Training Trajectory Research Articles

Spacecraft Relative Trajectory Planning Based on Meta-Learning

Spacecraft relative trajectory planning is central to many space missions like on-orbit service and debris removal. While early attempts of machine-learning-based trajectory planning have been witnessed, they still face the open problem of how to acquire sufficient training samples to conduct robust training. In this article, we have introduced a meta-learning framework to improve the adaptation ability of the planner when facing new initial conditions. To achieve this goal, we divided the training trajectories as sub-training samples and fake testing samples. Then, the meta planner is trained by repeatedly conducting a trail training-and-testing process. To this end, the gradient information of the meta learner is initially obtained on the subtraining sets and is further adjusted by looking at its testing performance on those fake testing data. Therefore, the meta planer explicitly take account of the potential testing performance into consideration and, hence, alleviate the overfitting phenomena with few training trajectories. Simulation results substantiate the effectiveness of our approach, as well as the advantages of quick adaptation to new initial conditions without overfitting.

Real-Time Energy-Efficient Driver Advisory System for High-Speed Trains

An on-board energy-efficient driving advisory system is proposed for a high-speed train, which runs on a vehicle control unit. A data interaction framework is presented to monitor train real-time state and temporary speed limitations. A bilevel optimal control method is designed to calculate the energy-optimal speed profile in real time. Specifically, the upper level is to calculate the min-time speed profile based on Pontryagin’s maximum principle, and the lower level is to determine coast profiles according to the Lagrange multiplier technique. The driving advice is extracted from the optimized trajectories. If the deviation of the train trajectory is detected, the speed profile is updated online. To highlight the achievable improvements of the proposed optimal control method, a pseudospectral method and a quadratic programming method are introduced as performance comparison. Simulation results show that the proposed method yields an energy-optimal solution within a control cycle of 256 ms. The driver-in-the-loop tests prove that the driving advice can be exactly followed by drivers. The proposed driver advisory system can improve the performance of punctuality and energy efficiency.

Organization of training of emercom cadets to conduct emergency rescue operations in a fire

Introduction. Training cadets to perform emergency rescue operations in a fire is an urgent task that requires improving the educational process in this area. The most difficult types of rescue operations are opening and disassembling the building and technological structures, which are held to ensure the penetration of fire in hard to reach areas of buildings, reconnaissance, search and rescue, the extinguishing means to eliminate burning.Materials and Methods. To implement high-quality training of trainees to perform emergency rescue operations in a fire, a review of literature sources, the regulatory framework and the experience of fire and rescue units was conducted. The development of the training trajectory and content of teaching materials is based on the main provisions of modular and game training, the requirements of competence and contextual approaches that contribute to the formation of educational motivation of cadets.Results. Based on a set of pedagogical theories, research by the authors, regulatory documents and practical experience, a training course and methodology for training cadets to perform emergency rescue operations for opening and disassembling construction and technological structures in a fire have been developed. The training course includes theoretical and practical training to the extent sufficient for the formation of students ' solid knowledge, practical skills in this professional field. To update and maintain the competencies formed as a result of mastering the training course at a sufficient level, it is proposed to use a proven and applied multi-level modular system of practical training. To improve the quality of training of trainees and an objective assessment of the formed knowledge, practical skills and abilities, it is proposed to use an expert questionnaire and involve practical employees of fire and rescue units.Discussion and Conclusions. The proposed approach to specialized training of trainees based on the study of individual courses embedded in the implemented educational process will increase the readiness of graduates for professional activities to perform basic combat tasks to save people and reduce material damage in fires.

Global Integration of Palliative Nursing Education to Improve Health Crisis Preparedness.

COVID-19 has highlighted the need for universal palliative care access. Nurses require palliative care education throughout the trajectory of professional training to effectively achieve this vision. Review of the National Consensus Project Clinical Practice Guidelines for Quality Palliative Care and use of educational exemplars highlight opportunities for improving palliative nursing education in academic and clinical settings. Consistently applying palliative care principles affects nursing outcomes across myriad domains of person-centered services. All nurses are responsible for delivering primary palliative care, but they cannot practice what they do not know. The End-of-Life Nursing Education Consortium Project offers evidence-based education for nursing students and practicing nurses nationally and globally. Equipping both nurses and nursing students with palliative care education is critical to improve the overall quality of health care throughout the continuum during COVID-19 and in the face of future health crises. [J Contin Educ Nurs. 2021;52(3):130-135.].

Professional Training in Integrative and Complementary Practices: the meanings attributed by Primary Health Care workers.

To understand the meanings attributed by Primary Health Care workers to the professional training process in Integrative and Complementary Practices. Descriptive, exploratory study with a qualitative approach, carried out with 20 professionals from 14 health units in three municipalities in the Metropolitan Region of Goiânia, state of Goiás, Brazil. Data were collected through semi-structured interviews, transcribed and analyzed using the thematic content analysis. Based on the analysis, the thematic category about training trajectories in Integrative and Complementary Practices emerged. It discusses that the training takes place through training provided by federal and municipal management or professional councils, via distance, semi-presential learning or in-person training. Furthermore, training courses are held at private educational institutions funded by the professionals themselves. Additionally, informal sources of information are used to obtain knowledge (internet, books and magazines). The results show, on the one hand, insufficient and diffuse training, with limited supply and quality and, on the other hand, the need to increase educational strategies to improve the training of health professionals aiming at providing different Integrative and Complementary Practices in the Primary Health Care.

Online information service for training in Industry 4.0 technologies

A new element of the information service in the field of technical training of specialists for Industry 4.0 is an online platform that implements distance forms of e-learning for specialists. An online learning service is an interactive transdisciplinary infrastructure that accumulates knowledge in demand by the intellectual industry. The information potential of the online learning service allows students to create curricula based on an arbitrary sequence of studying theoretical disciplines. The designer of professional courses ensures the structuring of content and its presentation to the listener in informational forms that cause maximum involvement of students in the disciplines studied. The online training information service contains methods and scenarios based on generally recognized world practices and adapting the trajectories of individual training of specialists to modern industry requirements. A scheme of an online information service for training technical specialists for Industry 4.0 based on network technologies of interaction between the listener and educational content is proposed. It is shown that online training services form an informational competitive environment that integrates the resources of private business, state educational institutions, scientific, industrial and academic communities.

Structure design and kinematics analysis and simulation of exercise bike type lower limb rehabilitation instrument

This article proposes a structural design of an exercise bike-type lower limb rehabilitation device, and introduces its components and design in detail. Through the organic combination of pedal-type rehabilitation actuators and exoskeleton auxiliary fixation mechanisms, it is safe and effective to maintain or restore old Human’ lower limb exercise ability. By formulating rehabilitation training strategies and using exoskeleton assisted fixation, the training trajectory of the user’s lower limbs can be fixed and sufficient safety guarantees are provided. This design uses SolidWorks for 3D software simulation to complete the part modeling, device assembly drawing and sports simulation of the exercise bike-type lower limb rehabilitation device, which has broad development prospects and practical value.

ТРАЕКТОРИЯ ОБУЧЕНИЯ И РАЗВИТИЯ ПЕРСОНАЛА, ОРИЕНТИРОВАННАЯ НА СТРАТЕГИЮ ОРГАНИЗАЦИИ

The article considers the trajectory of training and development of employees in modern conditions. The stages of planning and organizing the training and development of employees, as well as the stages of creating a system of continuous training and development of personnel are113 ТРУД И СОЦИАЛЬНАЯ СФЕРА presented. The analysis and examples of mixed learning in organizations are given. The features of micro-training in the modern system of training and development of employees are considered. Based on the results of the study, recommendations are given for the effective organization of the trajectory of training and development of personnel in the organization.

The Ontological basis for teaching CAD staff

The urgency and significance of the application of the ontological approach in teaching computer-aided design is substantiated. Training and retraining of personnel is one of the important stages in the implementation of automated systems for industrial purposes, and methodological support tools are necessarily present in the portfolio of all leading manufacturers of computer-aided design systems (CAD). Principles and approaches to the formation of the ontological base of the subject area of teaching computer-aided design are proposed. To highlight the structure of educational ontology, it is proposed to use the concepts of aspects of mechanical engineering design. The hierarchy of levels of training for CAD users is determined. At the operator level, training comes down to mastering a limited set of terms and concepts implemented in specific system solutions. At the technician level, it is required to master a wider set of standard design procedures typical for a whole class of basic CAD technologies. At the engineering levels, the user acquires the knowledge necessary to master the technologies and CAD tools in the complex of all stages of technical preparation of production. The article describes the method of ontological analysis of the studied subject area, which ensures the formation of target trajectories for training and retraining specialists, providing for a number of sequential stages in the formation of an ontological base. The article describes the method of ontological analysis of the subject area of education, which ensures the formation of target trajectories of training and retraining of specialists and provides for a number of successive stages of the formation of an ontological base. To optimize the individual trajectories of training CAD specialists, special software has been developed, integrated with the Protégé ontological editor.

CAM-FoC: A High Accuracy Lightweight Deep Neural Network for Grip Force Measurement of Elongated Surgical Instrument

Grip force measurement enables better control performance for robot-assisted minimally invasive surgery (RMIS). A deep-learning-based method is proposed to measure the instrument grip force without mounting additional sensors in this article. First, the training trajectory and input data frame are studied. Seven data are derived from the original sensor data, and a binary butterfly optimization algorithm with opposite-based learning (bBOA-OBL) is conducted to form the suitable input data frame. Based on the data frame, a novel convolutional network with an attention mechanism and feedforward of current (CAM-FoC) is proposed to calculate the grip force. The results of the ablation study tell that the master-slave trajectory has the highest accuracy, the optimized input data frame can reduce the error by 17%, and each component of CAM-FoC can enhance the measurement accuracy. Experiments and comparisons are also carried out. The root mean squared error (RMSE) in the experiment is only 0.1233 N and is lower than four other popular methods. In addition, the average computation time is around 2 ms on different platforms. The method manifests higher measurement accuracy than the state-of-the-art and is of acceptable computational complexity. The technology would potentially achieve grip force feedback in clinical usage, which can significantly improve surgery performance. The method could also be used by other robots composed of the cable-pulley mechanism to acquire external forces.

A pretrained proximal policy optimization algorithm with reward shaping for aircraft guidance to a moving destination in three-dimensional continuous space

To enhance the performance of guiding an aircraft to a moving destination in a certain direction in three-dimensional continuous space, it is essential to develop an efficient intelligent algorithm. In this article, a pretrained proximal policy optimization (PPO) with reward shaping algorithm, which does not require an accurate model, is proposed to solve the guidance problem of manned aircraft and unmanned aerial vehicles. Continuous action reward function and position reward function are presented, by which the training speed is increased and the performance of the generated trajectory is improved. Using pretrained PPO, a new agent can be trained efficiently for a new task. A reinforcement learning framework is built, in which an agent can be trained to generate a reference trajectory or a series of guidance instructions. General simulation results show that the proposed method can significantly improve the training efficiency and trajectory performance. The carrier-based aircraft approach simulation is carried out to prove the application value of the proposed approach.

Multi-objective railway timetabling including energy-efficient train trajectory optimization

Energy-efficient train driving is an important topic to railway undertakings (RUs) for sustainability and cost reduction. The timetable affects the possibilities for energy-efficient train driving by the amount of running time supplements, which is the topic of energy-efficient train timetabling (EETT). The scientific literature on EETT focuses mainly on the balance between total running time and energy consumption. However, in practice RUs consider a trade-off between the total running time, the infrastructure occupation and the timetable robustness, while energy efficiency is not considered. In this paper we consider a multiple-objective timetabling problem at a microscopic infrastructure level that adds energy consumption to the other three objectives. We approach the multiple-objective problem by a brute force search algorithm, where we use two different methods to compute the optimal solution: a weighted sum method and a distance metric method. We apply the method to a Dutch case study on the corridor between the stations Arnhem Central and Nijmegen with alternating Intercity and Sprinter trains, without intermediate overtaking possibilities. The results indicate that there is a balancing relationship between the total running time and energy consumption, without influencing the infrastructure occupation and robustness. The results of the 10 Pareto-optimal solutions show a variation of 5% for the total running time, 18% for the energy consumption, 0.3% for the extended cycle time, and 0.8% for the buffer time. The shortest running time leads to 18% more energy consumption than the longest running time with 5% more running time supplement. In both cases the extended cycle time and buffer time are almost constant. On the other hand, reducing the infrastructure occupation leads to homogenization of the timetable. Therefore, including energy consumption in the multiple-objective can be used to balance the trade-off between total running time and capacity consumption.

The Sishen-Saldanha railway project in South Africa: Arguments for and against construction, 1970 - 1976

The Sishen-Saldanha railway project was an undertaking of gigantic proportions in South Africa’s history, which currently serves as the longest freight train trajectory for iron ore in the world. It became imperative to provide reliable and efficient access to the coast for export purposes in a country with vast mineral resources. After the discovery of iron ore deposits at Sishen in the north-western Cape Province, South Africa’s largest mining corporation, the South African Iron and Steel Corporation (ISCOR), took the leading initiative for the proposed planning of a railway line connecting Sishen to Saldanha Bay on the West Coast. As a result of pressing international sanctions, the apartheid government sought to forge ahead with infrastructural developments in order to stabilise economic growth. With the dwindling market exports becoming an ever-serious concern, ISCOR’s project was to be a bulwark for ensuring optimum exports and economic development. In political circles, an intense parliamentary debate ensued in 1973 revolving around the acceptance and promulgation of the Sishen-Saldanha Railway Construction Bill. It reflected the controversial discussions between the ruling National Party and the United Party as liberal opposition party on pivotal issues concerning the construction of the railway line. Simultaneously, an underlying contention existed as to the choice of location of an appropriate export port at Saldanha or St. Croix. The author seeks to assess the primary sources pertaining to the proposed Sishen-Saldanha railway during its formative years from 1970 to 1976.

REAVILING THE DISTRIBUTION REGULARITIES OF THE PROCEDURE EXECUTION TIME OF THE ALGORITHM OF TOWER CONTROLLER`S ACTIONS USING GERT NETWORKS

The article discusses issues related to the calculation of the parameters distribution of the procedure execution time of the algorithm of the Tower controller`s actions when servicing the aircraft performing the approach (hereinafter simply the ALGORITHM), using the Graphical Evaluation and Review Technique (GERT network). ALGORITHM is an integral part of the trainee reference (or model-following) model in the intelligent training system ATC of Tower, which is being developed by the Department of the Information Technologies of the Flight Academy of the National Aviation University. The reference model is formed on the basis of a list (set) of extremely detailed technological operations, the order of performing these operations upon a specific situation, a model of information flows circulation at the specialist's workplace, reference values, and time spent probabilistic models on performing technological operations. The reference model in the process of system functioning closely interacts with the trainee current model, thereby ensuring the fixation of his mistakes. On the basis of his mistakes, the intelligent system forms an individual training trajectory for the trainee and provides an opportunity for an objective automatic assessment of his operation activities. The use of the GERT network in calculating the ALGORITHM time distribution parameters allows obtaining the expected mean time value and the root-mean-square (standard) deviation, but in some cases, it does not allow calculating the execution time of its individual parts, for which the time is directly proportional to the performance characteristics of an aircraft.

Participation in training at older ages: A European perspective on path dependency in life course trajectories.

Investments in lifelong learning may create unsatisfactory results, and this could potentially contribute to the reproduction of inequalities. We argue that the process is related to the accumulation of opportunities and barriers for participation in training, which can lock individuals in disadvantageous path-dependent trajectories. We take a longitudinal approach to analyse whether participation in training in older age is path-dependent, and whether this path dependency is related to institutional contexts. Using data from the Survey of Health, Ageing, and Retirement in Europe (SHARE), we trace individual training trajectories in the population aged 50+ in twelve European countries between 2010 and 2015 (27 370 respondents). Hierarchical Bayesian logit models serve to assess the probability of training during the sixth wave, with a lagged dependent variable as a predictor. Results suggest that training participation is path-dependent and participation in training is limited for people who have not trained previously. It is also related to macrostructural context: path dependency is lower in countries with stronger knowledge economies, stronger emphasis on education, and a proactive ageing climate. Recognising path dependency can help to improve access to training and design policies that address problems of cohesion, active ageing and adult learning.

Influence of the rail electrification system topology on the energy consumption of train trajectories

Electrically powered rail vehicles are considered one of the most energy-efficient means of transport. Transport activity is responsible for a considerable part of global energy consumption. The transport industry is therefore obliged to develop strategies for more efficient energy use. Railway electrification systems transmit the electrical power supplied by substations to moving trains. However, part of the power supplied is consumed by the electrification systems and does not reach the trains. In this study, transmission losses in the 2 × 25 kV electrification system are evaluated. The 2 × 25 kV system is widely used in high-speed and high-capacity railway lines. Assessment of the performance of the 2 × 25 kV system is carried out by computer simulation of the power flows between the elements involved in train movement by means of simplified physical models. The results show that the reduction of transmission losses is a feasible way to achieve energy savings and to improve the energy efficiency in electrified rail transport. For this, it is essential to add the topology of the electrification system to the data considered in the design of the train trajectories.

Learning adversarial policy in multiple scenes environment via multi-agent reinforcement learning

ABSTRACT Learning adversarial policy aims to learn behavioural strategies for agents with different goals, is one of the most significant tasks in multi-agent systems. Multi-agent reinforcement learning (MARL), as a state-of-the-art learning-based model, employs centralised or decentralised control methods to learn behavioural strategies by interacting with environments. It suffers from instability and slowness in the training process. Considering that parallel simulation or computation is an effective way to improve training performance, we propose a novel MARL method called Multiple scenes multi-agent proximal Policy Optimisation (MPO) in this paper. In MPO, we first simulate multiple parallel scenes in the training environment. Multiple policies control different agents in the same scene, and each policy also controls several identical agents from multiple scenes. Then, we expand proximal policy optimisation (PPO) with an improved actor-critic network, ensuring the stability of training in multi-agent tasks. The actor network only uses local information for decision making, and the critic network uses global information for training. Finally, effective training trajectories are computed with two criteria from multiple parallel scenes rather than single to accelerate the learning process. We evaluate our approach in two simulated 3D environments, one of which is Unity's official open-source soccer game, and the other is unmanned surface vehicles (USVs) built by Unity. Experiments demonstrate that MPO converges more stable and faster than benchmark methods in model training, and demonstrates excellent adversarial policy compared with benchmark models.

Pseudospectral optimal train control

In the last decade, pseudospectral methods have become popular for solving optimal control problems. Pseudospectral methods do not need prior knowledge about the optimal control structure and are thus very flexible for problems with complex path constraints, which are common in optimal train control, or train trajectory optimization. Practical optimal train control problems are nonsmooth with discontinuities in the dynamic equations and path constraints corresponding to gradients and speed limits varying along the track. Moreover, optimal train control problems typically include singular solutions with a vanishing Hessian of the associated Hamiltonian. These characteristics make these problems hard to solve and also lead to convergence issues in pseudospectral methods. We propose a computational framework that connects pseudospectral methods with Pontryagin’s Maximum Principle allowing flexible computations, verification and validation of the numerical approximations, and improvements of the continuous solution accuracy. We apply the framework to two basic problems in optimal train control: minimum-time train control and energy-efficient train control, and consider cases with short-distance regional trains and long-distance intercity trains for various scenarios including varying gradients, speed limits, and scheduled running time supplements. The framework confirms the flexibility of the pseudospectral method with regards to state, control and mixed algebraic inequality path constraints, and is able to identify conditions that lead to inconsistencies between the necessary optimality conditions and the numerical approximations of the states, costates, and controls. A new approach is proposed to correct the discrete approximations by incorporating implicit equations from the optimality conditions. In particular, the issue of oscillations in the singular solution for energy-efficient driving as computed by the pseudospectral method has been solved.

A STORY OF HOPE: LEADING CHANGE BEYOND BORDERS THROUGH A CULTURALLY INFORMED FOCUS

By the end of this presentation, participants will be able to: 1) appreciate the benefits of culturally diverse mentorship during training and early career trajectory; 2) articulate how culturally informed training adds multidimensionality to a “less trodden” career pathway; and 3) reconstruct a journey of change in child and adolescent mental health development in challenging settings.

Development and Assist-As-Needed Control of an End-Effector Upper Limb Rehabilitation Robot

Robot-assisted rehabilitation therapy has been proven to effectively improve upper limb motor function and daily behavior of patients with motor dysfunction, and the demand has increased at every stage of the rehabilitation recovery. According to the motor relearning program theory, upper limb motor dysfunction can be restored by a certain amount of repetitive training. Robotics devices can be an approach to accelerate the rehabilitation process by maximizing the patients’ training intensity. This paper develops a new end-effector upper limb rehabilitation robot (EULRR) first and then presents a controller that is suitable for the assist-as-needed (AAN) training of the patients when performing the rehabilitation training. The AAN controller is a strategy that helps the patient’s arm to stay close to the given trajectory while allowing for spatial freedom. This controller enables the patient’s arm to have spatial freedom by constructing a virtual channel around the predetermined training trajectory. Patients could move their arm freely in the allowed virtual channel during rehabilitation training while the robot provides assistance when deviating from the virtual channel. The AAN controller is preliminarily tested with a healthy male subject in different conditions based on the EULRR. The experimental results demonstrate that the proposed AAN controller could provide assistance when moving out of the virtual channel and provide no assistance when moving along the trajectory within the virtual channel. In the close future, the controller is planned to be used in elderly volunteers and help to increase the intensity of the rehabilitation therapy by assisting the arm movement and by provoking active participation.