Korea Institute of Robot and Convergence

Achieving both safe contact transitions and high-performance motion tracking is essential for robots manipulating in contact-rich environments. Disturbance-observer (DOB) frameworks enable robust motion control, but achieving compliant interaction typically requires additional strategies, and prior work has paid limited attention to how acceleration estimation affects in DOB behavior. In this work, we adopt a second-order sliding-mode observer (SOSML) to obtain noise-robust, low-lag acceleration estimates and integrates them into an Impedance-Aware Disturbance Observer (IADOB). The proposed controller integrates DOB feedback with inner force control to exploit the robot’s natural inertia and rendered stiffness, enabling safe contact transitions without sacrificing motion tracking performance. Experiments on a 7-degree-of-freedom (DoF) Franka Research 3 robot demonstrate improved contact stability, and higher admissible stiffness compared to conventional impedance and momentum observer-based controllers.

Cerebrospinal fluid (CSF) continuously circulates through the brain and surrounding tissues to remove metabolic waste, a process that becomes less efficient with ageing and in neurodegenerative disease. Visualizing this drainage in living animals has been difficult because existing imaging tools either lack depth, require radioactive tracers, or are too slow to capture dynamic flow. Here, we show that whole-body photoacoustic computed tomography (PACT) enables three-dimensional, real-time tracking of CSF transport in mice using indocyanine green. We visualize CSF movement from the spinal canal into the brain, quantify its efflux under different anesthesia conditions, and detect impaired clearance in a mouse model of Alzheimer’s disease. Compared with healthy animals, diseased mice retain the tracer in the brain for several days, indicating reduced waste removal. These results establish PACT as a non-invasive platform for measuring CSF and glymphatic function in vivo, providing a way to study how brain fluid transport is altered in ageing and neurological disorders.

Purpose This study assesses linkages between financial access, female economic inclusion and environmental degradation. Design/methodology/approach The focus is on 40 Sub-Saharan African countries for the period 2010–2021. The empirical evidence is based on the generalized method of moments (GMM) and quantile regressions. Findings From the findings, positive and negative synergies are apparent from the GMM results. From the quantile regressions results: (1) financial access policy thresholds are computed when female labor force participation is employed; (2) avoidable female unemployment thresholds are apparent when the female unemployment rate is used, while (3) financial access thresholds as well as thresholds for complementary policies are computed when female employment is used. Positive (negative) synergies are apparent when female labor force participation and its interaction with financial access both have positive (negative) signs. Policy implications are discussed. Originality/value The present study has complemented the extant literature by assessing how financial access and gender economic inclusion interact to influence environmental degradation.

Inspection robots are imperative for monitoring industrial machinery like belt conveyor systems in mines and steel mills. However, gathering sufficient training data for developing an effective inspection algorithm poses a challenge. In environments characterized by safety concerns and diverse conditions, audio or vibration signals or both often prove more reliable for fault detection than visual data. However, practical data collection remains difficult due to safety, security, and environmental constraints. This study addresses the training data scarcity by exploring publicly available datasets. The likelihood of encountering novel, untrained fault sounds in real-world scenarios was considered while introducing a novel sequence-to-sequence (Seq2Seq)-based deep neural network model capable of identifying such abnormalities, particularly in belt conveyor systems. Our model aims to discern whether unfamiliar sounds are typical or anomalous, acknowledging the inherent complexity of precisely classifying unknown sounds. The training involved public datasets comprising two main categories: normal and abnormal sounds, each encompassing nine distinct types. Subsequently, we evaluated our model using separate datasets entirely distinct from the training data. Our proposed model achieved an overall accuracy of 87.53 % with untrained datasets, including four environmental sounds (two usual, two unusual) and two belt conveyor operational noises (normal and faulty). Furthermore, we implemented our algorithm in a wire-guided moving robot, ConveyorGaze, tailored for inspecting belt conveyor systems in steel mills, demonstrating the feasibility of our approach.

Abstract To reliably manipulate previously unknown objects in semi-structured environments, robots require rapid deployments and seamless transitions in pose estimation and grasping. This work proposes a novel two-stage robotic grasping method that instantly achieves accurate grasping without prior training. At the first stage, depth information and structured markers are utilized to construct compact templates for packaged targets, reducing noise and automating annotations. Then, we conduct coarse matching and design a new variant of the iterative closest point algorithm, named adaptive template-based RANSAC and iterative closest point (ATSAC-ICP), for precise point cloud registration. The method extracts locally well-registered pairs, regresses and optimizes six-degree-of-freedom (6-DOF) pose to satisfy confidence probability and precision threshold. The second stage normalizes the target pose for consistent grasp planning, which is based on scene and placement patterns. The proposed method is evaluated by several sets of experiments using various randomly selected textured objects. The results show that the pose errors are approximately ±2 mm, ±3 deg, and the successful grasping rate is over 90%. Physical experiments, conducted in different lighting conditions and with external disturbances, demonstrate effectiveness and applicability in grasping daily objects.

This article explores the advent of an innovative autonomous robot designed to enhance hospital disinfection through targeted wiping and ultraviolet-C (UV-C) irradiation methods. The urgency for such advancements has been underscored by the COVID-19 pandemic, which revealed challenges, such as low compliance rates, physical fatigue, labor shortages, and heightened risk of pathogen exposure for disinfection workers. Traditional disinfection approaches, including UV-C irradiation mobile robots and hydrogen peroxide vapor methods, while effective, fall short in addressing obstacles like shaded areas and surface contaminants. To bridge this gap, we introduce a novel robot that combines physical wiping to remove contaminants with targeted UV-C irradiation for areas less amenable to wiping. Our development efforts have centered on optimizing disinfection efficacy and ensuring the robot’s reliability for practical applications in real-world hospitals. The performance and usability of this autonomous disinfection robot were thoroughly assessed at Pohang St. Mary’s Hospital, demonstrating its potential to transform hospital disinfection practices by complementing traditional disinfection tasks with advanced robotic assistance.

In this paper, we describe research on the battery pack disassembly automation system necessary for recycling waste batteries generated due to the increase in electric vehicles. In particular, it describes the recognition process among the steps required to remove the cover of the battery pack during the automated disassembly process. The recognition process includes recognizing the battery pack through a global camera and recognizing the bolt through a local camera attached to each manipulator. In other words, the approximate location information of the bolt is obtained through the battery pack recognition process, and the exact location of the bolt is obtained using the manipulator's local camera to release the bolt. In the battery pack recognition process, the position and posture of the battery pack were estimated by matching point cloud data through the ICP(Iterative Closet Point) algorithm. The bolt recognition process was learned using the yolo v5 model, and the recognition rate was increased by classifying and tagging misrecognized objects into different classes.