Search Results (82)

This paper presents a novel approach to determine dynamic safety and comfort zones in human–robot interactions (HRIs), with a focus on service robots operating in dynamic environments with people. The proposed proxemic model leverages the golden ratio-based comfort zone distribution and ISO safety standards to define adaptive proxemic boundaries for robots around humans. Unlike traditional fixed-threshold approaches, this novel method proposes a gradual and context-sensitive modulation of robot behaviour based on human position, orientation, and relative velocity. The system was implemented on an NVIDIA Jetson Xavier NX platform using a ZED 2i stereo depth camera Stereolabs, New York, USA and tested on two mobile robotic platforms: Go1 Unitree, Hangzhou, China (quadruped) and Scout Mini Agilex, Dongguan, China (wheeled). The initial verification of proposed proxemic model through experimental comfort validation was conducted using two simple interaction scenarios, and subjective feedback was collected from participants using a modified Godspeed Questionnaire Series. The results show that the participants felt comfortable during the experiments with robots. This acceptance of the proposed methodology plays an initial role in supporting further research of the methodology. The proposed solution also facilitates integration into existing navigation frameworks and opens pathways towards socially aware robotic systems. Full article

With the advancement of agricultural automation technologies, apple-harvesting robots have gradually become a focus of research. As their “perceptual core,” machine vision systems directly determine picking success rates and operational efficiency. However, existing vision systems still exhibit significant shortcomings in target detection and positioning accuracy in complex orchard environments (e.g., uneven illumination, foliage occlusion, and fruit overlap), which hinders practical applications. This study proposes a visual system for apple-harvesting robots based on improved Mask R-CNN and binocular vision to achieve more precise fruit positioning. The binocular camera (ZED2i) carried by the robot acquires dual-channel apple images. An improved Mask R-CNN is employed to implement instance segmentation of apple targets in binocular images, followed by a template-matching algorithm with parallel epipolar constraints for stereo matching. Four pairs of feature points from corresponding apples in binocular images are selected to calculate disparity and depth. Experimental results demonstrate average coefficients of variation and positioning accuracy of 5.09% and 99.61%, respectively, in binocular positioning. During harvesting operations with a self-designed apple-picking robot, the single-image processing time was 0.36 s, the average single harvesting cycle duration reached 7.7 s, and the comprehensive harvesting success rate achieved 94.3%. This work presents a novel high-precision visual positioning method for apple-harvesting robots. Full article

With the availability of multi-frequency, multi-constellation global navigation satellite system (GNSS) modules, precise transportation applications have become attainable. For transportation applications, GNSS geodetic-grade receivers can achieve an accuracy of a few centimeters to a few decimeters through differential, precise point positioning (PPP), real-time kinematic (RTK), and PPP-RTK solutions in both post-processing and real-time modes; however, these receivers are costly. Therefore, this research aims to assess the accuracy of a cost-effective multi-GNSS real-time PPP solution for transportation applications. For this purpose, the U-blox ZED-F9P module is utilized to collect dual-frequency multi-GNSS observations through a moving vehicle in a suburban area in New Aswan City, Egypt; thereafter, datasets involving different multi-GNSS combination scenarios are processed, including GPS, GPS/GLONASS, GPS/Galileo, and GPS/GLONASS/Galileo, using both RT-PPP and RTK solutions. For the RT-PPP solution, the satellite clock and orbit correction products from Bundesamt für Kartographie und Geodäsie (BKG), Centre National d’Etudes Spatiales (CNES), and the GNSS research center of Wuhan University (WHU) are applied to account for the real-time mode. Moreover, GNSS datasets from two geodetic-grade Trimble R4s receivers are collected; hence, the datasets are processed using the traditional kinematic differential solution to provide a reference solution. The results indicate that this cost-effective multi-GNSS RT-PPP solution can attain positioning accuracy within 1–3 dm, and is thus suitable for a variety of transportation applications, including intelligent transportation system (ITS), self-driving cars, and automobile navigation applications. Full article

This paper presents a self-driving system for automatic parallel parking, integrating obstacle avoidance for enhanced safety. The vehicle platform employs three primary sensors—a web camera, a Zed depth camera, and LiDAR—to perceive its surroundings, including sidewalks and potential obstacles. By processing camera and LiDAR data, the system determines the vehicle’s position and assesses parking space availability, with LiDAR also aiding in malfunction detection. The system operates in three stages: parking space identification, path planning using geometric circles, and fine-tuning with fuzzy control if misalignment is detected. Experimental results, evaluated visually in a model-scale setup, confirm the system’s ability to achieve smooth and reliable parallel parking maneuvers. Quantitative performance metrics, such as precise parking accuracy or total execution time, were not recorded in this study but will be included in future work to further support the system’s effectiveness. Full article

In application domains where severe environmental conditions are unavoidable, including high-energy physics and nuclear power plants, accurate and dependable time-to-digital converters (TDCs) are essential components. Single-event upsets (SEUs) associated with the configuration memory of field-programmable gate array (FPGA)-based implementations are becoming common sources of performance degradation even in terrestrial areas. Hence, the need to test and mitigate the effects of SEUs on FPGA-based TDCs is crucial to ensure that the design achieves reliable performance under critical conditions. The TMR SEM IP provides real-time fault injection, and dynamic SEU monitoring and correction in safety critical conditions without intervening with the functionality of the system, unlike traditional fault injection methods. This paper presents a scalable and fast fault emulation framework that tests the effects of SEUs on the configuration memory of a 5.7 ps-resolution TDC implemented on ZedBoard. The experimental results demonstrate that the standard deviation in mean bin width is 2.4964 ps for the golden TDC, but a 0.8% degradation in the deviation is observed when 3 million SEUs are injected, which corresponds to a 0.02 ps increment. Moreover, as the number of SEUs increases, the degradation in the RMS integral non-linearity (INL) of the TDC also increases, which shows 0.04 LSB (6.8%) and 0.05 LSB (8.8%) increments for 1 million and 3 million SEUs injected, respectively. The RMS differential non-linearity (DNL) of the faulty TDC with 3 million SEUs injected shows a 0.035 LSB (0.8%) increase compared to the golden TDC. Full article

This study analyzes human sleep disorders using non-contact approaches. The proposed approach analyzes periodic limb movement disorder (PLMD) under sleep conditions. This was conceptualized as data capture using a non-contact approach with ultrasonic sensors. The model was designed to estimate PLMD and classify it using real-time sleep data and a machine learning-based random forest classifier. Hardware schemes play a vital role in capturing sleep data in real time using ultrasonic sensors. A field-programmable gate array (FPGA)-based accelerator for a random forest classifier was designed to analyze PLMD. This is a novel approach that aids subjects in taking further medications. Verilog HDL was used for PLMD estimation using a Xilinx Vivado 2021.1 simulation and synthesis. The proposed method was validated using a Xilinx Zynq-7000 Zed board XC7Z020-CLG484. Full article

Pediatric gastroenterology is entering a pivotal phase marked by significant challenges and emerging opportunities in treating conditions like celiac disease (CeD), eosinophilic esophagitis (EoE), inflammatory bowel disease (IBD), and autoimmune hepatitis (AIH) pose significant clinical hurdles, but new therapeutic avenues are emerging. Advances in precision medicine, particularly proteomics, are reshaping care by tailoring treatments to individual patient characteristics. For CeD, therapies like gluten-degrading enzymes (latiglutenase, Kuma030) and zonulin inhibitors (larazotide acetate) show promise, though clinical outcomes are inconsistent. Immunotherapy and microbiota modulation, including probiotics and fecal microbiota transplantation (FMT), are also under exploration, with potential benefits in symptom management. Transglutaminase 2 inhibitors like ZED-1227 could help prevent gluten-induced damage. Monoclonal antibodies targeting immune pathways, such as AMG 714 and larazotide acetate, require further validation in pediatric populations. In EoE, biologics like dupilumab, cendakimab, dectrekumab (IL-13 inhibitors), and mepolizumab, reslizumab, and benralizumab (IL-5/IL-5R inhibitors) show varying efficacy, while thymic stromal lymphopoietin (TSLP) inhibitors like tezepelumab are also being investigated. These therapies require more pediatric-specific research to optimize their use. For IBD, biologics like vedolizumab, ustekinumab, and risankizumab, as well as small molecules like tofacitinib, etrasimod, and upadacitinib, are emerging treatments. New medications for individuals with refractory or steroid-dependent AIH have been explored. Personalized therapy, integrating precision medicine, therapeutic drug monitoring, and lifestyle changes, is increasingly guiding pediatric IBD management. This narrative review explores recent breakthroughs in treating CeD, EoE, IBD, and AIH, with a focus on pediatric studies when available, and discusses the growing role of proteomics in advancing personalized gastroenterological care. Full article

This article aims to examine the real-time precise point positioning (PPP) solution’s accuracy utilizing the low-cost dual-frequency multi-constellation U-blox ZED-F9P module and real-time GNSS orbit and clock products from five analysis centers, including Bundesamt für Kartographie und Geodäsie (BKG), Centre National d’Etudes Spatiales (CNES), International GNSS Service (IGS), Geo Forschungs Zentrum (GFZ), and GNSS research center of Wuhan University (WHU). Three-hour static quad-constellation GNSS measurements are collected from ZED-F9P modules and geodetic grade Trimble R4s receivers over a reference station in Aswan City, Egypt, for a period of three consecutive days. Since a multi-GNSS PPP processing model is applied in the majority of the previous studies, this study employs the single-constellation GNSS PPP solution to process the acquired datasets. Different single-constellation GNSS PPP scenarios are adopted, namely, GPS PPP, GLONASS PPP, Galileo PPP, and BeiDou PPP models. The obtained PPP solutions from the low-cost module are validated for the positioning and precipitable water vapor (PWV) domains. To provide a reference positioning solution, the post-processed dual-frequency geodetic-grade GNSS PPP solution is applied; additionally, as the station under investigation is not a part of the IGS reference station network, a new technique is proposed to estimate reference PWV values. The findings reveal that the GPS and Galileo 3D position’s accuracy is within the decimeter level, while it is within the meter level for both the GLONASS and BeiDou models. Additionally, millimeter-level PWV precision is obtained from the four PPP models. Full article

In this research, I introduce a water surface elevation measurement method that combines point cloud processing techniques and stereo vision cameras. While current vision-based water level measurement techniques focus on laboratory measurements or are based on auxiliary devices such as water rulers, I investigated the feasibility of measuring elevation based on images of the water surface. This research implements a monitoring system on-site, comprising a ZED 2i binocular camera (Stereolabs, San Francisco, CA, USA). First, the uncertainty of the camera is evaluated in a real measurement scenario. Then, the water surface images captured by the binocular camera are stereo matched to obtain parallax maps. Subsequently, the results of the binocular camera calibration are utilized to obtain the 3D point cloud coordinate values of the water surface image. Finally, the horizontal plane equation is solved by the RANSAC algorithm to finalize the height of the camera on the water surface. This approach is particularly significant as it offers a non-contact, shore-based solution that eliminates the need for physical water references, thereby enhancing the adaptability and efficiency of water level monitoring in challenging environments, such as remote or inaccessible areas. Within a measured elevation of 5 m, the water level measurement error is less than 2 cm. Full article

In this research, we present a novel approach for cone clustering, path planning, and path visualization in autonomous Formula Student race cars, utilizing the YOLOv8 model and a ZED 2 camera, executed on a Jetson Orin computer. Our system first identifies and then deprojects the positions of cones in space, employing an advanced clustering mechanism to generate midpoints and draw connecting lines. In previous clustering algorithms, cones were stored separately by color and connected based on relevance to create the lane edges. However, our proposed solution adopts a fundamentally different approach. Cones on the left and right sides within a dynamically changing maximum and minimum distance are connected by a central line, and the midpoint of this line is marked distinctly. Cones connected in this manner are then linked by their positions to form the edges of the track. The midpoints on these central lines are displayed as markers, facilitating the visualization of the optimal path. In our research, we also cover the analysis of the clustering algorithm on global maps. The implementation utilizes the ROS 2 framework for real-time data handling and visualization. Our results demonstrate the system’s efficiency in dynamic environments, highlighting potential advancements in the field of autonomous racing. The limitation of our approach is the dependency on precise cone detection and classification, which may be affected by environmental factors such as lighting and cone positioning. Full article

In this paper, we consider the use of high-definition maps for autonomous vehicle (AV) localization. An autonomous vehicle may have a variety of sensors, including cameras, lidars, and Global Positioning System(GPS) sensors. Each sensor technology has its own pros and cons; for example, GPS may not be very effective in a city environment with high-rise buildings; cameras may not be very effective in poorly illuminated environments; and lidars simply generate a relatively dense local point cloud. In a typical autonomous vehicle system, all of these sensors are present and sensor fusion algorithms are used to extract the most accurate information. Using our AV research vehicle, we drove on our university campus and recorded Real Time Kinematic-GPS(RTK-GPS) (ZED-F9P) and Velodyne Lidar (VLP-16) data in a time-synchronized fashion. In other words, for every GPS location on our campus, we have lidar-generated point cloud data, resulting in a simple high-definition map of the campus. The main challenge that we look to overcome in this paper is thus: given a high-definition map of the environment and local point cloud data generated by a single lidar scan, determine the AV research vehicle’s location by using point cloud “similarity” metrics. We first propose a computationally simple similarity metric and then describe a recursive Kalman filter-like approach for localization. The effectiveness of the proposed similarity metric has been demonstrated using the experimental data. Full article

Cattle farming is an important part of the global livestock industry, and cattle body size is the key indicator of livestock growth. However, traditional manual methods for measuring body sizes are not only time-consuming and labor-intensive but also incur significant costs. Meanwhile, automatic measurement techniques are prone to being affected by environmental conditions and the standing postures of livestock. To overcome these challenges, this study proposes a multi-view fusion-driven automatic measurement system for full-attitude cattle body measurements. Outdoors in natural light, three Zed2 cameras were installed covering different views of the channel. Multiple images, including RGB images, depth images, and point clouds, were automatically acquired from multiple views using the YOLOv8n algorithm. The point clouds from different views undergo multiple denoising to become local point clouds of the cattle body. The local point clouds are coarsely and finely aligned to become a complete point cloud of the cattle body. After detecting the 2D key points on the RGB image created by the YOLOv8x-pose algorithm, the 2D key points are mapped onto the 3D cattle body by combining the internal parameters of the camera and the depth values of the corresponding pixels of the depth map. Based on the mapped 3D key points, the body sizes of cows in different poses are automatically measured, including height, length, abdominal circumference, and chest circumference. In addition, support vector machines and Bézier curves are employed to rectify the missing and deformed circumference body sizes caused by environmental effects. The automatic body measurement system measured the height, length, abdominal circumference, and chest circumference of 47 Huaxi Beef Cattle, a breed native to China, and compared the results with manual measurements. The average relative errors were 2.32%, 2.27%, 3.67%, and 5.22%, respectively, when compared with manual measurements, demonstrating the feasibility and accuracy of the system. Full article

This research presents a sleep posture monitoring system designed to assist the elderly and patient attendees. Monitoring sleep posture in real time is challenging, and this approach introduces hardware-based edge computation methods. Initially, we detected the postures using minimally optimized sensing modules and fusion techniques. This was achieved based on subject (human) data at standard and adaptive levels using posture-learning processing elements (PEs). Intermittent posture evaluation was performed with respect to static and adaptive PEs. The final stage was accomplished using the learned subject posture data versus the real-time posture data using posture classification. An FPGA-based Hierarchical Binary Classifier (HBC) algorithm was developed to learn and evaluate sleep posture in real time. The IoT and display devices were used to communicate the monitored posture to attendant/support services. Posture learning and analysis were developed using customized, reconfigurable VLSI architectures for sensor fusion, control, and communication modules in static and adaptive scenarios. The proposed algorithms were coded in Verilog HDL, simulated, and synthesized using VIVADO 2017.3. A Zed Board-based field-programmable gate array (FPGA) Xilinx board was used for experimental validation. Full article

This study addresses the challenges of human–robot interactions in real-time environments with adaptive field-programmable gate array (FPGA)-based accelerators. Predicting human posture in indoor environments in confined areas is a significant challenge for service robots. The proposed approach works on two levels: the estimation of human location and the robot’s intention to serve based on the human’s location at static and adaptive positions. This paper presents three methodologies to address these challenges: binary classification to analyze static and adaptive postures for human localization in indoor environments using the sensor fusion method, adaptive Simultaneous Localization and Mapping (SLAM) for the robot to deliver the task, and human–robot implicit communication. VLSI hardware schemes are developed for the proposed method. Initially, the control unit processes real-time sensor data through PIR sensors and multiple ultrasonic sensors to analyze the human posture. Subsequently, static and adaptive human posture data are communicated to the robot via Wi-Fi. Finally, the robot performs services for humans using an adaptive SLAM-based triangulation navigation method. The experimental validation was conducted in a hospital environment. The proposed algorithms were coded in Verilog HDL, simulated, and synthesized using VIVADO 2017.3. A Zed-board-based FPGA Xilinx board was used for experimental validation. Full article

Background and Objectives: Total hip arthroplasty (THA) requires accurate implant placement to ensure optimal outcomes. In this study, the AR Hip navigation system, an imageless portable navigation tool using augmented reality (AR), was evaluated for measuring radiographic inclination (RI), anteversion (RA), leg lengthening (LL), and offset (OS) changes in supine and lateral decubitus THA. Notably, this is the first report to assess the accuracy of LL and OS measurements using AR technology. Methods: We analyzed 48 hips from primary THA patients: 17 in the supine (S) group and 31 in the lateral (L) group. RI, RA, LL, and OS were measured intraoperatively using AR Hip and postoperatively using Zed Hip 3D software (Version 18.0.0.0). The absolute errors and outlier rates (≥5° for RI/RA and ≥5 mm for LL/OS) were compared between groups. Results: The mean intraoperative RI values with AR Hip were 40.1 ± 0.6° (S), 40.2 ± 1.2° (L), and 40.1 ± 1.0° (total), while the postoperative RI values with Zed Hip were 39.7 ± 2.9° (S), 39.5 ± 2.5° (L), and 39.6 ± 2.6° (total). The absolute errors were 1.8 ± 1.7° (total), with no significant group differences (p = 0.957). For RA, the errors were 2.0 ± 1.2° (total) (p = 0.771). The LL errors were 2.3 ± 2.2 mm (total) (p = 0.271), and the OS errors were 3.5 ± 2.8 mm (total) (p = 0.620). The outlier rates for RI were 11.8% (S) and 3.2% (L); for RA, 0% (S) and 3.2% (L); for LL, 29.4% (S) and 6.5% (L) with a significant difference (p = 0.031); and for OS, 23.5% (S) and 25.8% (L). No significant differences were observed for RI, RA, or OS. Conclusions: AR Hip provided accurate measurements of cup orientation, LL, and OS in both supine and lateral THA. Importantly, this study is the first to report the accuracy of LL and OS measurements using AR technology, demonstrating the potential of AR Hip for improving THA precision. Full article