DEEPCOBOT Collective Efficient Deep Learning and Networked Control for Multiple Collaborative Robot Systems

• Vinod, Dinsha & Zhou, Jing (2026). Adaptive Event-Triggered Control for Uncertain Polytopic NLPV Systems: An Application in Robotic Vision. IEEE transactions on industrial electronics (1982. Print). ISSN 0278-0046. 73(6), s. 9245–9255. doi: 10.1109/tie.2026.3651341. Fulltekst i vitenarkiv Vis sammendrag

  This article presents the design of an adaptive event-triggered mechanism (AETM) for a specific class of uncertain polytopic nonlinear parameter-varying (NLPV) systems with Lipschitz nonlinearity. The primary objective of the proposed control design is to ensure the D-stability of the nominal system while concurrently minimizing the frequency of control updates with flexible design requirements. This is achieved by leveraging the principles of Lyapunov functions and linear matrix inequalities (LMIs). The efficacy of the developed control framework is validated on a mobile robot integrated with a distributed fog computing platform (DFCP) within the context of warehouse applications. The experimental findings substantiate the effectiveness of the control theory in auto-scaling the fog computing nodes for processing the vision data acquired from a mobile robot within the service time constraints.

• Østerholt, Lars; Gundersen, Are; Zhou, Jing & Hagen, Daniel (2025). Real-Time Markerless Vision-Based Control of Knuckle Boom Cranes via Embedded AI. International Conference on Control, Mechatronics and Automation. ISSN 2837-5114. 2025. doi: 10.1109/iccma67641.2025.11369496. Fulltekst i vitenarkiv Vis sammendrag

  This paper presents a load-handling system for a knuckle boom crane, integrating edge-AI-based computer vision, real-time control, and Screw theory kinematics. Utilizing YOLOv6-N for object detection and a camera-driven control system, the approach enables payload navigation in industrial environments without external markers. Key contributions include a markerless vision-based framework, real-time PLC implementation for control, and experimental validation of autonomous navigation across four distinct landing zones, demonstrating robust performance in dynamic settings. All without the need for external infrastructure. The system’s design minimizes setup complexity and enhances adaptability to diverse conditions.

• Vinod, Dinsha & Zhou, Jing (2025). Adaptive event-triggered control for resource-based auto-scaling of an uncertain distributed fog computing platform. Proceedings of the Annual Conference of the IEEE Industrial Electronics Society (IECON). ISSN 1553-572X. doi: 10.1109/iecon58223.2025.11221340. Fulltekst i vitenarkiv Vis sammendrag

  This paper investigates the design of an adaptive event-triggered controller to facilitate the efficient auto-scaling of the distributed fog computing platform (DFP), while meticulously considering resource constraints, disturbances, and uncertainties. A data-driven discrete polytopic linear parameter-varying (PLPV) model effectively addresses the service requirements of DFP with time-varying characteristics. The controller gains are formulated utilizing linear matrix inequalities (LMIs) to guarantee the DR stability of the system. Finally, the results are experimentally validated on a DFP to offload the images from an autonomous mobile robot (AMR) specifically designed for vision applications in a warehouse environment. Furthermore, the validation results are systematically compared to a static event-triggered control approach for discrete PLPV systems.

• Zhu, Mingda; Eidsvik, Johannes Arnesen; Landsverk, Ronny; Hagen, Daniel & Zhou, Jing (2025). Rapid Model-Based Design and Real-Time Digital Twin Integration: An Offshore Robot Case Study. Proceedings of the IEEE International Symposium on Industrial Electronics. s. 1–6. doi: 10.1109/isie62713.2025.11124748. Fulltekst i vitenarkiv Vis sammendrag

  The rapid advancement of digitalization has led to the widespread adoption of digital twins across various industries. While digital twins have demonstrated significant potential in many applications, challenges remain in their implementation, particularly in real-time control. Therefore, this paper addresses the challenges by proposing a DT-based method for fast prototyping of real-time control in medium-scale industrial robots, leveraging rapid model-based design. With Speedgoat and the User Datagram Protocol communication protocol, the proposed approach enables real-time data exchange and control execution. The effectiveness of the method is demonstrated through four case studies by utilizing the Comau robot at the Norwegian Motion Laboratory.

• Zhu, Mingda; Han, Peihua; Landsverk, Ronny; Strandene, Jan Christian Bjerke; Hagen, Daniel & Zhou, Jing (2025). A Data-driven Approach to Payload Heave Motion Prediction under Irregular Waves, IEEE Industrial Electronics Society Annual On-Line Conference (ONCON). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350357981. doi: 10.1109/ONCON62778.2024.10931669. Fulltekst i vitenarkiv Vis sammendrag

  Effective handling of the payload with an offshore crane is critical for ensuring safety and efficiency in the offshore operation. Accurate modelling of payload heave motion is essential for safeguarding transportation and improving feedback control for active heave compensation. Traditional kinematic modelling fails to account for the nonlinear dynamics of waveinduced motion. This paper proposes a data-driven method,leveraging real motion data from the Norwegian Motion Lab, to predict payload heave positions based on ship heave positions. Extensive experiments are carried out using a diverse dataset under various sea states, and the proposed method is evaluated against three methods from different disciplines. The results demonstrate that the data-driven approach outperforms the compared methods, showing a better overall performance across multiple wave scenarios.

• Schlanbusch, Siri Marte; Zhou, Jing & Schlanbusch, Rune (2025). Quantized Predictor-Based Tracking Control for Input Delay Systems: Application to a Helicopter System. IEEE Conference on Decision and Control. Proceedings. ISSN 0743-1546. doi: https:/ieeexplore.ieee.org/document/10886553. Fulltekst i vitenarkiv Vis sammendrag

  In this paper, the tracking control problem is studied for systems with quantized signals and communication delays. A bounded type of quantizer is introduced to reduce the communication transmission burden, where both control inputs and states are quantized. A predictor-feedback controller is designed to compensate for delays in the inputs, while boundedness of the tracking errors are achieved and practical stability is ensured. An application to a helicopter system is presented to show the effectiveness of the proposed predictor-based controller in a closed-loop configuration, and to illustrate the main findings.

• Zhu, Mingda; Nguyen, Hoang Nam Du; Han, Peihua; Zhou, Jing & Huynh, van Khang (2025). A Semi-Supervised Variational Autoencoder for Fault Detection of Low-Severity Inter-Turn Short-Circuit in PMSMs, 2025 IEEE Workshop on Electrical Machines Design, Control and Diagnosis - WEMDCD. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331520748. doi: 10.1109/WEMDCD61816.2025.11014178. Fulltekst i vitenarkiv Vis sammendrag

  Maintenance has been critical in energy and marine systems, ensuring safety, reliability and efficiency. Fault detection, a cornerstone of prognostics and health management systems, faces challenges due to limited faulty data. This study proposes a semi-supervised Variational Autoencoder (VAE) with Long Short-Term Memory Networks for fault detection. The method is demonstrated via an example of low-severity inter-turn short-circuit faults in permanent magnet synchronous machines. Trained only on healthy data, the model can generate anomaly scores based on the VAE's reconstruction error. The model is tested on time-series current data under varying conditions, achieving high detection accuracy. Comparative analysis shows its superiority over traditional methods such as One-Class Support Vector Machine, Isolation Forest and Autoencoder.

• Sveen, Emil Mühlbradt; Zhou, Jing; Ebbesen, Morten Kjeld & Poursina, Mohammad (2025). Decentralised adaptive learning-based control of robot manipulators with unknown parameters. Journal of Automation and Intelligence (JAI). 4(2), s. 136–144. doi: 10.1016/j.jai.2025.02.002. Fulltekst i vitenarkiv Vis sammendrag

  This paper studies motor joint control of a 4-degree-of-freedom (DoF) robotic manipulator using learning-based Adaptive Dynamic Programming (ADP) approach. The manipulator’s dynamics are modelled as an open-loop 4-link serial kinematic chain with 4 Degrees of Freedom (DoF). Decentralised optimal controllers are designed for each link using ADP approach based on a set of cost matrices and data collected from exploration trajectories. The proposed control strategy employs an off-line, off-policy iterative approach to derive four optimal control policies, one for each joint, under exploration strategies. The objective of the controller is to control the position of each joint. Simulation and experimental results show that four independent optimal controllers are found, each under similar exploration strategies, and the proposed ADP approach successfully yields optimal linear control policies despite the presence of these complexities. The experimental results conducted on the Quanser Qarm robotic platform demonstrate the effectiveness of the proposed ADP controllers in handling significant dynamic nonlinearities, such as actuation limitations, output saturation, and filter delays.

• Vinod, Dinsha & Zhou, Jing (2025). Event-Based Control for Discrete Polytopic LPV Systems With AI Inference. IEEE transactions on industrial electronics (1982. Print). ISSN 0278-0046. 72(9), s. 9497–9507. doi: 10.1109/TIE.2025.3536560. Fulltekst i vitenarkiv Vis sammendrag

  This article presents an in-depth exploration of event-based control schemes, focusing on event-triggered control (ETC) and self-triggered control (STC) for discrete polytopic linear parameter-varying (LPV) systems with time-varying characteristics. The primary objective of the proposed ETC design is to ensure optimal system performance while minimizing the frequency of control updates. The article first introduces a standard ETC algorithm for discrete-time polytopic LPV systems, leveraging a parameter-varying Lyapunov function. Subsequently, a dynamic ETC algorithm is proposed to extend the inter-event time (IET) associated with the standard ETC. Furthermore, standard and dynamic STC algorithms are developed for the polytopic LPV systems to reduce the periodic sampling by evaluating the subsequent control update based on the preceding triggered state. The control gains are designed using multiobjective linear matrix inequalities (LMIs). Lastly, the efficacy of the developed control theory is demonstrated through its implementation on a distributed fog computing platform (DFCP) in warehouse applications. The experimental results demonstrate the effectiveness of auto-scaling fog computing nodes in processing vision data obtained from a mobile robot operating within a warehouse environment subject to service time constraints.

• Nama, Ajay Nagendra; Beferull-Lozano, Baltasar; Saad, Leila Ben & Zhou, Jing (2024). Node-Variant Graph Filter Based Multi-Agent Deep Reinforcement Learning for Aligned Game and Wireless Environments. IEEE Conference on Industrial Electronics and Applications. 19. doi: 10.1109/ICIEA61579.2024.10665191. Fulltekst i vitenarkiv
• Sveen, Emil Mühlbradt & Zhou, Jing (2024). Learning Based Adaptive Dynamic Programming of a Four-Bar Mechanism with Linear Approximation. IEEE Conference on Industrial Electronics and Applications. doi: 10.1109/ICIEA61579.2024.10665201. Fulltekst i vitenarkiv Vis sammendrag

  This paper investigates the use of a learning-based approach of Adaptive Dynamic Programming (ADP) on a highly nonlinear four-bar mechanism which uses simple initial evaluation of nonlinear dynamics to increase both controller performance and robustness of algorithm convergence. This approach is based on the assumption of a gravity-induced moment on the crank, with an empirically identified stable equilibrium that is used as a linearising approximation in a state feedback signal. Previous work related to this study shows significant algorithm convergence boundedness, especially related to the initial crank position. In the results, a convergence analysis is provided with a direct relation to this of previous work, and further investigations of controller methods are also provided to evaluate the efficiency of the linear approximation. The results, when compared to the previous study related to the four-bar mechanism and learning-based ADP, show that, although simple and approximate, the presented case can significantly reduce the boundedness of the system and algorithm parameters that was previously found to be most important for convergence failure when using ADP on nonlinear systems.

• Singh, Jayant; Zhou, Jing; Beferull-Lozano, Baltasar; Yan, Shijun & Khan, Shalman (2024). Haptic Teleoperation Framework for Learning Task Space Fine Manipulation Skills. IEEE Conference on Industrial Electronics and Applications. doi: 10.1109/ICIEA61579.2024.10665270. Fulltekst i vitenarkiv Vis sammendrag

  This paper introduces a framework for teaching robot fine-manipulation skills by combining haptic teleoperation with Probabilistic Movement Primitives (ProMPs). Addressing the challenges of executing precise tasks such as snap-joint manipulation, our framework utilises ROS2 alongside a cartesian compliance controller for task space operation. This setup facilitates the intuitive guidance of robots by human operators, capturing the detailed movements critical for fine-manipulation tasks. Through experiments with the UR5e 6-DOF collaborative robot arm and a 3DSystems Touch haptic device, we illustrate the accurate representation and replication of the human demonstrated tasks.

• Vinod, Dinsha & Zhou, Jing (2024). An event-triggered MPC scheme for discrete pLPV systems: Application in auto-scaling of compute nodes in a fog cluster. Proceedings of the Annual Conference of the IEEE Industrial Electronics Society (IECON). ISSN 1553-572X. s. 1–6. doi: https:/ieeexplore.ieee.org/document/10906025. Fulltekst i vitenarkiv Vis sammendrag

  This paper proposes a control-theoretic approach for discrete polytopic linear parameter varying (pLPV) systems with time-varying characteristics. The approach employs event-triggered model predictive control (ET-MPC) to uphold the performance while minimising the frequency of controller updates. Initially, a model predictive control (MPC) is designed to predict the system’s dynamics in the future. An event-triggering mechanism is also incorporated in the design, which uses a parameter-varying Lyapunov function to lessen the burden of online optimization. The design of an ET-MPC is based on the global stability and feasibility of the pLPV system. Finally, the control-theoretic approach is experimentally validated on a distributed fog computing platform to enable the auto-scaling of compute nodes for mobile robot vision applications.

Se alle arbeider i NVA

• Zhou, Jing (2024). 2024 IEEE 19th Conference on Industrial Electronics and Applications (ICIEA). IEEE (Institute of Electrical and Electronics Engineers). ISBN 9798350360868. 2000 s. Fulltekst i vitenarkiv

Se alle arbeider i NVA

• Wathne, Joakim Holtskog; Hansen, Michael Rygaard & Zhou, Jing (2025). Benefits of Secondary Control over Primary Control for AHC Winches. Fulltekst i vitenarkiv
• Zhou, Jing (2025). Data-driven control and applications. doi: https:/irce.org/2025.html. Fulltekst i vitenarkiv
• Zhou, Jing (2025). Adaptive Control with Quantization. doi: https:/ecc25.euca-ecc.org/. Fulltekst i vitenarkiv Vis sammendrag

  In control engineering, information and sensing technologies are essential components of real-time measurement systems, providing variable resolution quantitative measurements in control systems, such as in electric power grid systems, intelligent transportation systems, vehicle coordination systems, and offshore mechatronics. Typically, these control systems rely on communication channels. An important aspect is to use quantization schemes with sufficient precision while maintaining low communication rates.This talk explores the challenges and advancements in quantized control, focusing on the theoretical foundations of stability analysis and the interplay between quantization and control system design. Specifically, it addresses the adaptive control of dynamic systems in the presence of uncertainties, nonlinear dynamics, and quantization. The discussion highlights how adaptive design and Lyapunov-based analysis can be applied systematically to mitigate, offering a unified and systematic framework for tackling these challenges.

• Zhou, Jing (2025). Data-Driven Adaptive and Quantized Control - Theory and Applications. doi: https:/ieeexplore.ieee.org/xpl/conhome/1835066/all-proceedings. Fulltekst i vitenarkiv
• Hagen, Daniel (2025). Rapid Model-Based Design and Real-Time Digital Twin Integration: An Offshore Robot Case Study. doi: 10.1109/isie62713.2025.11124748. Fulltekst i vitenarkiv
• Gaustad, Eskil Gresen; Knausgård, Kristian Muri & Zhou, Jing (2025). Supervisory Control Design for a SES Vessel. Universitetet i Agder. Fulltekst i vitenarkiv

Se alle arbeider i NVA