In this article, we address the critical challenge of vibration control of flexible long-reach robot manipulators used in nuclear decommissioning. The research is motivated by the urgent need to ensure precision and safety during the deployment of robotic systems in confined and hazardous environments, such as the through-wall deployment (TWD) system for the Sellafield nuclear site. The TWD system, featuring a rigid manipulator on a flexible two-link boom, is designed to maneuver through small openings in containment vessels. While this design avoids the need for bulky structures, the slenderness of the boom makes it prone to significant vibrations, potentially compromising the system's stability and accuracy. To address these challenges, we propose a novel real-time flexible control system that suppresses vibrations using only the robot manipulator's own actuation, without requiring additional actuators. The control strategy is based on the mixed-sensitivity H-infinity synthesis for a dedicated dynamics model via inertial sensing, enhancing the robustness and adaptability over the multimodal flexibilities. Experimental validation demonstrated the control system's effectiveness in reducing vibrations, thereby improving operational efficiency and safety. These findings have broader implications for deploying flexible, intelligent control systems in other high-stakes environments, such as the Fukushima Daiichi site, where similar vibration-related challenges are encountered.

This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the performance of one individual system to beyond so-called human baselines. However, these systems often look at one shot and one-way decisions, whereas the real world is more continuous and interactive. Humans, however, are often able to recover from and learn from errors - enabling a much higher rate of success. We look at the challenges of building a system that can detect/recover from its own errors, using the example of robotic nuclear gloveboxes as a use case to help illustrate examples. We then go on to talk about simple starting designs.

Rapid advancement of digital technologies has resulted in an acceleration of cyber–physical systems for autonomous mobile robots to improve energy asset management activities within inspection, maintenance and repair. Within this systems-based approach, the role of the human-in-the-loop has also increased leading to cyber–physical-human systems requiring real-time interaction of robotics and digital twins with a human operator. Subject to existing network systems and physical systems, cyber–physical-human systems face enormous challenges requiring further investigation. This review presents the state-of-the-art in discovery, design, development and deployment of cyber–physical-human systems for mobile robots in energy asset management. To address dominant concepts and misconceptions in this area, key terminologies, system concepts and applications are presented. Then a state-of-the-art review with associated trends for several applications within academic and industrial sectors is presented where current practises and limitations are then discussed. Finally, future opportunities are explored alongside highlighted concepts providing a pathway for rapid adoption and improved key performance indicators of mobile fleets for facility operators and those in the wider community.

The history around teleoperation and deployment of robotic systems in constrained and dangerous environments such as nuclear is a long and successful one. From the 1940s, robotic manipulators have been used to manipulate dangerous substances and enable work in environments either too dangerous or impossible to be operated by human operators. Through the decades, technical and scientific advances have improved the capabilities of these devices, whilst allowing for more tasks to be performed. In the case of nuclear decommissioning, using such devices for remote inspection and remote handling has become the only solution to work and survey some areas. Such applications deal with challenging environments due to space constrains, lack of up-to-date structural knowledge of the environment and poor visibility, requiring much training and planning to succeed. There is a growing need to speed these deployment processes and to increase the number of decommissioning activities whilst maintaining high levels of safety and performance. Considering the large number of research and innovation being done around improving robotic capabilities, numerous potential benefits could be made by translating them to the nuclear decommissioning use cases. We believe such innovations, in particular improved feedback mechanisms from the environment during training and deployments (i.e., Haptic Digital Twins) and higher modes of assisted or supervised control (i.e., Semi-autonomous operation) can play a large role. We list some of the best practices currently being followed in the industry around teleoperation and robotic deployments and the potential benefits of implementing the aforementioned innovations.

Active 3D scene representation is pivotal in modern robotics applications, including remote inspection, manipulation, and telepresence. Traditional methods primarily optimize geometric fidelity or rendering accuracy, but often overlook operator-specific objectives, such as safety-critical coverage or task-driven viewpoints. This limitation leads to suboptimal viewpoint selection, particularly in constrained environments such as nuclear decommissioning. To bridge this gap, we introduce a novel framework that integrates expert operator preferences into the active 3D scene representation pipeline. Specifically, we employ Reinforcement Learning from Human Feedback (RLHF) to guide robotic path planning, reshaping the reward function based on expert input. To capture operator-specific priorities, we conduct interactive choice experiments that evaluate user preferences in 3D scene representation. We validate our framework using a UR3e robotic arm for reactor tile inspection in a nuclear decommissioning scenario. Compared to baseline methods, our approach enhances scene representation while optimizing trajectory efficiency. The RLHF-based policy consistently outperforms random selection, prioritizing task-critical details. By unifying explicit 3D geometric modeling with implicit human-in-the-loop optimization, this work establishes a foundation for adaptive, safety-critical robotic perception systems, paving the way for enhanced automation in nuclear decommissioning, remote maintenance, and other high-risk environments.

In hazardous environments like nuclear facilities, robotic systems are essential for executing tasks that would otherwise expose humans to dangerous radiation levels, which pose severe health risks and can be fatal. However, many operations in the nuclear environment require teleoperating robots, resulting in a significant cognitive load on operators as well as physical strain over extended periods of time. To address this challenge, we propose enhancing the teleoperation system with an assistive model capable of predicting operator intentions and dynamically adapting to their needs. The machine learning model processes robotic arm force data, analyzing spatiotemporal patterns to accurately detect the ongoing task before its completion. To support this approach, we collected a diverse dataset from teleoperation experiments involving glovebox tasks in nuclear applications. This dataset encompasses heterogeneous spatiotemporal data captured from the teleoperation system. We employ a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model to learn and forecast operator intentions based on the spatiotemporal data. By accurately predicting these intentions, the robot can execute tasks more efficiently and effectively, requiring minimal input from the operator. Our experiments validated the model using the dataset, focusing on tasks such as radiation surveys and object grasping. The proposed approach demonstrated an F1-score of 89% for task classification and an F1-score of 86% classification forecasted operator intentions over a 5-second window. These results highlight the potential of our method to improve the safety, precision, and efficiency of robotic operations in hazardous environments, thereby significantly reducing human radiation exposure.

This paper reports the use of electro-optical (EO) probes in mapping electric field in known high voltage (HV) geometries (plane-plane and sphere-sphere). The measurements are performed autonomously with the use of a robotic arm and the development of an automatic data acquisition unit. The measured electric field profiles were then compared with finite element analysis (FEA) models calculated in COMSOL software and showed a good agreement with COMSOL. This work is part of the de-risking of non-contact electric field measurements for identifying defects on live cap and pin insulator strings on HV towers.

In current telerobotics and telemanipulator applications, operators must perform a wide variety of tasks, often with a high risk associated with failure. A system designed to generate data-based behavioural estimations using observed operator features could be used to reduce risks in industrial teleoperation. This paper describes a non-invasive bio-mechanical feature capture method for teleoperators used to trial novel human-error rate estimators which, in future work, are intended to improve operational safety by providing behavioural and postural feedback to the operator. Operator monitoring studies were conducted in situ using the MASCOT teleoperation system at UKAEA RACE; the operators were given controlled tasks to complete during observation. Building upon existing works for vehicle-driver intention estimation and robotic surgery operator analysis, we used 3D point-cloud data capture using a commercially available depth camera to estimate an operator’s skeletal pose. A total of 14 operators were observed and recorded for a total of approximately 8 h, each completing a baseline task and a task designed to induce detectable but safe collisions. Skeletal pose was estimated, collision statistics were recorded, and questionnaire-based psychological assessments were made, providing a database of qualitative and quantitative data. We then trialled data-driven analysis by using statistical and machine learning regression techniques (SVR) to estimate collision rates. We further perform and present an input variable sensitivity analysis for our selected features.

The use of wireless communication within the civil nuclear industry can bring many benefits over wired solutions, such as reducing lifecycle costs and enabling new applications in asset and process management. This paper will discuss aspects of wireless communication in industrial control systems, i.e. termed wireless control systems, of the civil nuclear industry. In this respect, we will review previous use of wireless communication in the nuclear industry, and provide the results of a recent feasibility study of wireless communication for an industrial, civil nuclear control system. The studied use case was of an advanced nuclear modular reactor, the Stable Salt Reactor (SSR), and the augmentation of one of its control systems, the refuelling control system, with wireless communication. Hence, in contrast to previous work on wireless control systems, this paper here will focus on the complex and rigorous processes required for regulated safety which have to be followed to allow for wireless control to be implemented in the nuclear civil sector. The following analysis and design procedure was followed: (a) the decision process for choosing the refuelling control system, (b) the review for a suitable communication protocol and technology, the analysis for placement of wireless transceivers for sensors and actuators, (c) the analysis for wireless communication integrity, (d) the basic analysis and guidelines for control system robustness under packet loss, (e) the discussion of possible self-powering options and (f) the safety analysis of the control system under communication failure. Our initial hypothesis is that wireless control systems in Nuclear Applications can improve asset integrity. Control systems can be made more robust and secure to external influences by securely communicating control responses and asset information within a Nuclear Plant. Safety is also improved by reducing the number of operator interactions required for servicing connections, as failures are reduced overall. The removal of power/data harnesses from in-reactor applications can enable faster deployment and replacement of instrumentation for new builds, existing plants and decommissioning.

Nuclear fusion laboratories typically require advanced teleoperation systems for maintenance, repair, and experimentation within the extreme conditions of fusion reactors. Operators of these systems must perform a wide variety of tasks, often with a high risk associated with failure; therefore, insight into operator behaviors and influencing factors could be used to reduce risks in industrial teleoperation. This study analyses and discusses the relationships between several operator factors and objective task performance metrics in teleoperation tasks at the JET fusion laboratory in UKAEA RACE. The primary aims of this study are to identify and analyze factors that predict task performance metrics, to examine measures for validity, and to validate the study design. Data were collected from 13 MAnipolatore Servo COntrollato Transistorizzato (MASCOT) teleoperators performing tasks as a part of a training exercise. Relationships between metrics were analyzed using correlational and regression analysis, as well as standard statistical tools for data screening and assessment. Study results indicate that operator sleepiness and experience are significant predictors of reported performance, and that operators can reliably self-evaluate task performance accurately. These results suggest that the task design is suitably sensitive to an operator's ability and, therefore, can be used for meaningful analysis, and implies that this skill-based test is a valid method of operationalizing operator performance. This study highlights areas for further research by indicating significant factor relationships and validates aspects of the study design, informing research and development strategies for enhancing human-robot interactions and teleoperation system design.

The nuclear energy sector can benefit from mobile robots for remote inspection and handling, reducing human exposure to radiation.Advances in cyber-physical systems have improved robotic platforms in this sector through digital twin (DT) technology.DTs enhance situational awareness for robot operators, crucial for safety in the nuclear energy sector, and their value is anticipated to increase with the growing complexity of cyber-physical systems.The primary motivation of this work is to rapidly develop and evaluate a robot fleet interface that accounts for these benefits in the context of nuclear environments.Here, we introduce a multimodal immersive DT platform for cyber-physical robot fleets based on the ROS-Unity 3D framework.The system design enables fleet monitoring and management by integrating building information models, mission parameters, robot sensor data, and multimodal user interaction through traditional and virtual reality interfaces.A modified heuristic evaluation approach, which accounts for the positive and negative aspects of the interface, was introduced to accelerate the iterative design process of our DT platform.Robot operators from leading nuclear research institutions (Sellafield Ltd. and the Japan Atomic Energy Agency) performed a simulated robot inspection mission while providing valuable insights into the design elements of the cyber-physical system.The three usability themes that emerged and inspired our design recommendations for future developers include increasing the interface's flexibility, considering each robot's individuality, and adapting the platform to expand sensor visualization capabilities.

Fault Detection and Isolation (FDI) is of great interest for the control community since it can drive improved performance in a system by allowing predictive maintenance/repairing and catering for improved operational safety. Fault Detection and Isolation in large-scale smelting furnaces presents several challenges, as it requires the understanding of complex thermal and chemical reactions occurring inside the structure. Furthermore, the impossibility of having full operational information about the process makes the use of model-based methods very complex or unfeasible. This paper introduces a methodology to develop a Data-Driven FDI system for the detection of incipient and intermittent failures in a network made out of 322 thermocouples located on the shell of the furnace. Statistical metrics over Fault Counter Time Windows (FTCW) were used to identify different types of sensor failures, which led to establishing a baseline of known failure events and to create a dataset to train the Machine Learning (ML) classification models. A data-driven approach was proposed based on the sensors physical (neighbouring) redundancy, which led to some type of physical redundancy. A post-processing stage was used to stabilize the model’s response in time, determining that the proposed FDI system successfully detects faults whilst reducing reported false negatives.

Simulation of pedestrians in shared spaces poses a significant challenge in autonomous driving virtual testing. The simulation pedestrian model can respond to autonomous vehicle behaviour changes. We present HFPM: a Hierarchical Forecasting Pedestrian Model to imitate pedestrian behaviour. The model has three layers: the dynamics model layer, the path planning layer, and the decision layer. In the dynamics model layer, an improved force model with the heading direction of the pedestrian is developed based on the Social Force Model, which can model pedestrian-pedestrian interaction. In the path planning layer, an Artificial Potential Field model is modified to plan a feasible path to the individual goals. The planning layer has a prediction module to predict the trajectory of vehicles on the road in order to choose the best route with no collision. The decision layer is a finite state machine with five states: the pedestrian can approach, walk, wait, run and reach the goal. The resulting HFPM model can produce more accurate simulation results than previously developed policy-based models, as demonstrated through qualitative and quantitative comparisons with a baseline pedestrian model obtained from the CITR data set.

We address the unique challenge of vibration suppression for a flexible long-reach robotic manipulator system, namely, the through-wall deployment (TWD) system that is used in nuclear environments. This paper proposes a novel dynamics-based trajectory optimization approach, which minimizes both the acceleration and the jerk at the manipulator’s joints, as well as the vibrations of the flexible long-reach boom where the manipulator’s base is mounted. Firstly, we create an integrated model for the system dynamics based on the knowledge of the robotic manipulator and the acceleration data from the vibration tests. We then develop an original procedure for generating the high-order polynomial trajectory that guarantees the zero-boundary condition for a flexible number of optimization parameters and waypoints. Following the simulation of a multi-objective optimization scheme, the optimized trajectory is experimentally validated on the practical TWD system with around 28% vibration reduction on average compared to the benchmark. Importantly, this reduction is achieved without compromising on the average speed of motion. The methodology is transferable to a wider range of flexible robotic manipulator systems with similar characteristics.

Teleoperating mobile manipulator (MM) robots using a single ground-based haptic (GBH) device is challenging due to differences in workspaces and mechanical structures. A hybrid control scheme combines navigation and manipulation modes to operate a robot using manual or automatic mode switching. Although an automatic scheme tends to reduce the user’s mental workload, in some cases, the bilateral teleoperation system loses transparency when interacting with the environment; in others, the interaction with the environment may happen in inappropriate operation mode without the user’s awareness. To overcome those challenges, this paper proposes a new hybrid control scheme for bilateral teleoperation of holonomic MM robots. In this scheme, while navigating, the user’s hand motion is restricted by an artificial force to prevent reaching the boundary of the GBH device’s workspace. When the end-effector touches the environment, a method not requiring any exteroceptive sensor automatically switches the operation mode to manipulation mode. After completing the remote task, the user must switch to navigation mode manually. The simulation results indicate that the baseline bubble technique, a widely used automatic scheme, creates over 50

Calcines' chemical composition analysis is a key process in ferronickel smelting. These values allow for a clear understanding of the smelted product's expected quality, catering for any required chemical upgrading of the raw material or modification in the furnace's set-point if the calcine has undesired characteristics. Offline tests for calcines' chemical composition can take several days, potentially delaying the whole operation. A data-driven approach to chemical composition classification using on-line data is proposed by combining clustering classification through a mixed Principal Component Analysis (PCA) model, data processing and standardization process, with a Machine Learning classification algorithm, i.e. Extreme Gradient Boosting (XGBoost). This allows for an online prediction of calcines' chemical composition based on the furnace's current operating conditions. The proposed method's accuracy scored mean values between 82.1% and 85.9%, which is encouraging in comparison with other proposed methods.

Nuclear facilities have a regulatory requirement to measure radiation levels within Post Operational Clean Out (POCO) around nuclear facilities each year, resulting in a trend towards robotic deployments to gain an improved understanding during nuclear decommissioning phases. The UK Nuclear Decommissioning Authority supports the view that human‐in‐the‐loop (HITL) robotic deployments are a solution to improve procedures and reduce risks within radiation characterisation of nuclear sites. The authors present a novel implementation of a Cyber‐Physical System (CPS) deployed in an analogue nuclear environment, comprised of a multi‐robot (MR) team coordinated by a HITL operator through a digital twin interface. The development of the CPS created efficient partnerships across systems including robots, digital systems and human. This was presented as a multi‐staged mission within an inspection scenario for the heterogeneous Symbiotic Multi‐Robot Fleet (SMuRF). Symbiotic interactions were achieved across the SMuRF where robots utilised automated collaborative governance to work together, where a single robot would face challenges in full characterisation of radiation. Key contributions include the demonstration of symbiotic autonomy and query‐based learning of an autonomous mission supporting scalable autonomy and autonomy as a service. The coordination of the CPS was a success and displayed further challenges and improvements related to future MR fleets.

Tele-manipulation is indispensable for the nuclear industry since teleoperated robots cancel the radiation hazard problem for the operator. The majority of the teleoperated solutions used in the nuclear industry rely on bilateral teleoperation, utilizing a variation of the 4-channel architecture, where the motion and force signals of the local and remote robots are exchanged in the communication channel. However, the performance limitation of teleoperated robots for nuclear decommissioning tasks is not clearly answered in the literature. In this study, we assess the task performance in bilateral tele-manipulation for radiation surveying in gloveboxes and compare it to radiation surveying of a glovebox operator. To analyze the performance, an experimental setup suitable for human operation (manual operation) and tele-manipulation is designed. Our results showed that a current commercial off-the-shelf (COTS) teleoperated robotic manipulation solution is flexible, yet insufficient, as its task performance is significantly lower when compared to manual operation and potentially hazardous for the equipment inside the glovebox. Finally, we propose a set of potential solutions, derived from both our observations and expert interviews, that could improve the performance of teleoperation systems in glovebox environments in future work.