This paper concerns the problem of dynamic modelling and parameter estimation for a seven degree of freedom hydraulic manipulator. The laboratory example is a dual–manipulator mobile robotic platform used for research into nuclear decommissioning. In contrast to earlier control model-orientated research using the same machine, the paper develops a nonlinear, mechanistic simulation model that can subsequently be used to investigate physically meaningful disturbances. The second contribution is to optimise the parameters of the new model, i.e. to determine reliable estimates of the physical parameters of a complex robotic arm which are not known in advance. To address the nonlinear and non-convex nature of the problem, the research relies on the multi-objectivisation of an output error single-performance index. The developed algorithm utilises a multi-objective genetic algorithm (GA) in order to find a proper solution. The performance of the model and the GA is evaluated using both simulated (i.e. with a known set of ‘true’ parameters) and experimental data. Both simulation and experimental results show that multi-objectivisation has improved convergence of the estimated parameters compared to the single-objective output error problem formulation. This is achieved by integrating the validation phase inside the algorithm implicitly and exploiting the inherent structure of the multi-objective GA for this specific system identification problem.

This article investigates visual servoing for a hydraulically actuated dual-arm robot, in which the user selects the object of interest from an on-screen image, whilst the computer control system implements via feedback control the required position and orientation of the manipulators. To improve on the current joystick direct tele-operation commonly used as standard in the nuclear industry, which is slow and requires extensive operator training, the proposed assisted tele-operation makes use of a single camera mounted on the robot. Focusing on pipe cutting as an example, the new system ensures that one manipulator automatically grasps the user-selected pipe, and appropriately positions the second for a cutting operation. Initial laboratory testing (using a plastic pipe) shows the efficacy of the approach for positioning the manipulators, and suggests that for both experienced and inexperienced users, the task is completed significantly faster than via tele-operation.

There has been an increase in customer churn over the past few years—customers decide not to continue purchasing products or services from an organization. Customers’ data lie in two categories: soft and hard. The term “hard data” refers to the records generated by various devices and programs, including but not limited to smartphones, computers, sensors, smart meters, fleet management systems, call detail records (CDRs), and consumer bank transaction data. On the other hand, information that is subject to interpretation and viewpoint is known as “soft data.” Fusing these two types of data leads to better customer behaviour analysis. This paper uses a supervised machine learning algorithm, namely a decision tree (DT), and the change mining method to model hard data. K-means clustering, an unsupervised machine learning algorithm, is also used along with the data preprocessing techniques. This paper also considers the Dempster-Shafer theory and other steps for soft data modelling. By fusing soft and hard data, the churn rate of customers compared with each other can be calculated. Besides, the customers’ banking data are leveraged for data modelling. The results show that the banking industry will gain a more dynamic and efficient customer relationship management system by using this model.

A novel non-singular terminal sliding mode controller (NTSMC) has been developed for the purpose of tracking and stabilizing tasks in uncertain electro-hydraulic robot manipulators. It is supposed that the controller communicates with the robot through a network that is vulnerable to cyber-attacks. To reduce the communication burden on the network layer and achieve resiliency against cyber-attacks, an event-based strategy is employed. For this purpose, the event-triggering rule is derived so that the Zeno-free behavior is guaranteed. Then, based on the cyber-attack characteristics, i.e., frequency and duration of the attacks, the resilient behavior of the proposed scheme in the presence of denial of service attacks, unmodelled dynamics, and external disturbance are analyzed. Moreover, to capture the nonlinear nature of the robot an experimentally validated analytical model of an uncertain 7-DoF manipulator with a hydraulic model of the joints and actuators, namely, Brokk-Hydrolek, is employed. Finally, the merits of the proposed methodology in terms of resiliency, robustness, and preservation of the communication resources are validated, and the results are compared to the state-of-the-art approaches based on the $\rho$ index criterion Note to Practitioners —The aim of this study is to address the problem of network-based control of robotic manipulators. These systems, relying on the network layer for data collection and control commands, are highly vulnerable to catastrophic cyber-attacks. Furthermore, they should comply with network restrictions, such as limited bandwidth, to achieve the desired performance. Therefore, due to the collaborative behavior of robot manipulators in industries, it is vital for engineers and practitioners to be assured of achieving desired performance in the presence of these threats and limitations. As a first step to deal with these issues, a 7-DoF robotic manipulator model is mathematically formulated and experimentally validated. Then, a controller design procedure that guarantees the desired performance in spite of model uncertainties, denial-of-service cyber-attacks, and network restrictions is derived. Additionally, a clear relation between cyber-attack characteristics and designed parameters is defined while resilient behavior is maintained. Note that the proposed approach can be applied to a wide range of network-based nonlinear dynamic systems.