Anca-Elena Iordan

The rapid advancement of robot-assisted minimally invasive surgery (RAMIS) has created an increasing demand for integrated solutions that combine advanced robotic actuation, sensing, and intelligent control within unified training and operational frameworks. This paper presents a Digital Twin–based virtual reality (VR) interaction and control system developed for an innovative parallel surgical robot, designed to support both surgical training and real-time robot interaction. The proposed framework extends a conventional VR simulator into a bidirectional Digital Twin architecture, enabling real-time synchronization between a virtual environment and the physical robotic system. The system integrates the ATHENA parallel robot, characterized by a 4-degree-of-freedom architecture with a Remote Center of Motion (RCM) constraint, together with a flexible laparoscopic instrument providing enhanced dexterity. Interaction is achieved using VR controllers, allowing intuitive manipulation of the robotic system within an immersive environment. To enhance operational performance, an artificial intelligence module based on neural networks is integrated as an assistive component, providing real-time trajectory refinement and motion guidance. The trained model is deployed using an ONNX-compatible runtime, ensuring efficient inference and seamless integration within the control architecture. The proposed system is validated through experimental evaluation of user interaction and task execution performance, as well as through external motion assessment using an OptiTrack optical tracking system. The results demonstrate improvements in motion stability, execution efficiency, and user interaction quality, while maintaining a high level of control intuitiveness. The findings highlight the potential of Digital Twin–based VR systems as a unifying platform for surgical training, interaction, and intelligent assistance in next-generation medical robotic systems.

Robust exercise recognition is essential for robot-assisted lower-limb rehabilitation, where misclassifications of sensor-derived movements can degrade therapy execution and supervision. This study proposes a novel hybrid weighted stacking ensemble to increase the efficiency of the intelligent module of the LegUp parallel robotic system for lower limb rehabilitation. The approach combines a Residual Multilayer Perceptron (ResMLP) and an optimized Kernel Extreme Learning Machine (KELM), where model hyperparameters are tuned using Optuna and the base-model probability outputs are fused through optimized weighting and a meta-learner. Experiments were conducted on a five-class dataset built from nine IMU orientation features acquired from three sensors placed on the healthy limb. Four meta-learners were evaluated (Logistic Regression, Random Forest, Gradient Boosting, and AdaBoost), with AdaBoost providing the best overall performance. To further assess the robustness and generalization capability of the proposed approach, a 5-fold cross-validation procedure was performed for the ResMLP, KELM, and the hybrid ensemble models. The proposed stacking hybrid ensemble consistently surpassed the performance of the strongest individual classifiers as well as the original LegUp Multilayer Perceptron model. These results indicate that combining residual learning with kernel-based classification in a weighted stacking framework yields a stable and high-performing solution for multi-class rehabilitation exercise recognition.

Manual alignment between the trocar, surgical instrument, and robot during minimally invasive surgery (MIS) can be time-consuming and error-prone, and many existing systems do not provide autonomous localization and pose estimation. This paper presents an artificial intelligence (AI)-assisted, vision-guided framework for automated localization and positioning of the ATHENA parallel surgical robot. The proposed approach combines an Intel RealSense RGB–depth (RGB-D) camera with a You Only Look Once version 11 (YOLO11) object detection model to estimate the 3D spatial coordinates of key surgical components in real time. The estimated coordinates are streamed over Transmission Control Protocol/Internet Protocol (TCP/IP) to a programmable logic controller (PLC) using Modbus/TCP, enabling closed-loop robot positioning for automated docking. Experimental validation in a controlled setup designed to replicate key intraoperative constraints demonstrated submillimeter positioning accuracy (≤0.8 mm), an average end-to-end latency of 67 ms, and a 42% reduction in setup time compared with manual alignment, while remaining robust under variable lighting. These results indicate that the proposed perception-to-control pipeline is a practical step toward reliable autonomous robotic docking in MIS workflows.

(1) Background: Most robotic MIS platforms lack native haptic feedback, leaving surgeons to infer tissue loads from vision alone—an especially risky limitation in esophageal procedures. (2) Methods: We develop a sensorless, image-only force-estimation pipeline that maps endoscopic video to tool–tissue forces using a lightweight EfficientNetV2B0 CNN. The model is trained on 9691 labeled frames from in vitro esophageal experiments and validated against an FT300 load cell. For intraoperative feasibility, the system is deployed as a plug-in on PARA-SILSROB, consuming the existing laparoscope feed and driving a commercial haptic device. The runtime processes every 10th frame of a 60 FPS stream (≈6 Hz updates) with ~15–20 ms per-prediction latency. (3) Results: On held-out tests, the model achieves MAE = 0.017 N and MSE = 0.0004 N², outperforming a recurrent CNN baseline while maintaining real-time performance on commodity hardware. Integrated evaluations confirm stable operation at the deployed update rate and low latency compatible with closed-loop haptics. (4) Conclusions: By avoiding distal force sensors and preserving sterile workflow, the approach is readily translatable and retrofit-friendly for current robotic platforms. The results support the practical feasibility of real-time, sensorless force feedback for robotic esophagectomy and related MIS tasks, with potential to reduce tissue trauma and enhance operative safety.

Accurately estimating the effort and duration required for software development is one of the most important challenges in the field of software engineering. In a context where software projects are becoming increasingly complex, project managers face real difficulties in meeting established deadlines and staying within budget constraints. The purpose of this research study is to identify which type of artificial neural network is most suitable for estimating the effort and duration of software development, given the relatively small size of existing datasets. In the process of software effort and duration prediction, four datasets were used: China, Desharnais, Kemerer and Maxwell. Additionally, different types of artificial neural networks were used: Multilayer Perceptron, Fractal Neural Network, Deep Fully Connected Neural Network, Extreme Learning Machine, and Hybrid Neural Network. Another goal of this research is to analyze the impact of a new and innovative hybrid architecture, which combines Fractal Neural Network with Random Forests in the estimation process. Five metrics were used to compare the accuracy of artificial neural networks: mean absolute error, median absolute error, root mean square error, coefficient of determination, and mean squared logarithmic error. Python 3.11 programming language was used in combination with TensorFlow, Keras, and Scikit-learn libraries to implement artificial neural networks.

Software effort estimation has constituted a significant research theme in recent years. The more important provocation for project managers concerns reaching their targets within the fixed time boundary. Machine learning strategies can lead software management to an entire novel stage. The purpose of this research work is to compare an optimized long short-term memory neural network, based on particle swarm optimization, with six machine learning methods used to predict software development effort: K-nearest neighbours, decision tree, random forest, gradient boosted tree, multilayer perceptron, and long short-term memory. The process of effort estimation uses five datasets: China and Desharnais, for which outputs are expressed in person-hours; and Albrecht, Kemerer, and Cocomo81, for which outputs are measured in person-months. To compare the accuracy of these intelligent methods four metrics were used: mean absolute error, median absolute error, root mean square error, and coefficient of determination. For all five datasets, based on metric values, it was concluded that the proposed optimized long short-term memory intelligent method predicts more accurately the effort required to develop a software product. Python 3.8.12 programming language was used in conjunction with the TensorFlow 2.10.0, Keras 2.10.0, and SKlearn 1.0.1 to implement these machine learning methods.

Development of object-oriented soft application is complicated, but object-oriented design together with reusable sections is even more difficult. In all likelihood design stage represents the most significant aspect that can influence the quality of educative soft application over its development process. Productively, nowadays there are a lot of design patterns whose utilisation can contribute upon disposal of a difficult issue. Choices relative to design issues taken by experienced architects are based on the newest architectural and design patterns. This chapter shows a soft application with interactive and educational features that can be used in study of shortest path determination from a graph. The development of this soft application is exquisite by usage of Model-View-Presenter architecture, but also of two design patterns: "Decorator" structural pattern and “Strategy” behavioural pattern. Soft application design is touched by way of characteristic UML diagrams marking analysis, design, and implementation stages, and for soft implementation is used C# programming language.

In recent years, drones have been widely used in various applications, from entertainment, agriculture, their use in photo and video services, military applications and so on. The risk of accidents while using a drone is quite high. To meet this risk, the most important solution is to use a device that helps and simplifies the control of a drone; in addition, the training of drone pilots is very important. To train the drone pilots, both physical and virtual environments can be used, but the probability of an accident is higher for beginners, so the safest method is to train in a virtual environment. The aim of this study is to develop a new device for controlling a drone in a virtual environment. This device is attached to the upper limb of the person involved in the control of that drone. For precise control, the newly created device uses MEMS sensor technology and artificial intelligence-specific methods.

Development of object-oriented software is hard, and reusable object-oriented software design is right more complex. The implementation needs to be proper to the problem, however also universal enough to be capable to solve ulterior requirements. In the procedure of realisation an interactive educational software, design represents presumably the most significant element that can alter its quality. Propitiously, at present there are several design patterns whose utilization can deliver a disposal of a generic problem. Design disposals of responsible architects are established by the design techniques. This chapter introduces an interactive educational software that can be used in the study of quadrilateral geometry. The study objectives consist in a refined implementation of the educational software by usage of "Factory" creational pattern and “Observer” behavioural pattern. The utilisation of factory pattern links collateral class hierarchies alike that it can locate the knowledge of which classes appertain conjunctively. The most significant benefit of using observer pattern is that this template simplifies programming process notably. The modelling of the software is achieved through specific UML diagrams representing the stages of analysis, design and implementation, and implementation is accomplished through the Java programming language.