Real-time Control Framework Research Articles

A CAV-Lead speed advice approach considering local spatiotemporal traffic state near bottlenecks

Bottlenecks of the freeway generated especially by traffic accidents or temporary work zones contribute to significant reductions in system throughput and hinder the efficient traffic operations. It is imperative to take proactive measures to improve traffic state. With the rapid advancements in intelligent transportation, connected and autonomous vehicles (CAVs) have attracted much attention by its speculated capabilities in improving traffic safety and well-organized operational coordination. Therefore, reasonably utilizing the advantages of CAVs is possible to reduce the impact induced by bottlenecks. In this research, we propose a novel algorithm called CAV-Lead to obtain the CAV’s regulated speed under mixed CAVs and human-driven vehicles (HVs) environment to improve the overall utilization of the freeway capacity near bottlenecks. Firstly, we illustrate the basic principle of the CAV-Lead algorithm that takes both microscopic and macroscopic traffic characteristics into account. Then, based on the local spatiotemporal traffic state, the CAV-Lead algorithm is proposed to determine each CAV’s speed under mixed flow. Furthermore, a real-time simulation control framework considering the random behavior of HVs is presented. Moreover, several simulation evaluations including comparisons with basic scenarios and similar research are conducted under various CAV market penetration rates (MPRs). The results demonstrate that the CAV-Lead could improve the traffic performance, especially for the high traffic demand with certain MPRs.

Quantum model prediction for frequency regulation of novel power systems which includes a high proportion of energy storage

As the proportion of renewable energy generation continues to increase, the participation of new energy stations with high-proportion energy storage in power system frequency regulation is of significant importance for stable and secure operation of the new power system. To address this issue, an energy storage control method based on quantum walks and model predictive control (MPC) has been proposed. First, historical frequency deviation signals and energy storage charge–discharge state signals are collected. Simulation data are generated through amplitude encoding and quantum walks, followed by quantum decoding. Subsequently, the decoded data are inputted into the MPC framework for real-time control, with parameters of the predictive model continuously adjusted through a feedback loop. Finally, a novel power system frequency regulation model with high-proportion new energy storage stations is constructed on the MATLAB/Simulink platform. Simulation verification is conducted with the proportional–integral–derivative (PID) and MPC methods as comparative approaches. Simulation results under step disturbances and random disturbances demonstrate that the proposed method exhibits stronger robustness and better control accuracy.

Trajectory planning and control of spacecraft avoiding dynamic debris swarm

The continuous accumulation of space debris poses a significant threat to spacecraft on orbit. This paper introduces a dynamic trajectory planning and control framework aimed at ensuring the safe traversal of spacecraft through space debris swarms. Initially, a threat model is established, considering the movement of the debris swarm and the constraints of spacecraft detection range. This model utilizes a dynamically updated, redefined Gaussian mixture model to characterize the threat posed by the debris swarm to spacecraft, with proximity to debris correlating to increased threat levels. Building upon this threat model, four guidance rules are defined, including target guidance, minimal threat, threat threshold, and local path optimization, to facilitate the generation of the shortest collision-free local trajectory for spacecraft. Combining the concept of receding horizon control, an online real-time planning and control framework is formulated for spacecraft navigating through debris swarms. Finally, numerical and semi-physical simulations verify that the proposed framework can stably generate spacecraft safe trajectories and control commands under the threat of numerous dynamic space debris, showing the characteristics of optimal planning trajectory, rapid computation speed and robust safety features.

Towards a digital twin framework in additive manufacturing: Machine learning and bayesian optimization for time series process optimization

Laser directed-energy deposition (DED) offers notable advantages in additive manufacturing (AM) for producing intricate geometries and facilitating material functional grading. However, inherent challenges such as material property inconsistencies and part variability persist, predominantly due to its layer-wise fabrication approach. Critical to these challenges is heat accumulation during DED, influencing the resultant material microstructure and properties. Although closed-loop control methods for managing heat accumulation and temperature regulation are prevalent in DED literature, few approaches integrate real-time monitoring, physics-based modeling, and control simultaneously in a cohesive framework. To address this, we present a digital twin (DT) framework for real-time model predictive control of process parameters of the DED for achieving a specific process design objective. To enable its implementation, we detail the development of a surrogate model utilizing Long Short-Term Memory (LSTM)-based machine learning which uses Bayesian Inference to predict temperatures across various spatial locations of the DED-built part. This model offers real-time predictions of future temperature states. In addition, we introduce a Bayesian Optimization (BO) method for Time Series Process Optimization (BOTSPO). Its foundational principles align with traditional BO, and its novelty lies in our unique time series process profile generator with a reduced dimensional representation. BOTSPO is used for dynamic process optimization in which we deploy BOTSPO to determine the optimal laser power profile, aiming to achieve desired mechanical properties in a DED build. The identified profile establishes a process trajectory that online process optimizations aim to match or exceed in performance. This paper elucidates components of the digital twin framework, advocating its prospective consolidation into a comprehensive digital twin system for AM.

MotGen: a closed-loop bacterial motility control framework using generative adversarial networks.

Many organisms' survival and behavior hinge on their responses to environmental signals. While research on bacteria-directed therapeutic agents has increased, systematic exploration of real-time modulation of bacterial motility remains limited. Current studies often focus on permanent motility changes through genetic alterations, restricting the ability to modulate bacterial motility dynamically on a large scale. To address this gap, we propose a novel real-time control framework for systematically modulating bacterial motility dynamics. We introduce MotGen, a deep learning approach leveraging Generative Adversarial Networks to analyze swimming performance statistics of motile bacteria based on live cell imaging data. By tracking objects and optimizing cell trajectory mapping under environmentally altered conditions, we trained MotGen on a comprehensive statistical dataset derived from real image data. Our experimental results demonstrate MotGen's ability to capture motility dynamics from real bacterial populations with low mean absolute error in both simulated and real datasets. MotGen allows us to approach optimal swimming conditions for desired motility statistics in real-time. MotGen's potential extends to practical biomedical applications, including immune response prediction, by providing imputation of bacterial motility patterns based on external environmental conditions. Our short-term, in-situ interventions for controlling motility behavior offer a promising foundation for the development of bacteria-based biomedical applications. MotGen is presented as a combination of Matlab image analysis code and a machine learning workflow in Python. Codes are available at https://github.com/bgmseo/MotGen, for cell tracking and implementation of trained models to generate bacterial motility statistics.

Real-time evaluation of signal accuracy in wastewater surveillance of pathogens with high rates of mutation

Wastewater surveillance of coronavirus disease 2019 (COVID-19) commonly applies reverse transcription-quantitative polymerase chain reaction (RT-qPCR) to quantify severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) RNA concentrations in wastewater over time. In most applications worldwide, maximal sensitivity and specificity of RT-qPCR has been achieved, in part, by monitoring two or more genomic loci of SARS-CoV-2. In Ontario, Canada, the provincial Wastewater Surveillance Initiative reports the average copies of the CDC N1 and N2 loci normalized to the fecal biomarker pepper mild mottle virus. In November 2021, the emergence of the Omicron variant of concern, harboring a C28311T mutation within the CDC N1 probe region, challenged the accuracy of the consensus between the RT-qPCR measurements of the N1 and N2 loci of SARS-CoV-2. In this study, we developed and applied a novel real-time dual loci quality assurance and control framework based on the relative difference between the loci measurements to the City of Ottawa dataset to identify a loss of sensitivity of the N1 assay in the period from July 10, 2022 to January 31, 2023. Further analysis via sequencing and allele-specific RT-qPCR revealed a high proportion of mutations C28312T and A28330G during the study period, both in the City of Ottawa and across the province. It is hypothesized that nucleotide mutations in the probe region, especially A28330G, led to inefficient annealing, resulting in reduction in sensitivity and accuracy of the N1 assay. This study highlights the importance of implementing quality assurance and control criteria to continually evaluate, in near real-time, the accuracy of the signal produced in wastewater surveillance applications that rely on detection of pathogens whose genomes undergo high rates of mutation.

Architecting an Open-Source IIoT Framework for Real-Time Control and Monitoring in the Bioleaching Industry

Electronic waste (e-waste) contains toxic elements causing an important impact on environmental and human health. However, the presence of valuable metals, such as copper or gold, among others, make recycling a necessity for obtaining an alternative source of raw materials. Conventional metal recovery methods are environmentally unsound, prompting the exploration of greener alternatives like bioleaching, which utilizes the activity of microorganisms for a more sustainable recovery. However, the mechanisms involved in the process and the conditions to optimize the metabolic paths are still not completely known. Monitorization and automatization of the different stages composing the global process are crucial for advancing in the implementation of this novel technology at an industrial scale. For the first time, an open-source industrial IoT system is designed to enhance and regulate bioleaching by implementing real-time monitoring and control within the plant’s infrastructure. This system includes an Android app that displays real-time plant data from sensors and a robust server featuring a flexible application programming interface (API) for future applications. The app caters to specific needs such as remote sensor reading, actuator control, and real-time bioleaching alerts, ensuring secure access and proactive event management. By utilizing collected data, it minimizes downtime, equipment failures, and supply chain disruptions. The server maintains seamless communication with the plant controller, enabling efficient pump activation and sensor data transmission. A telegram bot demonstrates the API’s flexibility by forwarding plant alerts to users. During validation with concurrent remote user access, the application demonstrated its ability to prevent irreversible plant failures through an advanced alarm system. Ultimately, this IIoT system amplifies plant performance, safety, and efficiency by optimizing processes and decision-making capabilities. It emerges as a pivotal open-source tool, securing remote oversight and management of large-scale bioleaching plants, promising adaptability for future enhancements.

AI-Enabled Vibrotactile Feedback-Based Condition Monitoring Framework for Outdoor Mobile Robots

An automated Condition Monitoring (CM) and real-time controlling framework is essential for outdoor mobile robots to ensure the robot’s health and operational safety. This work presents a novel Artificial Intelligence (AI)-enabled CM and vibrotactile haptic-feedback-based real-time control framework suitable for deploying mobile robots in dynamic outdoor environments. It encompasses two sections: developing a 1D Convolutional Neural Network (1D CNN) model for predicting system degradation and terrain flaws threshold classes and a vibrotactile haptic feedback system design enabling a remote operator to control the robot as per predicted class feedback in real-time. As vibration is an indicator of failure, we identified and separated system- and terrain-induced vibration threshold levels suitable for CM of outdoor robots into nine classes, namely Safe, moderately safe system-generated, and moderately safe terrain-induced affected by left, right, and both wheels, as well as severe classes such as unsafe system-generated and unsafe terrain-induced affected by left, right, and both wheels. The vibration-indicated data for each class are modelled based on two sensor data: an Inertial Measurement Unit (IMU) sensor for the change in linear and angular motion and a current sensor for the change in current consumption at each wheel motor. A wearable novel vibrotactile haptic feedback device architecture is presented with left and right vibration modules configured with unique haptic feedback patterns corresponding to each abnormal vibration threshold class. The proposed haptic-feedback-based CM framework and real-time remote controlling are validated with three field case studies using an in-house-developed outdoor robot, resulting in a threshold class prediction accuracy of 91.1% and an effectiveness that, by minimising the traversal through undesired terrain features, is four times better than the usual practice.

The Real-Time Optimal Attitude Control of Tunnel Boring Machine Based on Reinforcement Learning

Efficient control of tunnel boring machine (TBM) tunneling along the designed tunnel axis in an unknown variable geological environment is a difficult and significant task. At present, the TBM attitude during tunneling is mostly manually controlled based on the deviation between the tunneling axis and the designed tunnel axis and their experiences. The tunneling axis from manual control is often the snakelike motion around the designed tunnel axis, even exceeding the deviation limit, for which this paper analyzed three reasons, the unknown geological environment, the hysteresis of TBM position response, and the unsolved overall optimization of tunneling axis. For these reasons, this paper proposed a real-time optimal control framework of TBM attitude based on reinforcement learning, which contains the geological information predictive model, TBM attitude and position (TBMAP) predictive model, and optimal attitude control policy (OACP). This framework can predict the current geological information in real-time and provide the corresponding real-time optimal attitude control that simultaneously considers the hysteresis of TBM position response and the overall optimization of the tunneling axis. This attitude control framework can be directly deployed to TBM without increasing costs and excessive modifications to the equipment. To verify the effectiveness of this attitude control framework, the Xinjiang Yiner Water Supply Phase II Project, using the TBM method, was adopted as a case study. The results revealed that the accuracy of geological environment recognition reached 94%, and OACP can significantly reduce the accumulated deviation of the tunneling axis from the designed tunnel axis by over 80% compared with the manual control and easily provide real-time decision support for attitude control in actual engineering.

Deep Learning-Based Trajectory Planning and Control for Autonomous Ground Vehicle Parking Maneuver

In this paper, a novel integrated real-time trajectory planning and tracking control framework capable of dealing with autonomous ground vehicle (AGV) parking maneuver problems is presented. In the motion planning component, a newly-proposed idea of utilizing deep neural networks (DNNs) for approximating optimal parking trajectories is further extended by taking advantages of a recurrent network structure. The main aim is to fully exploit the inherent relationships between different vehicle states in the training process. Furthermore, two transfer learning strategies are applied such that the developed motion planner can be adapted to suit various AGVs. In order to follow the planned maneuver trajectory, an adaptive learning tracking control algorithm is designed and served as the motion controller. By adapting the network parameters, the stability of the proposed control scheme, along with the convergence of tracking errors, can be theoretically guaranteed. In order to validate the effectiveness and emphasize key features of our proposal, a number of experimental studies and comparative analysis were executed. The obtained results reveal that the proposed strategy can enable the AGV to fulfill the parking mission with enhanced motion planning and control performance. <i>Note to Practitioners</i>&#x2014;This article was motivated by the problem of optimal automatic parking planning and tracking control for autonomous ground vehicles (AGVs) maneuvering in a restricted environment (e.g., constrained parking regions). A number of challenges may arise when dealing with this problem (e.g., the model uncertainties involved in the vehicle dynamics, system variable limits, and the presence of external disturbances). Existing approaches to address such a problem usually exploit the merit of optimization-based planning/control techniques such as model predictive control and dynamic programming in order for an optimal solution. However, two practical issues may require further considerations: 1). The nonlinear (re)optimization process tends to consume a large amount of computing power and it might not be affordable in real-time; 2). Existing motion planning and control algorithms might not be easily adapted to suit various types of AGVs. To overcome the aforementioned issues, we present an idea of utilizing the recurrent deep neural network (RDNN) for planning optimal parking maneuver trajectories and an adaptive learning NN-based (ALNN) control scheme for robust trajectory tracking. In addition, by introducing two transfer learning strategies, the proposed RDNN motion planner can be adapted to suit different AGVs. In our follow-up research, we will explore the possibility of extending the developed methodology for large-scale AGV parking systems collaboratively operating in a more complex cluttered environment.

A Real-Time Planning and Control Framework for Robust and Dynamic Quadrupedal Locomotion

Legged locomotion poses significant challenges due to its nonlinear, underactuated and hybrid dynamic properties. These challenges are exacerbated by the high-speed motion and presence of aerial phases in dynamic legged locomotion, which highlights the requirement for online planning based on current states to cope with uncertainty and disturbances. This article proposes a real-time planning and control framework integrating motion planning and whole-body control. In the framework, the designed motion planner allows a wider body rotation range and fast reactive behaviors based on the 3-D single rigid body model. In addition, the combination of a Bézier curve based trajectory interpolator and a heuristic-based foothold planner helps generate continuous and smooth foot trajectories. The developed whole-body controller uses hierarchical quadratic optimization coupled with the full system dynamics, which ensures tasks are prioritized based on importance and joint commands are physically feasible. The performance of the framework is successfully validated in experiments with a torque-controlled quadrupedal robot for generating dynamic motions.

Dynamic Scheduling and Optimization of AGV in Factory Logistics Systems Based on Digital Twin

At present, discrete workshops demand higher transportation efficiency, but the traditional scheduling strategy of the logistics systems can no longer meet the requirements. In a transportation system with multiple automated guided vehicles (multi-AGVs), AGV path conflicts directly affect the efficiency and coordination of the whole system. At the same time, the uncertainty of the number and speed of AGVs will lead to excessive cost. To solve these problems, an AGVs Multi-Objective Dynamic Scheduling (AMODS) method is proposed which is based on the digital twin of the workshop. The digital twin of the workshop is built in the virtual space, and a two-way exchange and real-time control framework based on dynamic data is established. The digital twin system is adopted to exchange data in real time, create a real-time updated dynamic task list, determine the number of AGVs and the speed of AGVs under different working conditions, and effectively improve the efficiency of the logistics system. Compared with the traditional scheduling strategy, this paper is of practical significance for the scheduling of the discrete workshop logistics systems to improve the production efficiency, utilization rate of resources, and dynamic response capability.

A Real-Time Prognostic-Based Control Framework for Hybrid Electric Vehicles

A Real-Time Prognostic-Based Control Framework for Hybrid Electric Vehicles

Opposite Treatment on Null Space: A Unified Control Framework for a Class of Underactuated Robotic Systems With Null Space Avoidance

Design of feedback control for underactuated robotic systems (URSs) is often complex and nonintuitive due to the inherent incapability of generating arbitrary velocities or accelerations at each moment. Researchers have designed various controllers; however, there are few unified intuitive feedback stabilization controllers for a wide range of URSs. In this article, we propose a real-time and unified control framework for a class of URSs with three states and two inputs based on the intuition of avoiding null space. To control diverse URSs, unlike transforming them to canonical forms, we approach them from an inverse perspective based on a Jacobian-like mapping matrix and disclose a fundamental issue, null space attraction, which fails all Jacobian-based standard kinematics control. An opposite treatment on null space, avoiding null space, is applied to oppose null space attraction, allowing the standard kinematics controllers to keep control authority. Overall, the proposed control framework consisting of a standard kinematics controller and a null space avoidance controller can fundamentally solve point-to-point stabilization for the class of driftless URSs and also render <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Delta $ </tex-math></inline-formula> -neighborhood stabilization for URSs with a nonvanishing and constant drift. Both the convergence properties are rigorously analyzed. Simulations and applications are conducted to demonstrate the generality, effectiveness, and robustness of our controllers.

Bare PCB (Printed Circuit Board) Fault Detection in Real-time Using YOLOv5

With the continuous development of object detection technology, the YOLO series of algorithms with high precision and speed has been used in various fault detection tasks. This paper aims to establish a real-time quality control framework for PCB fault detection that can be adopted by industries. The development of more automized testing method by using YOLOv5. Detection of imperfections despite misalignment and incorrect orientation is required in the industry. Decreases quality check time and human examiner cost for quality control and auditing the product (as it might be slow and error-prone). Computer Camera is used of real-time fault detection in this prototype, however any digital camera integration would be possible and might improve the performance. Ultimately, increased revenue generation followed by better quality production and supply that meets the market demand.

Relaxed deep generative adversarial networks for real-time economic smart generation dispatch and control of integrated energy systems

The randomness of renewable energy connected to power systems cannot satisfy the frequency stability and economic dispatch of integrated energy systems. The conventional combined dispatch and control framework can benefit the interests of only a part of energy systems, such as gas/heat/cold systems. Real-time economic smart generation dispatch and control are applied to solve these two problems of integrated energy systems. This paper proposes a relaxed deep generative adversarial network method for the real-time control framework to replace conventional combined methods with multiple time-scale combined frameworks. The proposed approach combines deep learning and relaxed operation with generative adversarial networks as the proposed method. Because of the powerful representation capability of deep learning and the advantages of amplitude constraints of the relaxation operation, the proposed method can simultaneously generate multiple convergent and high-performance generation commands. The proposed method is simulated for simple and large-scale complex integrated energy systems based on a 14-bus with ten natural-gas systems. Furthermore, the generation controller based on the proposed method can economically satisfy the frequency stability for integrated energy systems, mitigate uneven energy distribution and excess energy, improve energy efficiency, and achieve multi-energy complementarity.

Model Predictive Control–Based Load-Frequency Regulation of Grid-Forming Inverter–Based Power Systems

The high-penetrated renewables enable flexible and versatile dispatchable resources in power systems. As the digitalization process improves with the help of information and communication technology (ICT), a real-time online control framework is essential to regulate such a low-inertia power system dominated by renewables. To enable control practices, a control-oriented model is developed linking load increments to frequency dynamics. Based on such a control-oriented model, a model predictive control (MPC)–based online feedback algorithm is well designed by the virtue of rapid data transmission enabled by digitalization. The MPC optimization is a convex quadratic programming, where an objective function that balances frequency deviations and load increments is formulated and operational constraints are integrated into a matrix-type inequality. In the end, the proposed MPC-based load-frequency control framework is illustrated by several case studies, where validations and analyses of constraints inside the model are also included.

Real-time vision-based control of industrial manipulators for layer-width setting in concrete 3D printing applications

In this paper, to have control over geometry specifications of rectangular bar-shaped layers in a robotic concrete 3D printing process, a real-time vision-based control framework is developed and proposed. The proposed control system is able to set the layer-width by automatically adjusting the velocity of an industrial manipulator during the 3D printing process of concrete based materials relying on a vision system feedback. Initially, details related to the control system, vision and processing units, and robotic platform are discussed. In continue, technical descriptions related to the printhead design, conversion process from a digital 3D drawing model to numerical motion control commands of an industrial manipulator and building material used in this work are reported. The reliability and responsiveness of the developed system is then evaluated through experimental tests by printing several single bar-shaped layers with different wideness by means of an unique printhead geometry and also by printing two layers with the same dimension centrally above another. Overall, the high accuracy and responsiveness of the developed system demonstrate a great potential for real-time vision-based control of industrial manipulators for layer-width setting in concrete 3D printing applications.

CoCo Games: Graphical Game-Theoretic Swarm Control for Communication-Aware Coverage

We propose a novel framework for real-time communication-aware coverage control in networked robot swarms. Our framework unifies the robot dynamics with network-level message-routing to reach consensus on swarm formations in the presence of communication uncertainties by leveraging local information. Specifically, we formulate the communication-aware coverage as a cooperative graphical game, and use variational inference to reach mixed strategy Nash equilibria of the stage games. We experimentally validate the proposed approach in a mobile ad-hoc wireless network scenario using teams of aerial vehicles and terrestrial user equipment (UE) operating over a large geographic region of interest. We show that our approach can provide wireless coverage to stationary and mobile UEs under realistic network conditions.

Real-Time Distributed Cooperative Adaptive Cruise Control Model Considering Time Delays and Actuator Lag

Real-time control of a fleet of Connected and Automated Vehicles (CAV) for Cooperative Adaptive Cruise Control (CACC) is a challenging problem concerning time delays (from sensing, communication, and computation) and actuator lag. This paper proposes a real-time predictive distributed CACC control framework that addresses time delays and actuator lag issues in the real-time networked control systems. We first formulate a Kalman Filter-based real-time current driving state prediction model to provide more accurate initial conditions for the distributed CACC controller by compensating time delays using sensing data from multi-rate onboard sensors (e.g., Radar, GPS, wheel speed, and accelerometer), and status-sharing and intent-sharing data in BSM via V2V communication. We solve the prediction model using a sequential Kalman Filter update process for multi-rate sensing data to improve computational efficiency. We propose a real-time distributed MPC-based CACC controller with actuator lag and intent-sharing information for each CAV with the delay-compensated predicted current driving states as initial conditions. We implement the real-time predictive distributed CACC control algorithms and conduct numerical analyses to demonstrate the benefits of intent-sharing-based distributed computing, delay compensation, and actuator lag consideration on string stability under various traffic dynamics.