Maria Koskinopoulou

E-waste is growing rapidly while recycling rates remain low. We propose an electronic-device Graph-based Adaptive Planning (eGRAP) that integrates vision, dynamic planning, and dual-arm execution for autonomous disassembly. A camera-equipped arm identifies parts and estimates their poses, and a directed graph encodes which parts must be removed first. A scheduler uses topological ordering of this graph to select valid next steps and assign them to two robot arms, allowing independent tasks to run in parallel. One arm carries a screwdriver (with an eye-in-hand depth camera) and the other holds or handles components. We demonstrate eGRAP on 3.5in hard drives: as parts are unscrewed and removed, the system updates its graph and plan online. Experiments show consistent full disassembly of each HDD, with high success rates and efficient cycle times, illustrating the method's ability to adaptively coordinate dual-arm tasks in real time.

Robotic waste sorting systems offer a scalable and consistent alternative to manual sorting for Construction and Demolition Waste (CDW) by reducing labor-intensive tasks and exposure to hazardous conditions, while enabling the extraction of high-purity materials (e.g., polymers) from the waste streams. Despite advancements in perception systems, manipulation and planning remain significant bottlenecks, limiting widespread adoption due to high complexity and cost. This paper introduces RaapWaste, a robot- and application-agnostic planning framework specifically designed for waste sorting, addressing challenges in motion planning, scheduling, and real-world integration. Built on open-source resources, RaapWaste employs a modular and flexible architecture, enabling integration of diverse planning techniques and scheduling strategies. The framework aims to simulate the performance of real-world sorting equipment (e.g., robots, grippers). To evaluate its effectiveness, we conducted simulations with articulated and delta robots, as well as real-world tests on CDW sorting. Metrics such as the Sorting Throughput (ST) and Sorting Ratio (SR) reveal the RaapWaste’s capability across different waste sorting cases. In simulation, the delta robot achieved an SR exceeding 95%, while the UR5e showed consistent performance. In real-world CDW experiments, the system achieved a peak SR of 99% and maintained 80% using the SPT scheduler.

In the quest for sustainable manufacturing, the integration of robotic assembly and disassembly processes has emerged as a pivotal innovation. This paper explores advancements in robotic assembly and disassembly aimed at enhancing sustainable manufacturing. Key advancements include machine learning for optimized robotic motion, advanced sensors for real-time control, and collaborative robots (cobots) for safe human-robot interaction. These technologies enable precise and efficient assembly of complex products and effective end-of-life disassembly for recycling. Case studies across various industries demonstrate significant reductions in waste, energy consumption, and environmental impact. The paper discusses current challenges and future directions, emphasizing the need for interdisciplinary collaboration and ongoing technological development to achieve fully sustainable manufacturing systems.

Introduction: This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, contributing to the Industry 4.0 paradigm. Industry 4.0, emphasizing data-driven processes, connectivity, and robotics, enhances accessibility and sustainability across the value chain. Integrating autonomous systems, including collaborative robots (cobots), into industrial workflows is crucial for improving efficiency and safety.Methods: The proposed system employs advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs), for identifying transparent plastic bags under diverse lighting and background conditions. Tracking algorithms and depth-sensing technologies are integrated to enable 3D spatial awareness during pick-and-place operations. The system incorporates vacuum gripping technology with compliance control for optimal grasping and manipulation points, using a Franka Emika robot arm.Results: The system successfully demonstrates its capability to automate the unpacking and cutting of transparent plastic bags for an 8-stack bulk-loader. Rigorous lab testing showed high accuracy in bag detection and manipulation under varying environmental conditions, as well as reliable performance in handling and processing tasks. The approach effectively addressed challenges related to transparency, plastic bag manipulation and industrial automation.Discussion: The results indicate that the proposed solution is highly effective for industrial applications requiring precision and adaptability, aligning with the principles of Industry 4.0. By combining advanced vision algorithms, depth sensing, and compliance control, the system offers a robust method for automating challenging tasks. The integration of cobots into such workflows demonstrates significant potential for enhancing efficiency, safety, and sustainability in industrial settings.

Needle intervention is widely employed in clinical practices such as biopsies, regional anesthesia, blood sampling, neurosurgery, and brachytherapy. Traditional needle insertion relies on surgeon expertise and kinesthetic feedback, yet accurately targeting deep tissue structures remains challenging. To address this, significant research has advanced sensing technologies to aid insertion accuracy. This paper comprehensively reviews recent developments in needle insertion sensing techniques, encompassing needle tip position tracking, proximity measurement, and puncture detection. It evaluates these methods across metrics including accuracy, cost-effectiveness, portability, compatibility, noise resistance capability, Technology Readiness Level (TRL), and future trends. Emerging research directions highlight advancements in machine learning integration, miniaturization, and enhanced multimodal sensing capabilities to improve procedural outcomes and expand application domains.

Globally, workplace safety is a critical concern, and statistics highlight the widespread impact of occupational hazards. According to the International Labour Organization (ILO), an estimated 2.78 million work-related fatalities occur worldwide each year, with an additional 374 million non-fatal workplace injuries and illnesses. These incidents result in significant economic and social costs, emphasizing the urgent need for effective safety measures across industries. The construction sector in particular faces substantial challenges, contributing a notable share to these statistics due to the nature of its operations. As technology, including machine vision algorithms and robotics, continues to advance, there is a growing opportunity to enhance global workplace safety standards and mitigate the human toll of occupational hazards on a broader scale. This paper explores the development and evaluation of two distinct algorithms designed for the accurate detection of safety equipment on construction sites. The first algorithm leverages the Faster R-CNN architecture, employing ResNet-50 as its backbone for robust object detection. Subsequently, the results obtained from Faster R-CNN are compared with those of the second algorithm, Few-Shot Object Detection (FsDet). The selection of FsDet is motivated by its efficiency in addressing the time-intensive process of compiling datasets for network training in object recognition. The research methodology involves training and fine-tuning both algorithms to assess their performance in safety equipment detection. Comparative analysis aims to evaluate the effectiveness of novel training methods employed in the development of these machine vision algorithms.

Subsea exploration, inspection, and intervention operations heavily rely on remotely operated vehicles (ROVs). However, the inherent complexity of the underwater environment presents significant challenges to the operators of these vehicles. This paper delves into the challenges associated with navigation and maneuvering tasks in the teleoperation of ROVs, such as reduced situational awareness and heightened teleoperator workload. To address these challenges, we introduce an underwater Digital Twin (DT) system designed to enhance underwater teleoperation, enable autonomous navigation, support system monitoring, and facilitate system testing through simulation. Our approach involves a dynamic representation of the underwater robot and its environment using desktop virtual reality, as well as the integration of mapping, localization, path planning and simulation capabilities within the DT system. Our research demonstrates the system's adaptability, versatility and feasibility, highlighting significant challenges and, in turn, improving the teleoperators' situational awareness and reducing their workload.

Intravenous Access (IVA) is the most common invasive medical procedure. Globally, it is estimated that over one billion IVA devices (needles/catheters) are used annually. However, the overall failure rate in this procedure is unacceptably high, reaching values between 35 and 50%. This has driven a great deal of research and technological development over recent decades, including the integration of different levels of autonomy in IVA medical devices to greatly improve this process. This paper will review these recent technical developments, including methods and systems for vein imaging and localization, needle insertion, venipuncture detection, catheter placement, and complete robotic IVA platforms. Furthermore, this paper explores emerging technical aspects, current limitations, and new research directions that may enable wider clinical translation and better acceptance of robotic IVA technologies.