Autonomous Control Approach Research Articles

Observer‐based adaptive neural networks optimal control for spacecraft proximity maneuver with state constraints

AbstractThis article proposes an adaptive neural network (NN) optimal control approach for autonomous relative motion control of non‐cooperative spacecraft in proximity. The proposed method aims to minimize fuel consumption under various challenges including model uncertainty, state constraints, external disturbances, and input saturation. To account for uncertain parameters of non‐cooperative target and external disturbances, we start by designing a NN disturbance observer. Subsequently, a novel optimal control index function is presented. An adaptive NN based on the actor‐critic (A‐C) framework and backstepping theory is then utilized to approximate the solution of Hamilton–Jacobi–Bellman (HJB) equation and obtain an optimal control law. The Lyapunov framework is leveraged to establish the stability of the closed‐loop control system. Finally, numerical simulations are conducted to assess the feasibility and effectiveness of the proposed control scheme in comparison with an existing approach.

An Autonomous Distributed Coordination Strategy for Sustainable Consumption in a Microgrid Based on a Bio-Inspired Approach

Distributed energy resources have demonstrated their potential to mitigate the limitations of large, centralized generation systems. This is achieved through the geographical distribution of generation sources that capitalize on the potential of their respective environments to satisfy local demand. In a microgrid, the control problem is inherently distributed, rendering traditional control techniques inefficient due to the impracticality of central governance. Instead, coordination among its components is essential. The challenge involves enabling these components to operate under optimal conditions, such as charging batteries with surplus solar energy or deactivating controllable loads when market prices rise. Consequently, there is a pressing need for innovative distributed strategies like emergent control. Inspired by phenomena such as the environmentally responsive behavior of ants, emergent control involves decentralized coordination schemes. This paper introduces an emergent control strategy for microgrids, grounded in the response threshold model, to establish an autonomous distributed control approach. The results, utilizing our methodology, demonstrate seamless coordination among the diverse components of a microgrid. For instance, system resilience is evident in scenarios where, upon the failure of certain components, others commence operation. Moreover, in dynamic conditions, such as varying weather and economic factors, the microgrid adeptly adapts to meet demand fluctuations. Our emergent control scheme enhances response times, performance, and on/off delay times. In various test scenarios, Integrated Absolute Error (IAE) metrics of approximately 0.01% were achieved, indicating a negligible difference between supplied and demanded energy. Furthermore, our approach prioritizes the utilization of renewable sources, increasing their usage from 59.7% to 86.1%. This shift not only reduces reliance on the public grid but also leads to significant energy cost savings.

A deep reinforcement learning-based approach for autonomous lane-changing velocity control in mixed flow of vehicle group level

As an important driving behavior, lane-changing has a great impact on the safety and efficiency of traffic flow interacting with surrounding vehicles, especially in mixed traffic flows with autonomous vehicles and human-driven vehicles. This study proposes a deep reinforcement learning-based lane-changing model to train autonomous vehicles to complete lane-changing in the interaction with different human driving behaviors. First, a mixed-flow lane-changing environment of vehicle group level is constructed with surrounding vehicle trajectories extracted from natural driving trajectories. Then, the state space and action space are determined, the reward function is designed to comprehensively consider safety and efficiency, so as to guide autonomous vehicles not to collide, and determine the acceleration and direction angle to complete lane-changing behavior, and a collision avoidance strategy is integrated into the proposed method to ensure the safety of longitudinal motion. Furthermore, the trained model can learn the experience of successful lane-changing, resulting in a 90% success rate without collision in testing. Finally, the driving performance of the proposed method is analyzed in terms of safety and efficiency evaluation indicators, which proves that the proposed method can improve the efficiency and safety of the lane-changing process.

Towards Exoscope Automation in Neurosurgery: A Markerless Visual-Servoing Approach

Exoscopes are a promising tool for neurosurgeons, offering improved visualisation and ergonomics compared with traditional surgical microscopes. They consist of an external scope that projects the surgical field onto a 2D or 3D monitor, providing a wider field of view and better access to the surgical site. Despite the advantages, exoscopes present some limitations, such as the need for manual or foot joystick repositioning, which can disrupt the flow of the procedure and increase the risk of user error. In this study, a markerless visual-servoing approach for autonomous exoscope control is proposed to address these limitations and enhance the ergonomics and reduce the physical and cognitive load compared with traditional joystick control. The system uses visual information from the operating field to control the exoscope, eliminating the need for markers or additional tracking devices. The proposed approach was validated using a 7-DOF robotic manipulator with a stereo camera in an eye-in-hand configuration. Results showed that the system achieved 89 % accuracy in detecting the target and tracking its movement with a tracking error ranging from 0.50±0.17 cm for low-speed movements to 1.38±0.73 cm for high-speed movements. The proposed system also demonstrated improved efficiency, with a shorter execution time of 72.07±19.36 s compared with 106.52±18.50 s for the foot-joystick control. Additionally, the time out of the FoV was significantly higher in the joystick control mode and the frequency of appearance of the instrument in the centre of the image was higher when using the proposed system. The NASA TLX results indicated lower physical and cognitive load compared with the joystick control-based modality.

Runtime Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systems

Run Time Assurance (RTA) Systems are online verification mechanisms that filter an unverified primary controller output to ensure system safety. The primary control may come from a human operator, an advanced control approach, or an autonomous control approach that cannot be verified to the same level as simpler control systems designs. The critical feature of RTA systems is their ability to alter unsafe control inputs explicitly to assure safety. In many cases, RTA systems can functionally be described as containing a monitor that watches the state of the system and output of a primary controller, and a backup controller that replaces or modifies control input when necessary to assure safety. An important quality of an RTA system is that the assurance mechanism is constructed in a way that is entirely agnostic to the underlying structure of the primary controller. By effectively decoupling the enforcement of safety constraints from performance-related objectives, RTA offers a number of useful advantages over traditional (offline) verification. This article provides a tutorial on developing RTA systems.

Design and Evaluation of an Integrated Autonomous Control Method for Automobile Terminals

Background: Automobile terminals play a key role in global finished car supply chains. Due to their connecting character between manufacturers on the one side and distributers on the other side, they are continuously faced with volatile demand fluctuations and unforeseen dynamic events, which cannot be handled adequately by existing planning methods. Autonomous control concepts already showed promising results coping with such dynamics. Methods: This paper describes the causes of dynamics and the terminal systems’ inherent shortcomings in dealing with such dynamics. On this basis, it derives terminal’s demand for novel planning approaches and presents a new integrated autonomous control method for automobile terminals. This novel autonomous control approach combines yard and berth assignments. This paper evaluates the performance of the new approach in a small comprehensive generic scenario. It compares classical planning approaches with the new autonomous control approach, by using a discrete event simulation model. Moreover, it analyses all relevant parameters of the new approach in a full factorial experiment design. In a second step this paper proves the applicability of the combined autonomous control approach to real-world terminals. It presents a simulation model of a real-world terminal and compares the new method with the existing terminal planning approaches. Results: This paper will show that the autonomous control approach is capable of outperforming existing centralized planning methods. In the generic and in the real-world case the new combined method leads to the best logistic target achievement. Conclusions: The new approach is highly suitable to automobile terminal systems and helps to overcome existing shortcomings. Especially in highly dynamic and complex settings, autonomous control performs better than conventional yard planning approaches.

Blockchained smart contract pyramid-driven multi-agent autonomous process control for resilient individualised manufacturing towards Industry 5.0

The production control for the mass individualisation paradigm of R&D-stage products is challenging due to the mix-flow and frequently-disturbed environment. With the convergence of the sustainable development goals and the increasing individualised demands in products, resilient manufacturing is envisioned in Industry 5.0 proposition. Concerning that conventional centralised production control methods suffer from low stability and inefficiency of decisions under frequent disruptions, this paper establishes a blockchained smart contract pyramid-driven multi-agent autonomous process control (BSCP-MAAPC) approach for improving the timeliness and adaptability of control towards resilient individualised manufacturing. Firstly, a blockchain-based multi-agent system architecture is designed based on agent encapsulation of manufacturing units. Blockchained smart contracts are used as the enabler of the multi-agent system for peer-to-peer negotiation and coordination of tasks. Secondly, a quad-play blockchained smart contract pyramid together with a series of decentralised control patterns are designed to enable the initial task dispatching of various individualised demands, as well as rapid dynamic adjustment of schedule in response to internal random disruptions. Finally, a blockchained smart contract pyramid-driven multi-agent autonomous process control system prototype is built in the ManuChain system, and experiments are conducted to analyze the proposed BSCP-MAAPC approach in different environments. HIGHLIGHTS A blockchained smart contract pyramid-driven multi-agent autonomous process control (BSCP-MAAPC) approach. A quad-play blockchained smart contract pyramid together with a series of decentralized control patterns. Blockchained smart contracts as the enabler of the multi-agent system for peer-to-peer negotiation and coordination of tasks.

Optimization-Based Approach for Resilient Connected and Autonomous Intersection Crossing Traffic Control Under V2X Communication

In this paper, we present an optimization-based approach for safe, efficient, and resilient autonomous intersection traffic control in realistic vehicle-to-everything (V2X) communication environment. The proposed framework produces the fastest discrete-time trajectory for vehicles who want to cross an intersection. Constraints for safety are designed carefully in the optimization problem formulation to prevent potential collisions during intersection crossings. A novel vehicle-to-intersection (V2I) interaction mechanism is designed to handle imperfect communication characteristics such as packet delivery delay and loss. The proposed intersection management framework is evaluated by running extensive simulations using an open source vehicular network and microscopic traffic simulation software, Veins. The results show that the overall traffic control performance of the proposed framework is substantially better than conventional traffic light control framework, in particular when traffic volume is light and medium, even in situations with a realistic wireless vehicular network setting where packet delivery delays and drops occasionally occur.

A smart predictive framework for system-level stormwater management optimization

This study presents a global real-time control (RTC) approach for sustainable and adaptive management of stormwater. A network of inter-connected devices are assumed to dynamically generate the required set-points for the system actuators at the remote control center where global optimization algorithms calculate real-time operational decision-making target values. These target values activate the local controllers to manipulate the spatially distributed detention basin's outlets enabling a smart catchment scale optimal control. A real world watershed with four outlets to a nearby watercourse is chosen to test the applicability and efficiency of the proposed dynamic control approach, based on model simulation results. Results show that the proposed autonomous control approach has the ability to enhance the global performance of the stormwater management system in terms of quality and quantity to balance the network flow dynamics and environmental demands, while reducing the potential for erosion of receiving water bodies. Climate change is specifically discussed as a challenge for the designed control framework. Although, the performance criteria are shown to be affected by the increased rainfall intensities compared to actual rainfall scenarios, the proposed methodology still improves the peak flow reduction and detention time of water, at global scale, up to 54% and 14 h respectively under climate change conditions.

Reputation-based competitive pricing negotiation and power trading for grid-connected microgrid networks

The integration of renewables and microgrids into the modern electric grid has forced financial, technical, and policy change. Control strategies that enable energy trading between microgrids provide more effective use of distributed energy resources. This study presents a decentralized, autonomous control approach to manage energy transactions between nodes of a grid-connected microgrid network. Agents in the network form relationships, with interactions between agents described by quantifying their reputation using historical knowledge of familiarity, acceptance, and value between nodes. Methods are demonstrated on a network of 9 nodes with varying levels of network connectivity for a simulated year. Results indicate that certain relationships between nodes allow some microgrids to achieve greater financial benefit than others through a reduction in operating cost. A baseline case with no trading is used to compare results, with nodes experiencing anywhere from 3% to 72% reduction in their annual cost of energy depending on network connectivity and configuration. Node pair connections with the most opportunities to trade had a significant effect on the amount of excess renewables successfully traded in the network, and network configurations containing those pairs also resulted in the lowest grid load factors. Enabling localized trading led to a decrease in utility revenue by 21–27%, which could be partly recouped by establishing wheeling charges or trading fees.

A Data-Driven Multi-Agent Autonomous Voltage Control Framework Using Deep Reinforcement Learning

The complexity of modern power grids keeps increasing due to the expansion of renewable energy resources and the requirement of fast demand responses, which results in a great challenge for conventional power grid control systems. Existing autonomous control approaches for the power grid requires an accurate system model and a powerful computational platform, which is difficult to scale up for the large-scale energy system with more control options and operating conditions. Facing these challenges, this article proposes a data-driven multi-agent power grid control scheme using a deep reinforcement learning (DRL) method. Specifically, the classic autonomous voltage control (AVC) problem is taken as an example and formulated as a Markov Game with a heuristic method to partition agents. Then, a multi-agent AVC (MA-AVC) algorithm based on a multi-agent deep deterministic policy gradient (MADDPG) method that features centralized training and decentralized execution is developed to solve the AVC problem. The proposed method can learn from scratch and gradually master the system operation rules by input and output data. In order to demonstrate the effectiveness of the proposed MA-AVC algorithm, comprehensive case studies are conducted on an Illinois 200-Bus system considering load/generation changes, N-1 contingencies, and weak centralized communication environment.

Cooperation of Multiple Connected Vehicles at Unsignalized Intersections: Distributed Observation, Optimization, and Control

Cooperation of connected vehicles is a promising approach for autonomous intersection control. This article presents a systematic approach to the cooperation of connected vehicles at unsignalized intersections without global coordination. A task-area partition framework is proposed to decompose the mission of cooperative passing into three main tasks, i.e., vehicle state observation, arriving time optimization, and trajectory tracking control. To accomplish these tasks, a distributed observation algorithm is introduced to achieve fixed-time observation of other vehicles’ states for passing sequence determination, a distributed optimization algorithm is introduced to schedule conflict-free arriving times for trajectory planning, and a distributed control algorithm is proposed to address parameter mismatches and acceleration saturation for fixed-time trajectory tracking control. Numerical simulations demonstrate that the proposed method can achieve cooperative passing of vehicles without global coordination at the cost of a growth of 8.8–18.1% average travel times in low and medium traffic volumes.

Robust Autonomous Intersection Control Approach for Connected Autonomous Vehicles

Traffic light-free intersection control is envisioned to alleviate congestion and manage vehicles intelligently. With the help of vehicle-to-infrastructure (V2I) communication and edge computing (EC), vehicles are instructed to cross the intersection with high vehicle safety and traffic efficiency without traffic lights. However, unstable channel conditions can lead to the reduction of traveling safety. In this paper, we propose a robust autonomous intersection control (AIC) approach with global optimization scheduling, which protects connected autonomous vehicles from collision under any channel conditions while achieving decent traffic efficiency. In particular, we propose an AIC model that gives vehicles certain autonomy under centralized control to ensure the traveling safety in case of some emergencies. By conducting an interference graph, we simplify the AIC problem as a weighted maximal clique problem with restriction. To improve the fairness and efficiency in terms of vehicle passage, multiple factors such as travel delay, traffic of the current lane and passengers' desired speed are considered. Furthermore, we propose a heuristic algorithm to search the solution space. For further optimization, a particle swarm optimization algorithm is proposed, achieving a near-optimal result with adjustable overhead. Finally, we build the simulation model and conduct a comparative performance evaluation. Simulation results demonstrate the superiority of our proposed scheme.

Optimisation of a fuzzy logic-based local real-time control system for mitigation of sewer flooding using genetic algorithms

Abstract Urban flooding damages properties, causes economic losses and can seriously threaten public health. An innovative, fuzzy logic (FL)-based, local autonomous real-time control (RTC) approach for mitigating this hazard utilising the existing spare capacity in urban drainage networks has been developed. The default parameters for the control algorithm, which uses water level-based data, were derived based on domain expert knowledge and optimised by linking the control algorithm programmatically to a hydrodynamic sewer network model. This paper describes a novel genetic algorithm (GA) optimisation of the FL membership functions (MFs) for the developed control algorithm. In order to provide the GA with strong training and test scenarios, the compiled rainfall time series based on recorded rainfall and incorporating multiple events were used in the optimisation. Both decimal and integer GA optimisations were carried out. The integer optimisation was shown to perform better on unseen events than the decimal version with considerably reduced computational run time. The optimised FL MFs result in an average 25% decrease in the flood volume compared to those selected by experts for unseen rainfall events. This distributed, autonomous control using GA optimisation offers significant benefits over traditional RTC approaches for flood risk management.

Conceptual Design of an Integrated Autonomous Production Control Model in association with a Prescriptive Maintenance Model (PriMa)

Autonomous production control models facilitate coping with co-occurrent and ever-growing production system complexity. The choice of the appropriate control model and objective function in manufacturing industry depends on several interrelated factors such as machine and process flexibility, plant availability, process stability, resource utilization, environmental and economic sustainability. Numerous theoretical models and approaches for autonomous production control have been proposed. Yet, it is hard to determine the effectiveness of efforts in real-life applications, due to neglecting or incomplete consideration of the aforementioned factors. This paper concentrates on the correlative relation between production planning and control (PPC) and maintenance planning. An integrated approach is presented that establishes the link between autonomous production control and prescriptive maintenance model (PriMa). Traditionally, PPC and maintenance planning are carried out apart from one another. In the light of PriMa, various aspects of data-driven maintenance planning and the missing link with autonomous production control are discussed. To this end, this paper presents a conceptual model, which encompasses three sub-systems, namely i) maintenance system, ii) autonomous production control system, and iii) production planning. The proposed model is intended to reduce planning complexity and at the same time achieve an improved plant availability and resource efficiency.

Shipboard Landing Control Enabled by an Uncertainty and Disturbance Estimator

This paper presents an autonomous landing control approach for a quadrotor unmanned aerial vehicle subject to wind disturbance and three-dimensional movements of the landing platform. To achieve an accurate relative position estimation of the quadrotor to the landing platform, a camera, a distance sensor, and a single-board computer are integrated to the quadrotor. The coordinate transformation is introduced to deal with the constraint that only the relative position information is available. The impacts of unknown ship motions are treated as part of the lumped uncertainty terms. Then, the uncertainty and disturbance estimator-based controllers are developed to achieve the accurate relative position control of the quadrotor while dealing with unknown ship motions, ground effect, state couplings, and external disturbances. The uncertainty and disturbance estimator filter is designed based on the internal model principle to enhance the performance of the developed controller. The reference model of the relative altitude controller is modified to ensure the accurate tracking of descending commands. To maximize the capability of the developed controller, a parameter selection guideline based on the derived ship heave acceleration spectrum is provided. Both numerical simulations and flight experiments are carried out to demonstrate the effectiveness of the developed approach.

Hybrid AC/DC microgrids: A generalized approach for autonomous droop-based primary control in islanded operations

This manuscript establishes a comprehensive approach to improve the primary voltage and frequency controls in hybrid AC/DC microgrids (MGs). Dealing with the islanded operations, the proposed approach ends in an efficient autonomous power sharing task through the interlinking converter (IC). An improved droop-based power control is proposed and then applied to the IC between the AC and DC MGs. As a salient contribution, a generalized mathematical basis is established to determine the active power transfer through the IC. The founded approach portrays two prominent features namely (1): it can be readily deployed for general lines’ impedances which are interconnecting the source and loads in AC MG, and (2): the required control commands are explicitly generated only by voltage and frequency measurements at IC terminals. Moreover, to improve performance of the AC MG, the proposed approach is extended to control the reactive power contribution by IC. To obtain a general insight regarding the affecting parameters on the proposed approach, proper sensitivity studies are conducted. A typical test system is numerically analyzed to explore efficiency of the proposed approach. Results are discussed in depth.

Real-time Autonomous UAV Formation Flight with Collision and Obstacle Avoidance in Unknown Environment

In this paper autonomous formation control for Unmanned Aerial Vehicles (UAVs) has been discussed and a real time solution has been put forward by benefiting General Purpose Graphical Processing Units (GPGPU) accelerated potential field approach while ensuring obstacle and collision avoidance in unknown environment by using real-time sensors. GPGPU accelerated real time formation control for UAVs was designed and the basic model of the approach has been explained in our previous work (Cetin and Yilmaz 2014). As the deficiencies of the previous approach, autonomous real time collision and coordinated obstacle avoidance features in unknown environments are also handled while maintaining formation flight conditions in this work. With these features, improved autonomous formation control approach is discussed as a real time solution. The computation is performed by using Graphical Processing Units (GPUs) as parallel computation architectures by benefiting from Single Instruction Multiple Data (SIMD) type parallel algorithms. Classic binary map conversation, connected component labeling and minimum bounding box algorithms which are commonly used for image processing applications, has been evaluated for real time obstacle detection and avoidance features by developing GPGPU suitable parallel algorithms. Real-time solution has been developed by integrated these parallel algorithms with parallel Artificial Potential Field (APF) computation algorithm. Simulation results are proved that this novel autonomous improved formation control approach is successful and it would be used in real time applications like UAV formation flight missions.

Assessment of a new constraint satisfaction problem based active demand control approach to address distribution network constraints

The requirement of electricity market reform in smart grid comprises power supply reliability, energy price stability, and environmental friendliness sustainability, which challenges network design and control activities from distribute network operator's (DNO) perspective. Demand side management (DSM) is considered as one of the solutions for deferring network capacity reinforcement, increasing energy efficiency, addressing network constraints, and implementing low carbon energy strategies. In this study, a new real time active demand control approach is proposed to deal effectively with distribution network thermal constraints within an active network management system. The novelty consists in the application of a constraint satisfaction problem model in power flow management (PFM) to achieve DSM flexible demand objective. This approach implements DNO's direct control of demand response (DR) via the curtailment of real power consumption from the contractual demand. The control performance is based on a contractual prioritisation and preferred control depth to obtain the desired objective function of curtailment minimisation. In the simulation of the DR-PFM presented, the network thermal overload problem is relieved effectively by this new approach. This new control approach has potential to play an important role in the development of autonomous control approaches in smart grid.

Autonomous Landing of an Unmanned Aerial Vehicle using Image-Based Fuzzy Control

This paper presents a vision based autonomous landing control approach for unmanned aerial vehicles (UAV). The 3D position of an unmanned helicopter is estimated based on the homographies estimated of a known landmark. The translation and altitude estimation of the helicopter against the helipad position are the only information that is used to control the longitudinal, lateral and descend speeds of the vehicle. The control system approach consists in three Fuzzy controllers to manage the speeds of each 3D axis of the aircraft's coordinate system. The 3D position estimation was proven first, comparing it with the GPS + IMU data with very good results. The robust of the vision algorithm against occlusions was also tested. The excellent behavior of the Fuzzy control approach using the 3D position estimation based in homographies was proved in an outdoors test using a real unmanned helicopter.