Human–robot collaboration (HRC) is essential for improving productivity and safety across various industries. While reactive motion re-planning strategies are useful, there is a growing demand for proactive methods that predict human intentions to enable more efficient collaboration. This study addresses this need by introducing a framework that combines deep learning-based human hand trajectory forecasting with heuristic optimization for robotic task sequencing. The deep learning model advances real-time hand position forecasting using a multi-task learning loss to account for both hand positions and contact delay regression, achieving state-of-the-art performance on the Ego4D Future Hand Prediction benchmark. By integrating hand trajectory predictions into task planning, the framework offers a cohesive solution for HRC. To optimize task sequencing, the framework incorporates a Dynamic Variable Neighborhood Search (DynamicVNS) heuristic algorithm, which allows robots to pre-plan task sequences and avoid potential collisions with human hand positions. DynamicVNS provides significant computational advantages over the generalized VNS method. The framework was validated on a UR10e robot performing a visual inspection task in a HRC scenario, where the robot effectively anticipated and responded to human hand movements in a shared workspace. Experimental results highlight the system’s effectiveness and potential to enhance HRC in industrial settings by combining predictive accuracy and task planning efficiency. • We enhance hand position forecasting with a novel loss, achieving state-of-the-art results. • Our method unifies forecasting and task planning using the Dynamic TSP with Time Windows. • We enable real-time hand motion prediction and seamless integration into robot planning.

This article proposes motion planning algorithms for industrial manipulators in the presence of human operators based on deep neural networks (DNNs), aimed at imitating the behavior of a nonlinear model predictive control (NMPC) scheme. The proposed DNN solutions retain the safety features of NMPC in terms of speed and separation monitoring, defined according to the guidelines in the ISO/TS 15066 standard. At the same time, they improve the robot performance in terms of task completion time, and ofa posteriorievaluation of the NMPC cost function on experimental data. The reasons for this improvement are the reduced computational delay of running a DNN compared to solving the nonlinear programs associated to NMPC, and the ability to implicitly learn how to predict the human operator's motion from the training set.

This paper presents a new open-source mechanical design of a 6-DOF anthropomorphic ALARIS robotic hand that can serve as a low-cost design platform for further customization and utilization for research and educational purposes. The presented hand design employs linkage-based three-phalange finger and two-phalange adaptive thumb designs with non-backdrivable worm-and-rack transmission mechanisms. Combination of design improvements and solutions, discussed in the paper, are implemented in a functional robotic hand prototype with powerful grasping capabilities, which utilizes off-the-shelf inexpensive components and 3D printing technology ensuring the hand low manufacturing cost and replicability. The open-source mechanical design of the presented ALARIS robotic hand is freely available for downloading from the authors’ research lab web-site https://www.alaris.kz and https://github.com/alarisnu/alaris_hand.

Assistive robot solutions are mostly designed as robot helpers with robotic arms and aim to assist disabled and elderly people with carrying out basic activities of daily life such as reaching household objects, i.e. cups, feeding with spoon, opening a drawer/fridge doors, etc., However, commercial assistive robotic arms with joystick control require extensive and tiring hand motor skill training that limits robot's practical usage by patients with disabilities. The main objective of this work is to present the methodology for designing an intelligent human-machine interface for a commercial joystick controlled assistive robotic arm realizing shared autonomy and supervisory control modes. Preliminary results on a RGB-D based object detection and position estimation system development using publicly available YOLOv3 and CenterNet deep learning models implementation of an autonomous object grasping mode by the Kinova Jaco robotic arm are described in detail and experimentally demonstrated.

This paper presents a new approach to the solar tracking control. Today several methods are used to minimize the angle of incidence between the incoming sunlight and the photovoltaic (PV) panel. Most of them require optical solar sensor(s) to maximize energy output. There are approaches where geolocation data and the timetable of the Sun's position support a solar tracking mechanism. This paper proposes a novel sensorless (no optical or geo positioning sensors required) solar tracking mechanism based on a maximum power point tracking (MPPT) control for a mobile autonomous PV system. Such a system would provide an automatic PV panel position adjustment towards the Sun using a sensorless 3-DOF solar tracker system with a MPPT based control.

This paper presents an intelligent fault classification approach to power transformer dissolved gas analysis (DGA), dealing with highly versatile or noise-corrupted data. Bootstrap and genetic programming (GP) are implemented to improve the interpretation accuracy for DGA of power transformers. Bootstrap preprocessing is utilized to approximately equalize the sample numbers for different fault classes to improve subsequent fault classification with GP feature extraction. GP is applied to establish classification features for each class based on the collected gas data. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor ( KNN) classifiers for fault classification. The classification accuracies of the combined GP-ANN, GP-SVM, and GP-KNN classifiers are compared with the ones derived from ANN, SVM, andKNN classifiers, respectively. The test results indicate that the developed preprocessing approach can significantly improve the diagnosis accuracies for power transformer fault classification.

This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.