Robot Research Articles

Automated Simulation Encryption Nanodevices

This article implements the method of automated simulation and design of new non-radiating nanoelectronic encryption modules. Currently, cryptographic equipment is practically not protected from electromagnetic attacks and information decryption, as it is created according to outdated complementary metal-oxide-semiconductor microtechnology. To increase the error-free operation of encryption devices, the article uses a system of automated design of nanodevices based on quantum cellular automata using majoritarian principles of their operation. Automated simulation proved that the consuption of the nanodevices developed in the work does not exceed 3,8´10-23 J. Therefore, unmanned aerial vehicles equipped with the nanodevices developed in the article are completely protected from electromagnetic attacks. The results of automated modeling and verification using a computer design system QCADesigne fully confirmed the effectiveness of introducing single-electron nanodevices into encryption devices of unmanned systems. The proposed logic takes advantage of low power consumption quantum-dot cellular automata together with complicated clocking circuits as a paradigm of nanotechnology advances in encryption engineering.

The Evolution of Air Threats in Future Conflicts

Currently, there is an observable trend towards continuous and comprehensive development in both fixed-wing and rotary-wing aircraft design. Furthermore, a dynamic progression has been also witnessed in the evolution of unmanned aerial vehicles, loitering munitions, lethal autonomous weapons systems, ballistic missiles, cruise missiles, hypersonic cruise missiles, lighter-than-air sensor platforms, high altitude pseudo satellites and any others. The development of modern technologies and the acquisition of new materials create opportunities for the modernization of existing air threats as well as the development of novel types. Additionally, the potential of artificial intelligence in unmanned systems is a significant factor that should not be overlooked. The aforementioned circumstances have prompted the author of the article to conduct a thorough examination of contemporary military air threats and to make a forecast regarding the evolution of air threats in future conflicts.

Robotic milling stability optimization based on robot functional redundancy

PurposeCompared with the high stiffness of traditional CNC machine tools, the structural stiffness of industrial robots is usually less than 1 N/µm. Chatter not only affects the quality of robotic milling but also reduces the accuracy of the milling process. The purpose of this paper is to reduce chatter in the robotic machining process.Design/methodology/approachFirst, the mode coupling chatter mechanism is analyzed. Then the milling force model and the principal stiffness model are established. Finally, the robot milling stability optimization method is proposed. The method considered functional redundancies, and a new robot milling stability index is proposed to improve the quality of milling operations.FindingsThe experimental results prove a significant reduction in force fluctuations and surface roughness after using the proposed robotic milling stability optimization method.Originality/valueIn this paper, a new robot milling stability index and a new robot milling stability optimization method are proposed. This method can significantly increase the milling stability and improve the milling quality, which can be widely used in the industry.

History of unmanned aircraft flight controller development

Unmanned aircraft find successful applications across various fields and continue to see increasing demand in numerous sectors. Modern flight control systems empower the creation and programming of unmanned vehicles for a diverse range of tasks.(Research purpose) This study aims to retrospectively analyze the evolution of drone control systems, tracing their development from the early unmanned aerial vehicles to the flight controllers of modern multifunctional drones. (Materials and methods) The study employs the historical-analytical method for data collection and processing. This encompasses a thorough examination of original works by both domestic and foreign authors, including literary references, scientific journal articles, monographs, conference materials, museum exhibitions, photographic archives, and open-access software source code. (Results and discussion) The historical process of unmanned aerial vehicle development has led to the emergence of many types of designs that provide better flight performance and new functions through the creation of flight control systems. Designers integrated worldwide aviation expertise and the latest advancements in science, engineering, and technology to enhance unmanned systems. The miniaturization of flight control systems has facilitated the widespread adoption and application of unmanned aerial vehicle in many domains. The introduction of intelligent flight control modes has ensured a high level of autonomy in drone operations. (Conclusions) In the course of the research into the historical development of control systems for unmanned aerial vehicles, block diagrams illustrating these control systems were created. Additionally, a block diagram was constructed outlining the evolution of these systems, with a periodization of individual stages. The block diagram includes nine stages; with the current emphasis primarily directed towards the advancement of intelligent control systems. The findings confirm that the extensive diversification of unmanned aerial vehicle applications and functionalities is closely linked to the continuous development and enhancement of micro-electromechanical systems technologies. The study identifies the key flight controllers that have significantly influenced the enhancement of unmanned aircraft and have outlined potential directions for the future development of flight controllers.

Triangular Topology Sequence-Based Multi-Target Association for Aerial-Ground Unmanned Systems

The heterogeneous nature of aerial-ground unmanned systems has a considerable advantage in terms of full-area awareness. However, it also presents a great challenge in the multi-target association domain. The almost orthogonal observation view results in large parallax of the aerial-ground sensors large, rendering the trajectory association and visual feature association methods inapplicable. To address this problem, this paper proposes a multi-objective association method based on triangular topology from the relative position relationship of targets. First, the algorithm extracts the distance and azimuth of the target relative to the Unmanned Ground Vehicle based on its position in the sensor and constructs a triangular topology. Then, a bicircle matching model satisfying the triangular topological sequence association constraints is proposed to transform the constrained structure matching problem into an unconstrained one. Finally, an association algorithm based on the similarity association matrix is proposed to complete the association of topologies immediately by obtaining the “optimal path” in the matrix. Simulation experiments show that the correlation accuracy is above 80% when the interference target is less than 20%, and above 90% when the observation error is less than 2.0[Formula: see text]m. The overall performance of this method outperforms similar algorithms in comparative tests.

Adaptive Cooperative Secure Control of Networked Multiple Unmanned Systems under FDI Attacks

With the expanding applications of multiple unmanned systems in various fields, more and more research attention has been paid to their security. The aim is to enhance the anti-interference ability, ensure their reliability and stability, and better serve human society. This article conducts adaptive cooperative secure tracking consensus of networked multiple unmanned systems subjected to false data injection attacks. From a practical perspective, each unmanned system is modeled using high-order unknown nonlinear discrete-time systems. To reduce the communication bandwidth between agents, a quantizer-based codec mechanism is constructed. This quantizer uses a uniform logarithmic quantizer, combining the advantages of both quantizers. Because the transmission information attached with the false data can affect the accuracy of the decoder, a new adaptive law is added to the decoder to overcome this difficulty. A distributed controller is devised in the backstepping framework. Rigorous mathematical analysis shows that our proposed control algorithms ensure that all signals of the resultant systems remain bounded. Finally, simulation examples reveal the practical utility of the theoretical analysis.

An improved multi-state constraint kalman filter based on maximum correntropy criterion

In recent years, the multi-state constraint Kalman filter has been widely used in the visual-inertial navigation of unmanned systems. However, in most previous studies, the measurement noise of the navigation system was assumed to be Gaussian noise, but this is not the case in practice. In this paper, the maximum correntropy criterion is introduced into the multi-state constraint Kalman filter to improve the robustness of the visual-inertial system. First, the new maximum correntropy criterion-based Kalman filter is introduced, it uses the maximum correntropy criterion to replace the minimum mean square error criterion to suppress the interference of measurement outliers on the filtering results, and it has no numerical problem in the presence of large measurements outliers. Then, an improved multi-state constraint Kalman filter is designed by applying the new maximum correntropy criterion-based Kalman filter to the multi-state constraint Kalman filter, which improved the robustness of the multi-state constraint Kalman filter. The results of numerical simulation and dataset experiments show that the proposed filter improves the accuracy and robustness of the visual-inertial system.

Posture Optimization in Robot Machining with Kinematic Redundancy for High-Precision Positioning

Vertically articulated industrial robots are suitable for machining purposes owing to their advantages over multi-axis machine tools, such as larger workspace, easier installation, and lower cost. However, the rigidity and positioning accuracy of industrial robots are inferior to those of machine tools, which renders it difficult to maintain the robot posture required for machining operations. This study focuses on improving the accuracy of robot machining based on posture optimization by exploiting the kinematic redundancy of a six-axis vertically articulated robot. To decrease positioning errors caused by static and dynamic external forces during machining, this study proposes a path generation method for a redundant joint that simultaneously considers the static and dynamic rigidity of the machining robot. The relationships between the static and dynamic mechanical characteristics of the machining robot and the redundant angle are illustrated using two maps: a static stiffness map and a natural frequency map. Using these two maps in the proposed path generation method, the redundant angle that can be selected for the robot posture with arbitrary mechanical characteristics is selected. Experimental results confirm that the proposed path generation method can control the priority of reducing static positioning error and vibration amplitude by changing the weight coefficients. In addition, the proposed method can improve positioning accuracy compared with conventional trajectory generation methods for redundant robots.

Reinforcement Learning-Based Low-Altitude Path Planning for UAS Swarm in Diverse Threat Environments

Unmanned aircraft systems (UASs) with autonomous maneuvering decision capabilities are expected to play a key role in future unmanned systems applications. While reinforcement learning has proven successful in solving UAS path planning problems in simple urban environments, it remains under-researched for some complex mountain environments. In this paper, the path planning of UAS swarm for the low-altitude rapid traverse in diverse environments is studied when facing the threats of complex terrain, radars and swarm failure. First, a UAS swarm radar detection probability is built up for evaluating the radar detection threat by a networked radar system, where the detection probability of a UAS swarm is equated to a single UAS with appropriate position and radar cross section named as the swarm virtual leader. Second, a reinforcement learning based path planning method is proposed to seek the optimal path for the swarm virtual leader which balances instantaneous reward, including detection probability and path constraints with terminal reward, including normal rate. Third, a formation optimization strategy is designed to further reduce the threat of radar detection through dynamically adjusting the formation geometry. Final, simulations in the complex environment have been carried out to evaluate the performance of the proposed method, where the path quality, task success rate and normal rate are counted as the performance indicators.

Preface

It is our pleasure to introduce you the Proceedings of 2023 7th International Conference on Robotics and Machine Vision (ICRMV 2023). Interest in robotics and machine vision have remarkably increased in recent years. The extensive illustrations and the consistently succinct yet insightful papers reflect all the authors’ depth and rigor as researchers in these fields. The major emphasis of this proceeding is on robotics and machine vision, provides a very useful instructional tool to the readers who are still in studies.The volume includes 8 selected papers which were submitted to the conference from universities, research institutes and industries. Each contributed paper was rigorously peer-reviewed by reviewers who were drawn from a large pool of technical committee members as well as other international reviewers in related fields. We believe that the proceeding has met its goal of providing reference in researching on conference themes.The objective of ICRMV 2023 has always been bringing together a group of researchers, scientists, academics, and engineers in the area of robot systems and applications from all over the world, who share much more than technical interests, among other things, culture and history. It provides a high-standard international forum for R&D exchanges in various fields of robotics and machine vision.As the coronavirus (COVID-19) spreads worldwide, taking into account the various circumstances of the participant, ICRMV adopts all available social media methods, we arrange different parallel sessions in the afternoon to provide participants an opportunity to share their knowledge with each other online, the themes include robot design and machine vision.We truly believe the participants will find the discussion fruitful, and will enjoy the opportunity for setting up future collaborations. It is our sincere hope that ICRMV will one day become the leading conference in this specific academic area.And we also believe that the proceeding has met its goal of providing reference in researching on robot design and machine vision. Look forward to meeting all of you again next year face to face on conference.With our warmest regards,ICRMV 2023 Conference CommitteeList of Committees, Statement of Peer Review are avilable in this pdf.

Preface

2023 2nd International Symposium on Intelligent Unmanned Systems and Artificial Intelligence (SIUSAI 2023) was held in Shenzhen, China, on April 21-23, 2023.It aims to bring scientists, researchers, practitioners and industry delegates from academia and industry together to exchange and share their latest research and experiences in the field of Unmanned Systems and Artificial Intelligence. The conference is expected to provide opportunities for advances and collaborations in this field.SIUSAI 2023 is organized by Southwest University of Science and Technology School of Computer Science and Technology, Southwest University of Science and Technology School of Manufacturing Science and Engineering, co-organized by Hohai University, Key Laboratory of Testing for Manufacturing Process, Ministry of Education, Southwest University of Science and Technology, Sichuan Big Data and Intelligent System Engineering Technology Research Center, The International Association of Electrical, Electronic and Energy Engineering (IAEEEE), and supported by CoreShare Academy Exchange Center.The conference contained one day of registration and two full-days program consisting of keynote lectures, oral presentations, video presentations and poster presentations. We would like to express our sincere gratitude to our keynote speakers Pro. Huiyu Zhou from University of Leicester and Prof. Saleh Mobayen from University of Zanjan who shared their newest and outstanding research achievements at the conference.After a couple of months well preparation and hard work, the conference has been held successfully and the proceeding of the 2023 International Symposium on Intelligent Unmanned Systems and Artificial Intelligence (SIUSAI 2023) will be smoothly published soon.On behalf of the conference organizing committee, we would like to show our congratulation and sincere gratitude to all authors, peer reviewers, speakers, oral, Video and poster presenters and listeners. We deeply appreciate their efforts in making the conference an impressive success.List of Committee Members is available in this pdf.

Coordinated Trajectory Planning for Multiple Autonomous Underwater Vehicles: A Parallel Grey Wolf Optimizer

The utilization of unmanned systems has witnessed a steady surge in popularity owing to its tremendous potential for a wide range of applications. In particular, the coordination among multiple vehicle systems has been demonstrated to possess unparalleled efficacy in accomplishing intricate and diverse tasks. In light of this, the present paper delves into the coordinated path planning mission that is accomplished by collaborative efforts amongst multiple Autonomous Underwater Vehicles (AUVs). First, considering the potential threats, arrival time windows, space, and physical constraints for the AUVs, a sophisticated coordinated path planning model is formulated in a 3D environment, serving as a systematic and structured blueprint for the underlying mechanism. Subsequently, the optimization problem is addressed through the incorporation of a restricted initialization scheme and a multi-objective clustering strategy in the proposed methodology. The resulting approach leads to the development of the Parallel Grey Wolf Optimizer (P-GWO) which exhibits strong global searching abilities and a rapid convergence rate, rendering it a dependable and effective solution. The results demonstrate a 10–15% improvement in convergence rate and a reduction of over 60% in the average cost value compared to reliable references, thus presenting an effective solution for underwater missions with specific requirements.

국내 관광·레저 시설의 사고 발생 특징 분석

The purpose of this study is to analyze the current status and change trends of tourism·leisure facilities in South Korea, and to identify factors (types and causes) of accidents in each facility by collecting accident cases (from 2011 to 2023) and conducting chi-square test. As a result, the tourism and leisure facilities have rapidly increased throughout the country within the last 10 years. Some facilities have become deteriorated, operated in unmanned systems, longer and higher, and more unique and combined. In tramway facilities (cableway, monorail), stationary facility mainly occurred due to mechanical defects compared with other facilities. In landscape facilities (pedestrian suspension bridge, sky-walk), fall accidents mostly caused by individual negligence and operating system problem. Finally, in adventure facilities (zip-line), collision (including rear-end) accidents significantly resulted from mechanical and operating system factors. Therefore, it should be required more intensive safety management for accident prevention of tourism and leisure by improving legal and institution, and developing safety education and training programs.

РЕЗОНАНСНА СИСТЕМА БЕЗДРОТОВОЇ ПЕРЕДАЧІ ЕНЕРГІЇ З ВИКОРИСТАННЯМ ЕЛЕКТРИЧНОГО ПОЛЯ

The paper reviews the existing types of wireless technologies for power transmission using electromagnetic interaction. According to the type of interaction, systems using magnetic, electric and electromagnetic components are distinguished. Short-range, medium-range and long-range systems are distinguished by range. As promising for implementation in future unmanned systems, the work considers a modified system of wireless transmission of electrical energy using an electric field. The scheme is presented and the principle of operation of such a system is considered. The characteristics of resonant circuits used as emitters and receivers in such a system were studied. The results of measuring the parameters of the spatial distribution of the electric field of the resonators are presented. The interaction of the spectral components of the input signal and the resonant characteristics of the radiating circuits was investigated. The paper presents the method of determining the efficiency of electric energy transmission at high frequencies and the results of measurement of transmission efficiency for the studied type of systems. It was concluded that there is an active factor in the form of an alternating electric field, the feature of which propagation allows creating a device suitable for powering unmanned mobile systems of low and medium power. References 11, figures 4, tables 2.

Cooperative Decisions of a Multi-Agent System for the Target-Pursuit Problem in Manned–Unmanned Environment

With the development of intelligent technology, multi-agent systems have been widely applied in military and civilian fields. Compared to a single platform, multi-agent systems can complete more dangerous, difficult, and heavy tasks. However, due to the limited autonomy of unmanned platforms and the regulatory needs of personnel, multi-agent systems cooperating with manned platforms to perform tasks have been more widely promoted at this stage of development. This paper addresses a differential game method for cooperative decision-making of a multi-agent system cooperating with the manned platform for the target-pursuit problem. The manned platform pursues the target according to a certain trajectory, and its state can be obtained by the multi-agent system. Firstly, for the case that the target moves with a fixed trajectory, the target-pursuit problem in a manned–unmanned environment is viewed in the form of game based on a communication graph among agents. Secondly, strategies of all agents are proposed while maintaining their group cohesion. A set of coupled differential equations is solved to implement strategy calculation. Compared to purely unmanned systems, the strategies combine the advantages of the manned platform and add a reference item, which can achieve team cohesion relatively quickly. Furthermore, a brief analysis is made on the scenarios where the target is in another case or adopts other strategies. Finally, comparative simulations have verified the effectiveness and synergy of the strategy.

Towards region-based robotic machining system from perspective of intelligent manufacturing: A technology framework with case study

The region-based robotic machining system is mainly used for repair and remanufacturing of the complex components with local defects. Taking the automotive body manufacturing as an example, the resistance spot welding process is highly prone to randomly distributed and tiny-sized welding slag splashes, which poses a great challenge to the locally automated removal of the welding slag defects. In this paper, we construct a region-based robotic machining system that integrates the processes of defect detection, defect region division and positioning, and machining path decision-making, aiming to enhance the automation of locally grinding of automotive body welding slags. Both the framework of the system and the implementation process are proposed. In the framework, the improved YOLO v3 algorithm is put forward to accurately detect the automotive body welding slags by virtue of the machine vision and deep learning. Based on this, the K-means algorithm is used to divide the welding slags into the regions, so that the problem of positioning individual welding slag is transformed into the problem of positioning the boundary points of welding slag region. The binocular image-based region boundary points matching is then presented to accurately locate the welding slag regions accordingly. The Dijkstra algorithm is finally employed to make an autonomous decision on the pre-planned grinding path of automotive body welding slags based on the positioning results. The experiments on a case of locally robotic grinding of the welding slags on an automotive door frame are implemented to verify the effectiveness and practicality of the system. This study provides a valuable reference for the locally automated repair of automotive body welding slag defects, putty defects, paint defects, etc.

Dynamic performance of industrial robots in the secondary carbon fiber-reinforced plastics machining

Carbon fiber-reinforced plastics (CFRPs) find many applications given their superior properties. These materials are usually formed using a near-net-shape method that requires secondary machining, such as drilling and trimming, after molding. Industrial robots are becoming increasingly popular machining tools in industries exhibiting high demand for CFRPs. However, it remains challenging to achieve high dimensional accuracy when using such robots and dynamic performance is poor. We experimentally investigated the dynamic properties of the tool tip according to the dominant robot posture during CFRP secondary machining. Based on the results, multi-layer perceptron models were developed to predict the dominant natural frequency and dynamic stiffness of the tool tip. The minimum and maximum mean absolute percentage errors were 1.99 and 7.94, respectively; the error changed markedly with robot posture. Our models improved CFRP robotic machinability. Experimentally, the delamination rates of drilled holes decreased by 15 % and 75 % in terms of length and area, respectively, and the trimmed surface roughness improved by 27 %.

Imitation Learning through Image Augmentation Using Enhanced Swin Transformer Model in Remote Sensing

In unmanned systems, remote sensing is an approach that collects and analyzes data such as visual images, infrared thermal images, and LiDAR sensor data from a distance using a system that operates without human intervention. Recent advancements in deep learning enable the direct mapping of input images in remote sensing to desired outputs, making it possible to learn through imitation learning and for unmanned systems to learn by collecting and analyzing those images. In the case of autonomous cars, raw high-dimensional data are collected using sensors, which are mapped to the values of steering and throttle through a deep learning network to train imitation learning. Therefore, by imitation learning, the unmanned systems observe expert demonstrations and learn expert policies, even in complex environments. However, in imitation learning, collecting and analyzing a large number of images from the game environment incurs time and costs. Training with a limited dataset leads to a lack of understanding of the environment. There are some augmentation approaches that have the limitation of increasing the dataset because of considering only the locations of objects visited and estimated. Therefore, it is required to consider the diverse kinds of the location of objects not visited to solve the limitation. This paper proposes an enhanced model to augment the number of training images comprising a Preprocessor, an enhanced Swin Transformer model, and an Action model. Using the original network structure of the Swin Transformer model for image augmentation in imitation learning is challenging. Therefore, the internal structure of the Swin Transformer model is enhanced, and the Preprocessor and Action model are combined to augment training images. The proposed method was verified through an experimental process by learning from expert demonstrations and augmented images, which reduced the total loss from 1.24068 to 0.41616. Compared to expert demonstrations, the accuracy was approximately 86.4%, and the proposed method achieved 920 points and 1200 points more than the comparison model to verify generalization.

The Group Interaction Field for Learning and Explaining Pedestrian Anticipation

Anticipating others’ actions is innate and essential in order for humans to navigate and interact well with others in dense crowds. This ability is urgently required for unmanned systems such as service robots and self-driving cars. However, existing solutions struggle to predict pedestrian anticipation accurately, because the influence of group-related social behaviors has not been well considered. While group relationships and group interactions are ubiquitous and significantly influence pedestrian anticipation, their influence is diverse and subtle, making it difficult to explicitly quantify. Here, we propose the group interaction field (GIF), a novel group-aware representation that quantifies pedestrian anticipation into a probability field of pedestrians’ future locations and attention orientations. An end-to-end neural network, GIFNet, is tailored to estimate the GIF from explicit multidimensional observations. GIFNet quantifies the influence of group behaviors by formulating a group interaction graph with propagation and graph attention that is adaptive to the group size and dynamic interaction states. The experimental results show that the GIF effectively represents the change in pedestrians’ anticipation under the prominent impact of group behaviors and accurately predicts pedestrians’ future states. Moreover, the GIF contributes to explaining various predictions of pedestrians’ behavior in different social states. The proposed GIF will eventually be able to allow unmanned systems to work in a human-like manner and comply with social norms, thereby promoting harmonious human–machine relationships.

Towards evaluation of the PID criteria based UAVs observation and tracking head within resizable selection by COA algorithm

The study of unmanned systems has garnered significant academic attention worldwide. The advancements in tracking technologies, particularly the unmanned aerial vehicle (UAV) developed by the US Air Force, have motivated scientists to extensively explore this field due to the abundance of available aerial resources. However, the UAV’s effectiveness in motion is influenced by its three fundamental motions: pitch, roll, and yaw. To address this, scientists have been developing optimization algorithms and models to enhance the UAV’s performance. Nonetheless, in practical scenarios, each motion requires specific measurements, and their relative importance varies. This presents several challenges, including the existence of multiple criteria for selecting optimization values, determining the criteria’s significance, and evaluating trade-offs between performance across different optimization cases. Consequently, the selection and evaluation of UAV motion control algorithms becomes complex. This study proposes a novel selection process that employs the cuckoo optimization algorithm (COA) and real measured resizable margins for goal detection instead of traditional fixed-size evaluation criteria. The framework consists of enhancing PID motion gains using the COA algorithm, focusing on altitude and attitude functional PID controllers. The results of the selection process demonstrate the significance of various criteria for different motions. Rigorous evaluation and analysis were conducted to validate the proposed research framework.