Level Of Automation Research Articles

Iterative Function Allocation of Single Pilot Operations Based on Biclustering Method

The successful transition from a two-pilot to a single-pilot mode cannot solely rely on simply augmenting advanced automation in the cockpit. The degree of support provided by functions at different levels of automation varies, and introducing new functions simultaneously brings new demands for the single pilot, leading to imbalanced workload. To address these shortcomings and enhance the rationality of function allocation under workload constraints, this paper introduces an iterative function allocation method. Initially, the functions are categorized and classified into different levels of automation to obtain the initial function allocation scheme. Subsequently, a novel bicluster mining algorithm called K-Miner is proposed to identify elements requiring iterative design. As a case study, the multitask surface scenario in SPO is considered. By applying the proposed iterative design method, the task performance of the single pilot is improved, the workload of the single pilot is effectively reduced, and situational awareness is improved to a certain extent.

An overview of machine learning applications in elastic power systems

Abstract. With the development of economy and the access of renewable energy, the power system is facing new challenges. Machine learning provides a new way for the intelligent management of power system through big data analysis, pattern recognition and predictive modeling. This paper reviews the application of machine learning technology in elastic power system, including load forecasting, transient stability assessment, intelligent scheduling and fault diagnosis. Machine learning will better improve the stability, reliability and economic benefit of the system. Future research will focus on algorithm optimization, model adaptability improvement and integration with traditional power system knowledge to promote the development of power system to a higher level of intelligence and automation.

Assessing energy consumption in scalable semi-autonomous destination-based E-platoons: A multiplayer approach

Recent developments in connected and automated vehicle technologies have opened up new possibilities but also posed enduring challenges. One of the primary challenges is the efficient coordination of vehicles in urban environments, specifically through scalable and destination-based platooning. While considerable research has focused on platooning with a limited number of vehicles demonstrating seamless connectivity and coordination on highways, there remains a significant gap in understanding and implementing scalable platoons in more dynamic urban settings. This paper bridges these gaps by developing a novel extension to the 3DCoAutosim simulation platform. Our model introduces ’Scalable Semi-autonomous Destination-based Multiplayer E-Platoons’, accommodating different automation levels and simulation characteristics of vehicles in five distinct platoons. We employed seven electric vehicles to create these platoons, each consisting of an autonomous lead vehicle, followers that are either autonomous or semi-autonomous (accompanied by drivers), customised according to the specific requirements of each platoon. Utilising Time Series Analysis, Multiple Linear Regression and a comprehensive, comparative scenario-based analysis, we assessed and validated our developed model’s impact on battery energy consumption under varying road slopes and car-following models. Our assessment employs real-world trip data from Upper Austria, with results indicating a potential reduction in total battery energy consumption when operating in platoon mode.

Transforming science labs into automated factories of discovery.

Laboratories in chemistry, biochemistry, and materials science are at the leading edge of technology, discovering molecules and materials to unlock capabilities in energy, catalysis, biotechnology, sustainability, electronics, and more. Yet, most modern laboratories resemble factories from generations past, with a large reliance on humans manually performing synthesis and characterization tasks. Robotics and automation can enable scientific experiments to be conducted faster, more safely, more accurately, and with greater reproducibility, allowing scientists to tackle large societal problems in domains such as health and energy on a shorter timescale. We define five levels of laboratory automation, from laboratory assistance to full automation. We also introduce robotics research challenges that arise when increasing levels of automation and when increasing the generality of tasks within the laboratory. Robots are poised to transform science labs into automated factories of discovery that accelerate scientific progress.

Safety evaluation for mixed traffic flow of CAVs with different automation and connection levels

With the development of connected communication and automated driving technologies, connected automated vehicles (CAVs) are expected to gradually replace human-driven vehicles (HDVs), owing to their significant safety advantages. However, widespread adoption of CAVs will still require a considerable amount of time due to constraints such as technological development, legal regulations, and social acceptance. During the transitional period of CAVs’ proliferation, road traffic will comprise vehicles with different levels of connection and automation. These vehicles will differ in technology regarding communication, perception, decision-making, and other aspects, potentially posing severe challenges to mixed traffic flow safety. To address this issue, this paper proposes a mixed traffic flow model from both automation and connection perspectives to consider time delay and communication degradation. Four safety evaluation metrics are employed, and three-speed scenarios are set to investigate the influence of connection levels, automation levels, and their combined effects on mixed traffic flow safety. The result shows that (1) low automation enhances traffic safety in a non-connected environment, whereas medium and high automation decreases traffic safety. Conversely, in a connected environment, the role of automation levels exhibits the opposite pattern. (2) non-connected vehicles enhance traffic safety in a low-automated environment, while connected vehicles diminish it. However, connection level effects are reversed in medium and highly automated environments. (3) In connected and automated environments, traffic safety is increased by non-connected and low-automated vehicles, connected and medium automated vehicles, and connected and highly automated vehicles. However, other vehicle configurations decrease traffic safety. (4) Across various scenarios, the integration of connection and high automation proves beneficial for reducing traffic collision risks and improving traffic safety. In summary, this study provides theoretical support for managing and controlling mixed traffic flow with different automation and connection levels in the future.

Human factors considerations of Interaction between wearers and intelligent lower-limb prostheses: a prospective discussion.

Compared to traditional lower-limb prostheses (LLPs), intelligent LLPs are more versatile devices with emerging technologies, such as microcontrollers and user-controlled interfaces (UCIs). As emerging technologies allow a higher level of automation and more involvement from wearers in the LLP setting adjustments, the previous framework established to study human factors elements that affect wearer-LLP interaction may not be sufficient to understand the new elements (e.g., transparency) and dynamics in this interaction. In addition, the increased complexity of interaction amplifies the limitations of the traditional evaluation approaches of wearer-LLP interaction. Therefore, to ensure wearer acceptance and adoption, from a human factors perspective, we propose a new framework to introduce elements and usability requirements for the wearer-LLP interaction. This paper organizes human factors elements that appear with the development of intelligent LLP technologies into three aspects: wearer, device, and task by using a classic model of the human-machine systems. By adopting Nielsen's five usability requirements, we introduce learnability, efficiency, memorability, use error, and satisfaction into the evaluation of wearer-LLP interaction. We identify two types of wearer-LLP interaction. The first type, direct interaction, occurs when the wearer continuously interacts with the intelligent LLP (primarily when the LLP is in action); the second type, indirect interaction, occurs when the wearer initiates communication with the LLP usually through a UCI to address the current or foreseeable challenges. For each type of interaction, we highlight new elements, such as device transparency and prior knowledge of the wearer with the UCI. In addition, we redefine the usability goals of two types of wearer-LLP interaction with Nelson's five usability requirements and review methods to evaluate the interaction. Researchers and designers for intelligent LLPs should consider the new device elements that may additionally influence wearers' acceptance and the need to interpret findings within the constraints of the specific wearer and task characteristics. The proposed framework can also be used to organize literature and identify gaps for future directions. By adopting the holistic usability requirements, findings across empirical studies can be more comparable. At the end of this paper, we discuss research trends and future directions in the human factors design of intelligent LLPs.

Methodology to Generate Strategic Manufacturing Indicators to Support Decision-Making – Case Study of a Food Company

This study proposes a methodology that selects key performance indicators and measures their influence on the strategic manufacturing objectives of a food company. The proposed hybrid methodology used the focus model centered on a value function to select criteria and classify key performance indicators and the multi-criteria model DEMATEL to identify the level of influence of key performance indicators on strategic manufacturing objectives. This new method constructs a value function with input from all production line members. This allows the degree of direct and indirect influence of selected key performance indicators to be measured to achieve the organization’s strategic objectives. Finally, seven key performance indicators were selected, the most influential being the level of automation, performance, set-up times, and resource use.

AI-Powered Information Governance: Balancing Automation and Human Oversight for Optimal Organization Productivity

This study employs a mixed-methods approach to examine the optimal balance between AI-powered automation and human oversight in information governance frameworks, aiming to enhance organizational productivity, efficiency, and compliance. Quantitative data collected from 384 respondents were analyzed using Pearson correlation, regression models, and Structural Equation Modeling (SEM). The results reveal strong positive correlations between AI automation levels and both organization size (r = 0.55, p < .01) and AI adoption duration (r = 0.62, p < .01). Regression analysis indicates that higher levels of AI automation significantly improve error reduction (β = 1.12, p < .001) and compliance (β = 1.05, p < .001), especially in larger organizations with longer AI adoption periods. SEM findings highlight that human oversight positively impacts error reduction (β = 0.65, p < .001) and compliance improvement (β = 0.72, p < .001), and the interaction between human oversight and AI automation further enhances these outcomes (error reduction: β = 0.32, p < .001; compliance improvement: β = 0.35, p < .001). The qualitative analysis, involving thematic extraction from industry reports, reveals ethical challenges such as data quality issues, algorithmic bias, and privacy concerns. Hence, it is necessary to integrate human oversight to ensure ethical standards and build stakeholder trust in AI-driven systems. The study concludes with practical recommendations for organizations: establishing transparent AI governance frameworks, investing in continuous training for employees, and regularly auditing AI processes to mitigate risks. By addressing both the technological and ethical dimensions, organizations can implement AI-powered information governance that not only boosts productivity and efficiency but also ensures compliance and ethical integrity.

From data silos to seamless integration and coordination: a data-asset centric approach to smart hospital facility management

PurposeExisting hospital building operations involve numerous information technology applications and complex building systems; therefore, an intelligent facility management (FM) platform is required to ensure their continuous operation. To address the persistent issues of data silos, inefficient data interoperability, and workflow incoordination that have been identified in the current body of FM practice and literature, the present study develops a data-asset (DA) centric FM platform specifically designed for hospital buildings.Design/methodology/approachThis study proposes a semi-customized approach to develop the DA-centric FM platform for hospital buildings. To elucidate the precise function requirements of the hospital FM platform, focus group interviews are employed. By seamlessly integrating the as-built BIM model, IoT sensor data and FM workflow data, the BIM-based DA model with a data transfer mechanism is developed. The development of the FM platform with function modules in a case study is guided by a five-tier architecture and the coordination theory (CT). The case study provides an in-depth introduction to the applications of DA management, space management and maintenance management modules.FindingsThe capabilities of the developed DA-centric hospital FM platform are validated through the case application and user satisfaction survey, which assess data quality, automation level, operation efficiency, flexibility and functionality. For hospital FM activities, this DA-centric FM platform realizes data integration and seamless transformation, optimizes workflow coordination and enhances operation performance.Originality/valueThe initial scholarly contribution is the establishment of the BIM-based DA model, which serves as the data middle platform for continuous data integration, transmission and sharing within the FM platform. Subsequently, under the guidance of the CT, the business process of function modules is designed, improving the intra-module and inter-module workflow coordination. The developed DA-centric FM system along with its performance benchmarking application, assists facility managers and decision-makers in implementing smart operations for hospital buildings and achieving the management goals of safety, efficiency, energy savings and convenience.

Управление логистическими процессами в трансграничной электронной коммерции

In the context of the globalization of the economy and the development of cross-border e-commerce, the importance of cross-border logistics is increasing, allowing for an effective process of product distribution. The issues of organizing transport and logistics processes during the delivery of goods within the framework of the functioning of cross-border e-commerce are discussed. The main aspects of the development of e-commerce logistics and its impact on the trading business have been studied. An analysis of the cross-border e-commerce market in Russia is carried out. It is noted that currently the global logistics industry is in an unstable environment. The main directions and trends in the development of logistics services in modern conditions are considered and the specifics of adapting the process of goods distribution within the framework of cross-border e-commerce to changes in the external environment are investigated. The distinctive features of e-commerce logistics have been studied in the context of its impact on the trading business, which allows for increased efficiency of logistics processes such as procurement, transportation, order processing, inventory and warehouse management, packaging and labeling. It has been proven that with the development of information technology and telecommunication networks, as well as increasing demand in the field of online trading, the need for effective logistics support is significantly increasing, and delivery speed is becoming increasingly important to provide quality service to consumers. The advantages of e-commerce are substantiated from the perspective of subjects of trade and logistics activities, which include the global nature of customer coverage and the convenience of inter-subject interaction, reduction of operating costs of trade and logistics activities, expanded opportunities for marketing and advertising support, increased level of automation of e-commerce logistics management processes.

Automatic Assist Level Adjustment Function of a Gait Exercise Rehabilitation Robot with Functional Electrical Stimulation for Spinal Cord Injury: Insights from Clinical Trials.

This study aimed to identify whether the combined use of functional electrical stimulation (FES) reduces the motor torque of a gait exercise rehabilitation robot in spinal cord injury (SCI) and to verify the effectiveness of the developed automatic assist level adjustment in people with paraplegia. Acute and chronic SCI patients (1 case each) performed 10 min of gait exercises with and without FES using a rehabilitation robot. Reinforcement learning was used to adjust the assist level automatically. The maximum torque values and assist levels for each of the ten walking cycles when walking became steady were averaged and compared with and without FES. The motor's output torque and the assist level were measured as outcomes. The assist level adjustment allowed both the motor torque and assist level to decrease gradually to a steady state. The motor torque and the assist levels were significantly lower with the FES than without the FES under steady conditions in both cases. No adverse events were reported. The combined use of FES attenuated the motor torque of a gait exercise rehabilitation robot for SCI. Automatic assistive level adjustment is also useful for spinal cord injuries.

The results of research on technological indicators in the experimental module for growing broiler chickens

Russia ranks fifth in the world in poultry meat production. In the period from 2010 to 2021, the volume of production of this type of product increased by 1.77 times, which in physical terms is 2,190 thousand tons. The largest volume of poultry meat production, 89.7%, falls on the meat of broiler chickens. This indicator is justified by consumer preferences of the retail market, a low feed conversion rate, a high level of automation of production processes, as well as the possibility of up to 8 production cycles per year. The main share, amounting to 93%, of broiler chicken meat production is accounted for by large agricultural enterprises. Households of the population and peasant farms account for 7% of production. This result is observed due to the lack of technical and technological solutions for small-scale production, providing for the use of automation of production processes, which leads to a decrease in productivity and an increase in poultry mortality. The combination of these factors increases the cost of finished products, making small-scale production uncompetitive. To solve this problem, a project has been developed and a prototype of a technological module for fattening broiler chickens has been manufactured. The production capacity of the module is 2,800 broiler chickens per year. The module uses a cellular method of keeping poultry on a mesh flooring. As a result of the conducted studies, the feed conversion rate was 1.66, the cost of water was 3.4 liters, electricity was 3.22 kWh and labor was 0.051 people per kilogram of live weight. The obtained indicators are comparable with those of large poultry farms, which allows us to conclude that it is advisable to use technological modules at small poultry enterprises.

Magnetic Railway Sleeper Detector

In an ever expanding railway network all around the world, the need for track maintenance grows steadily. Traditionally, one major part of track maintenance is ramming large vibrating steel picks into the gravel between and under railway sleepers to compress the gravel and generate a safe substructure. Even today, maintenance personnel still have to manually locate the sleepers if they cannot be detected by computer vision systems or visually by the operator. Here we developed a first of its kind magnetic sleeper detector, even able to find sleepers, buried in gravel, undetectable by vision based systems. Our approach of magnetic detection is based on a DC magnetic field excitation and a detector moving with respect to the rail system, including the sleepers and fasteners for mounting the rails. Due to railway application constraints a large air gap between the sensor and the sleeper structure is required, which significantly complicates the magnetic sensing task for robust sleeper detection. The design and optimization of the magnetic circuit was based on extensive 3D simulation studies to ensure highest possible variation in magnetic flux density at the sensor locations for absence and presence of a sleeper. Furthermore, a low noise and high sensitivity electronic circuit has been realized to cope with sensor signal offsets from unknown or changing sensor orientations with respect to the earth’s magnetic field, or magnetic interferences from other trains potentially passing by during active measurements. Since we only want to detect sleepers in close vicinity of the moving sensor system, digital signal processing of the acquired signals can easily compensate for disturbing slowly changing or static field components within real world application scenarios. We demonstrate that magnetic detection of even buried sleepers on railway tracks is possible for distances of up to 172 mm between the sensor and the sleeper. This enables an even higher level of railway maintenance automation previously impossible in certain scenarios.

Towards sustainable high-speed cruising: Optimizing energy efficiency of plug-in hybrid electric vehicle via intelligent pulse-and-glide strategy

Conventional pulse-and-glide (PnG) strategies expose issues including poor coordination with energy management systems (EMSs), discomfort and low levels of automation, this paper innovatively addresses these challenges by the comprehensive considerations of energy economy, dynamic performance, and ride comfort, proposing an intelligent pulse-and-glide (I-PnG) strategy tailored for plug-in hybrid electric vehicle (PHEV) configurations. The I-PnG strategy is aimed at optimizing economic cruising in high-speed scenarios; however, it demonstrates applicability across diverse conditions without deterioration in performance. I-PnG is a data-driven autonomous driving solution developed through a deep Q network (DQN), featuring two distinct modes: ECO and SPORT, the former prioritizes energy economy, while the latter emphasizes dynamic performance enhancement. The results indicate that our proposed strategy significantly optimizes energy management compared to the baseline methods. Specifically, during variable-speed cruising, I-PnG ECO achieves a maximum energy efficiency improvement of 16.13 % and a cost reduction of 7.74 %, while I-PnG SPORT exhibits a maximum energy efficiency improvement of 13.37 % and a cost reduction of 3.92 %. Under the Highway Fuel Economy Test (HWFET), I-PnG ECO and I-PnG SPORT further improve energy efficiency by up to 22.94 % and 19.04 %, respectively, with corresponding cost savings of 18.47 % and 13.35 %.

Over-the-air upgrading for enhancing security of intelligent connected vehicles: a survey

The continuous improvement in the connectivity, automation and autonomy levels of Intelligent Connected Vehicles (ICVs) significantly increases the probability of potential security threats. Over-the-Air (OTA) is a promising technique for upgrading features of ICVs and enhancing their reliability and security against environmental disturbances as well as malicious attacks. To better understand the potential security risks and possible countermeasures, we survey research works in ICV security during OTA from cloud upgrade, terminal upgrade, and object upgrade. We also summarize existing methods in OTA upgrading techniques and systematically investigate the overall framework of OTA upgrading methods from the perspectives of Software-Over-the-Air (SOTA) and Firmware-Over-the-Air (FOTA).We further discuss possible mitigation strategies and open issues yet to be resolved in this research direction. This survey shows that OTA provides a powerful technique for upgrading the ICV features and improving ICV security.

A Comprehensive Analysis of Maritime Cyber Security Incidents: Trends, Impacts, and Countermeasures

The maritime industry is currently experiencing a process of digital transformation, which involves a significant level of automation and enhanced communication with external networks. As a result, various facilities in the maritime sector such as commercial and navy vessels, shipping companies, ports, and shipbuilders, are becoming more susceptible to cyber threats. In addition to the potential economic and reputational harm to shipping companies, a cyber-attack on maritime systems could result in significant incidents such as the release of hazardous substances, collisions, grounding, and fires. This poses significant risks to both ship crew, ship, cargo, and environment. This study examines cyber security events in the maritime sector. The main objective is to cultivate a thorough comprehension of cyber-attacks that specifically target systems in maritime facilities, by analyzing insights derived from incidents in the Maritime Cyber-Attack Database. The work involves the construction and examination of a number of cyber security incidents. An inquiry is carried out to determine the time patterns, geographical spread, sector-specific consequences, and attributes of these cyber-attacks, including the identity of the perpetrator, intention (whether deliberate or unintentional), and the affected systems inside the maritime domain. The paper examines particular instances to identify the main stages of a cyber-attack on maritime facilities' systems, the fundamental strategies employed by attackers, and proposes standard cyber security solutions to reduce these risks. The study's contribution entails the methodical delineation of the cyber security terrain that is unique to the maritime industry.

Risk Assessment for Inland Vessels with Various Levels of Automation: a Hazard Identification Study

Abstract The future viability of inland navigation is closely linked to the automation of inland vessels. This will make their use more attractive and efficient. Potential solutions for automation in the scope of this paper include remotely controlled inland vessels that do not require a boatmaster to be on board but are controlled from shore. The implementation of such new technologies involves unknown risks. It is therefore necessary to assess the safety and classify the risks associated with inland vessels of varying degrees of automation. To identify these risks, a Hazard Identification (HAZID) study has been conducted. The outcomes of the study may serve as a basis for adapting regulations and introducing novel technologies, which would facilitate increased automation of inland navigation

A Conceptual Model for Automation of Small Ports

Abstract For large ports and terminals, the loading and discharge operations have to a great extent been automated already. However, for the vast number of small ports, for instance all Norwegian ports, this large-scale automation is not possible due to the small size of the ports compared to the cost of introducing full automation. Still, these small ports are important logistics hubs in the transport system. They facilitate the shift from congested roads to the sea by allowing the goods to arrive closer to the final destination by using smaller, possibly autonomous, vessels. However, this puts pressure on the ports to facilitate reduced laytime in the port, to increase the port efficiency and to improve interoperability towards hinterland systems and terminals. For small ports, this means that manual and automated work processes need to exist side by side, and that it will be important to get an overview of which processes to automate and which will remain manual, in addition to the handling of the hand-over between humans and automation. This paper describes a conceptual model that can be used by small ports as a starting point on their way to introduce automation of their services supporting the cargo flow through the port. The model includes a description of port functions, tasks and responsibilities and use the concept of operational envelope to define the overall capabilities of the system, including both automation and human. This will be the starting point for how to structure the description of an operation centre that monitor and control the maritime terminal operations. The starting point for this work is a use case analysis performed in some small ports in Norway, and their need to optimize the utilization of their assets. The work is done as part of the AutoPort project which is a research project funded by the Norwegian Research Council (project number 337211). The goal of this work is to describe a methodology on how to identify the interface between automation and human operators when it comes to small ports and the movement of cargo through its terminals, and by this give a description on how different levels of automation can be implemented. The methodology consists of several steps, including definition of the context (big picture of the use case, actors and their roles, and communication), the scenario (port activities and processes), and the use cases including the control tasks performed by the automated systems.

Small modular reactor reinforcement learning framework: Automating reactor core startup

A small modular reactor (SMR) has been considered a potential alternative for achieving carbon neutrality, and therefore, an increasing number of countries are performing extensive research and development. However, this is still in the development stage, and there are several technological or economical challenges that need to be overcome. Minimizing manual operations may be considered a wise approach to reduce the number of operators. Reactor core startup, which is a manual operation, is considered as an example. A method to automate the reactor core startup via the reinforcement learning (RL) algorithm is proposed in this paper. Further, an efficient SMR dynamic simulation model that performs simulations considering the action of the RL agent to achieve states and reward is developed. The suggested SMR dynamic simulation model is validated by the data available in the existing literature. The proposed method can perform automatic reactor core startup. The proposed framework that incorporates the SMR simulator to the RL algorithm is expected to be applied to various cases for reducing manual operations and contributing to realizing a higher level of SMR automation.

Prediction of dose distributions for non-small cell lung cancer patients using MHA-ResUNet.

The current level of automation in the production of radiotherapy plans for lung cancer patients is relatively low. With the development of artificial intelligence, it has become a reality to use neural networks to predict dose distributions and provide assistance for radiation therapy planning. However, due to the significant individual variability in the distribution of non-small cell lung cancer (NSCLC) planning target volume (PTV) and the complex spatial relationships between the PTV and organs at risk (OARs), there is still a lack of a high-precision dose prediction network tailored to the characteristics of NSCLC. To assist in the development of volumetric modulated arc therapy (VMAT) plans for non-small cell lung cancer patients, a deep neural network is proposed to predict high-precision dose distribution. This study has developed a network called MHA-ResUNet, which combines a large-kernel dilated convolution module and multi-head attention (MHA) modules. The network was trained based on 80 VMAT plans of NSCLC patients. CT images, PTV, and OARs were fed into the independent input channel. The dose distribution was taken as the output to train the model. The performance of this network was compared with that of several commonly used networks, and the networks' performance was evaluated based on the voxel-level mean absolute error (MAE) within the PTV and OARs, as well as the error in clinical dose-volume metrics. The MAE between the predicted dose distribution and the manually planned dose distribution within the PTV is 1.43Gy, and the D95 error is less than 1Gy. Compared with the other three commonly used networks, the dose error of the MHA-ResUNet is the smallest in PTV and OARs. The proposed MHA-ResUNet network improves the receptive field and filters the shallow features to learn the relative spatial relation between the PTV and the OARs, enabling accurate prediction of dose distributions in NSCLC patients undergoing VMAT radiotherapy.