays attention to the details of the training process. The main goal of this study is to train a neural network on a selected dataset and to study the accuracy metrics of the trained neural network. The main goal of this study is to determine the dependence of localization accuracy on the area of the object, which will allow for more detailed development of unmanned systems with automatic object detection, as well as to assess the profitability of using such systems in task planning. On the basis of the data obtained, conclusions were drawn about the dependence of localization accuracy on the area of an object in images from unmanned aerial vehicles. These data can serve as a reference for unmanned aerial vehicle developers, particularly when selecting photo modules or planning the system architecture.

The Armed Forces of Ukraine unmanned systems future development

The relevance of the article is due to the Armed Forces of Ukraine unmanned systems development normative forecasting need in order to achieve a superiority over the enemy. One of the futures` main provisions of the Armed Forces of Ukraine unmanned systems development has been outlined. Futures have been developed by using a modified method of "branches" as a component of foresight (scenario forecasting). Elements of SWOT analysis and the cognitive-dynamic method of forecasting were also applied in the part regarding normative forecasting. The future of the Armed Forces of Ukraine unmanned systems development is presented as the desired version of the development of these systems in the future, using cause-and-effect logic. Within its framework, the main trends in the development of unmanned systems in the leading countries of the World were considered. The list and content of the main stages of development of futures according to the modified method of "branches" are presented. The forecasting horizon is defined. The author's view on the ecosystem of unmanned systems that has apeared in Ukraine is offered. The results of the analysis of the stakeholders of the considered ecosystem are presented with the distribution of their influence and interest according to the Mendelov and Johnson matrices. Based on the analysis of external and internal factors that will influence the development of unmanned systems, as well as the future operating environment, the key results that must be achieved to realize the main development goal and the main ways (actions, influences) to achieve them are determined. The key results cover two main areas - as organizational and technological and as combat also. In addition, the priority directions for the unmanned systems of the Armed Forces of Ukraine development by components, levels, types and technical aspects have been determined. The proposed futures may be used both as for more detailed regulatory forecasting of the unmanned systems development, for example, when developing of a corresponding foresight, as during the program documents (strategies, concepts, etc.) development or priorities of the State's military and technical policy determination.

Research on underwater unmanned platform route planning based on marine environment constraints

Since the development of unmanned systems, autonomous underwater unmanned platforms have become an important facility for countries to explore the ocean field which play an important role in both military and civilian. In this paper, the route planning of underwater unmanned platform is carried out from three constraints: the risk that affects the operational effectiveness of the unmanned underwater platform, the navigation resistance and the navigation path length. The simulation results show that the model can deal with three constraints reasonably and plan a suitable route.

ИННОВАЦИОННЫЕ ТЕХНОЛОГИИ ДЛЯ БЕСПИЛОТНЫХ СИСТЕМ

Specialists in the motor transport industry are faced with a large-scale task of developing unmanned systems: highly automated vehicles and supporting infrastructure. The article analyzes the state policy of the formation and implementation of innovative, modern and end-to-end technologies for unmanned vehicles and road transport infrastructure. The authors provide an overview of innovative technologies presented in documents at the federal level that influence the development of unmanned systems, prospects and possibilities for their use in the motor transport industry. Innovative foreign and domestic experience in the use of modern innovative technologies in organizing freight and passenger road transport in Russia, the USA, Germany, Israel, and China is presented.

Государственная политика в области развития беспилотных систем

Currently, unmanned aerial vehicles are increasingly being used in the oil and gas industry, agriculture, electric power, construction and architecture, mining, and urban economy. The number of works carried out using unmanned vehicles is increasing: aerial photography, laser scanning, gas analysis, multispectral photography and others. The organization of the functioning of unmanned logistics corridors on public roads is underway. Unmanned vehicles for technological transportation are increasingly being used in the territories of factories. The state sets a large-scale task for the specialists of the transport industry to develop unmanned transport. In order to conduct research in this area, it is necessary to clearly trace the main guidelines of state policy in the field of unmanned transport, to represent the field of development of the transport industry. The article analyzes the state policy aimed at the development and maintenance of unmanned systems in the aviation, railway, and automotive industries. The regulatory and legislative framework regulating the possibility of creating and operating unmanned vehicles in the Russian Federation is given. One of the problems of the use of drones is the lack of legal regulation of their use in the transport complex of the country. Currently, programs and documents regulating the development of unmanned systems are being implemented and planned for implementation at the state level: “Strategy for the development of unmanned aviation of the Russian Federation for the period up to 2030 and for the future up to 2035”, “Transport Strategy of the Russian Federation up to 2030 with a forecast for the period up to 2035”, Decree of the Government of the Russian Federation “On the establishment of an experimental Legal Regime in the Field of digital innovations and Approval of the Program of an experimental legal Regime in the Field of Digital innovations for the Operation of Highly Automated Vehicles in relation to the implementation of the initiative “Unmanned Logistics Corridors” on the Federal Highway M-11 “Neva”, etc. For the possibility of using unmanned vehicles in the Russian Federation, interdepartmental interaction of federal executive authorities is necessary. The state policy in the field of creation, production and operation of unmanned systems is aimed, among other things, at the development of human resources, training of specialists with interdisciplinary knowledge.

Deep learning-based perception systems for autonomous driving: A comprehensive survey

With the rapid development of society and the economy, autonomous driving techniques are widely applied in many areas, such as autonomous vehicles, autonomous drones, and robotics. As a dominating technique, deep learning has become more and more popular for 2-D and 3-D object detection. Numerous deep learning-based methods have been proposed to solve various vision issues. To further help with the development of unmanned systems, this paper presents a comprehensive survey of the recent processes from the past five years for 3-D object detection, road detection, traffic sign detection, and traffic light detection and classification. To summarize and analyze previous works in detail, this paper only focuses on deep learning-based object detection tasks in autonomous driving that take place when the input is a point cloud or image(s). It also presents comparative results for insight comparison and inspiring future researches.

State prediction for marine diesel engine based on variational modal decomposition and long short-term memory

With the development of unmanned systems, more and more attentions are paid to the energy and power systems of data-driven ships. The autonomy of unmanned ships puts forward urgent requirements for the monitoring and prediction of the energy and power system of ships. Aiming at the state prediction for marine diesel engine, an improvement method based on variational modal decomposition (VMD) and long short-term memory (LSTM) is proposed in this paper. The sub signals are obtained by decomposing the signal to be predicted through VMD, the sub signals and resident signal are all predicted with LSTM, and the reconstruction prediction signal is obtained by sum all the predicted sub signals and resident signal. Compared with LSTM, ESN, and SVR methods, the proposed method reduces the prediction errors significantly. Compared with LSTM, the RE errors of the two sensors are reduced by 49.79% and 56.32% respectively, and the RMSE errors are reduced by 34.65% and 27.71% respectively. The performance of this method is better than other methods, and it has sufficient accuracy performance for state prediction of marine diesel engine.

Unmanned Systems Security: Models, Challenges, and Future Directions

A series of promising technologies such as artificial intelligence and the sixth-generation mobile network are thriving in recent years, resulting in unprecedented development of unmanned systems. Because of its faster processing ability, stronger adaptability and longer working hours, unmanned systems have been widely applied in all kinds of fields, including but not limited to military, industry, agriculture, and medical treatments. The broad application also presents many problems, making the security of unmanned systems a significant concern. Nevertheless, current research is mostly focused on a single or specific system, while paying little attention to general security issues in unmanned systems. Toward this end, we provide in this article a unified definition and a brief overview of unmanned systems. After that, a two-dimensional security model is proposed from a holistic perspective, based on which we present comprehensive security analysis for unmanned systems, including the attack types and corresponding countermeasures. Several existing challenges are also identified and discussed in detail as well as future research directions.

Using Ship-Deployed High-Endurance Unmanned Aerial Vehicles for the Study of Ocean Surface and Atmospheric Boundary Layer Processes

Unmanned aerial vehicles (UAVs) are proving to be an important modern sensing platform that supplement the sensing capabilities from platforms such as satellites, aircraft, research vessels, moorings, and gliders. UAVs, like satellites and aircraft can provide a synoptic view of a relatively large area. However, the coarse resolution provided by satellites and the operational limitations of manned aircraft has motivated the development of unmanned systems. UAVs offer unparalleled flexibility of tasking; for example, low altitude flight and slow airspeed allow for the characterization of a wide variety of geophysical phenomena at the ocean surface and in the marine atmospheric boundary layer. Here, we present the development of cutting-edge payload instrumentation for UAVs that provides a new capability for ship-deployed operations to capture a unique, high resolution spatial and temporal variability of the changing air-sea interaction processes than was previously possible. The modular design of the base payload means that new instruments can be incorporated into new research proposals that may include new instruments for expanded use of the payloads as a long-term research facility. Additionally, we implement a novel capability for vertical take-off and landing (VTOL) from research vessels. This VTOL capability is safer and requires less logistical support than previous ship-deployed systems. The payloads developed include thermal infrared, visible broadband and hyperspectral, and near-infrared hyperspectral high-resolution imaging. Additional capabilities include quantification of the longwave and shortwave hemispheric radiation budget (up- and down-welling) as well as direct air-sea turbulent fluxes. Finally, a UAV-deployed dropsonde-microbuoy was developed in order to profile the temperature, pressure and humidity of the atmosphere and the temperature and salinity of the near-surface ocean. These technological advancements provide the next generation of instrumentation capability for UAVs. When deployed from research vessels, UAVs will provide a transformational science prism unequaled using 1-D data snapshots from ships or moorings alone.

Managing Awareness in a CURVE‐y World: Agile Systems Engineering for Autonomous Vehicles

ABSTRACTAwareness is vital to agility. Based on an INCOSE agile systems engineering case study, this article illustrates different perspectives on enabling, exploiting, and balancing awareness, including issues of networks versus hierarchies, teaming and leadership, pattern exploitation, model uncertainty, and optimal estimation and control. The SPAWAR System Center Pacific (SSC‐Pac) in San Diego, US‐CA established capability to facilitate agile development of unmanned systems. As a case study in the INCOSE Agile Systems Engineering Life Cycle Model (ASELCM) Discovery Project, SSC‐Pac provided an example of agility challenges and issues of awareness in addressing them. The model‐based ASELCM Pattern helped us analyze this example beyond the context of agile software methods.

Naval robots and rescue

AbstractThe development of unmanned systems (UMS) for naval combat poses a profound challenge to existing conventions regarding the treatment of the shipwrecked and wounded in war at sea. Article 18 of the 1949 Geneva Convention II states that warring parties are required to take “all possible measures” to search for and collect seamen left in the water after each engagement. The authors of the present paper analyze the ethical basis of this convention and argue that the international community should demand that UMS intended for roles in war at sea be provided with the capacity to make some contribution to search and rescue operations.

Formation Algorithms for Multiple Mobile Robots Based on Vision Detection

Abstract Unmanned operating system is applied to various fields. The disadvantages of the single unmanned system, such as its own limitations, poor flexibility, poor ability, low efficiency, cannot be overcome, as the complexity of the tasks continue to increase. As a result, the cooperative operation system of multi-unmanned platforms is gradually regarded as the main trend of the development of unmanned systems. A novel multiple mobile robots co-avoidance scheme and an improved linear formation algorithm are proposed in this paper. The basic principle and programming steps of the algorithm are described in detail. The improved linear formation algorithm is used for simulation studies. The validity and practicability of the line formation algorithm are verified.

Development of the remote-controlled platform truck for handling heavy object and the remote control human interface for the disaster response

General interest for robotic technology has been increased by the public and the media after Fukushima Daiichi Nuclear Power Plant (hereafter referred to as 1F) disaster. Especially, robots which can work under the very severe condition where personnel cannot access have demands for development. As to respond to such high demands, NEDO established ‘Disaster response unmanned systems development project’ in 2012.[1] This project is specialized in the development of various remote-controlled equipment, such as remote-controlled platform truck and remote control human interface under ‘Mobile Robot Development’. Remote-controlled platform truck is designed to safely and surely deliver robots and supplies, instead of using stairs and elevator, etc. in and out of building where it is too critical for personnel to work under. Remote control human interface for robots is designed to standardize the command and operation screen for operator, based on opinions from project members, and manned facility construction.[2] In this article, mechanical structure and development tasks for remote-controlled platform truck, and commonalization approach for operation and camera display of various remote-controlled equipment and robot for remote control human interface are stated. Background: due to hydrogen explosion triggered by The Great East Japan Earthquake on 11 March 2011, a reactor building at Fukushima Daiichi Nuclear Power Plant was severely damaged. It is required to reduce high radiation dose in the atmosphere of the reactor building to perform restoration. To pursue decontamination of the reactor building, equipment to lift and carry decontamination devices to upper floor are required.

Unmanned systems with Ada and RTEMS

This tutorial provides an introduction to the development of software in Ada for unmanned systems. The authors will demonstrate how they are using Ada over RTEMS in developing the real time control software for a large unmanned ground vehicle. RTEMS is an open source, real-time operating system that provides a high performance environment for embedded applications on a range of processors and embedded hardware. The format of the tutorial will be hands-on, focusing on developing applications in Ada over RTEMS using a live Fedora GNU Linux DVD. The DVD provides a complete GNAT Ada installation with all sources and scripts as well as the prebuilt toolset and simulators. The instructors will demonstrate some of the hardware components of the large unmanned ground vehicle controlled by software developed in Ada over RTEMS. The attendee will gain from this tutorial a practical application of how Ada can be used in the development of unmanned systems. The attendee should bring a x86 compatible laptop with DVD reader, if possible.