Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0121
Hyeon-Seo Kim, Byeong-Woo Cho, Byungjeon Kang
Accurate identification of landmarks is critical for effective diagnosis and treatment in endoscopy, particularly in the upper gastrointestinal tract. However, there are many similar structures inside the stomach, and it might be difficult to accurately locate landmarks in camera images because of other factors such as air bubbles and the narrow field of view of wired endoscopic images. This study presents a comparative analysis experiment conducted with a model that can identify anatomical landmarks of the upper gastrointestinal tract with high accuracy through small-scale data-based local augmentation. We used five classes captured by esophagogastroduodenoscopy criterion, preprocessed medical image data to address the class imbalance, and compared the accuracies of ResNet50, MobileNetV2, and DensNet265 models. We used a dataset comprising 2,546 images of patients who underwent upper gastrointestinal endoscopy at Yonsei Severance Hospital. We augmented 4,632 images and evenly distributed them across five classes. Our results indicate that this is the most accurate model for improving diagnosis and treatment in upper gastrointestinal endoscopy. The ReseNet50 model achieved the highest accuracy at 74.88%, followed by the MobileNetV2 model at 78.91% and DensNet265 at 84.70%.
{"title":"Deep Learning-based Landmark Identification for the Upper Gastrointestinal Track in Endoscopic Images","authors":"Hyeon-Seo Kim, Byeong-Woo Cho, Byungjeon Kang","doi":"10.5302/j.icros.2023.23.0121","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0121","url":null,"abstract":"Accurate identification of landmarks is critical for effective diagnosis and treatment in endoscopy, particularly in the upper gastrointestinal tract. However, there are many similar structures inside the stomach, and it might be difficult to accurately locate landmarks in camera images because of other factors such as air bubbles and the narrow field of view of wired endoscopic images. This study presents a comparative analysis experiment conducted with a model that can identify anatomical landmarks of the upper gastrointestinal tract with high accuracy through small-scale data-based local augmentation. We used five classes captured by esophagogastroduodenoscopy criterion, preprocessed medical image data to address the class imbalance, and compared the accuracies of ResNet50, MobileNetV2, and DensNet265 models. We used a dataset comprising 2,546 images of patients who underwent upper gastrointestinal endoscopy at Yonsei Severance Hospital. We augmented 4,632 images and evenly distributed them across five classes. Our results indicate that this is the most accurate model for improving diagnosis and treatment in upper gastrointestinal endoscopy. The ReseNet50 model achieved the highest accuracy at 74.88%, followed by the MobileNetV2 model at 78.91% and DensNet265 at 84.70%.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0134
Janghan Kim, Hyung-Seok Park, Kyung-Joon Park
Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) have been actively employed for tasks that are challenging for humans, such as scenarios like battlefield and disaster. Swarm unmanned systems, comprising UAVs and UGVs, experience dynamic additions or removals of unmanned aircraft. In this paper, we propose a rule caching-based recovery technique for achieving rapid forwarding rule establishment for additional UAVs deployed for recovery in wireless Software-defined Networking (SDN) based swarm unmanned systems. To validate the proposed algorithm, we conducted experiments by setting up a testbed using ODROID and a controller. Our results demonstrate that the proposed algorithm improves forwarding rule establishment performance by up to 50.3%.
{"title":"Fast Routing With Rule Caching in Lossy Mobile SDN","authors":"Janghan Kim, Hyung-Seok Park, Kyung-Joon Park","doi":"10.5302/j.icros.2023.23.0134","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0134","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) have been actively employed for tasks that are challenging for humans, such as scenarios like battlefield and disaster. Swarm unmanned systems, comprising UAVs and UGVs, experience dynamic additions or removals of unmanned aircraft. In this paper, we propose a rule caching-based recovery technique for achieving rapid forwarding rule establishment for additional UAVs deployed for recovery in wireless Software-defined Networking (SDN) based swarm unmanned systems. To validate the proposed algorithm, we conducted experiments by setting up a testbed using ODROID and a controller. Our results demonstrate that the proposed algorithm improves forwarding rule establishment performance by up to 50.3%.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0129
Bumjin Park, Cheongwoong Kang, Jaesik Choi
{"title":"Message Passing With Gating Mechanisms in Multi-agent Reinforcement Learning","authors":"Bumjin Park, Cheongwoong Kang, Jaesik Choi","doi":"10.5302/j.icros.2023.23.0129","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0129","url":null,"abstract":"","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.22.8013
Byeongseon Choi, Jaebyung Park
Using robots to guide humans in large and complex environments has been a longstanding research topic in robotics. Two technical factors for guide robots: 1) stable mobility and 2) human-robot interaction capability. This study introduces a hospital guide robot with improvements in these areas. We first constructed the robot’s mechanical and electrical systems. To achieve stable mobility, we analyzed the kinematics of the robot and implemented a pose estimation algorithm using a sensor fusion technique. Secondly, we developed the “Hospital Guidance System” software to enhance the human-robot interaction capability. Using a quick response code-based system, hospital visitors can seamlessly access medical care and guidance. We conducted experiments to validate the robot’s ability to provide hospital guidance services based on pre-defined scenarios.
{"title":"Development of Hospital Guide Robot With Stable Mobility and Improved Human-robot Interaction","authors":"Byeongseon Choi, Jaebyung Park","doi":"10.5302/j.icros.2023.22.8013","DOIUrl":"https://doi.org/10.5302/j.icros.2023.22.8013","url":null,"abstract":"Using robots to guide humans in large and complex environments has been a longstanding research topic in robotics. Two technical factors for guide robots: 1) stable mobility and 2) human-robot interaction capability. This study introduces a hospital guide robot with improvements in these areas. We first constructed the robot’s mechanical and electrical systems. To achieve stable mobility, we analyzed the kinematics of the robot and implemented a pose estimation algorithm using a sensor fusion technique. Secondly, we developed the “Hospital Guidance System” software to enhance the human-robot interaction capability. Using a quick response code-based system, hospital visitors can seamlessly access medical care and guidance. We conducted experiments to validate the robot’s ability to provide hospital guidance services based on pre-defined scenarios.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0067
Ho-Ju Ryu, Jeong-Ku Kim, Seul Jung
{"title":"A Study of Comparing Deep Neural Networks for Classifying Driver Steering Characteristics","authors":"Ho-Ju Ryu, Jeong-Ku Kim, Seul Jung","doi":"10.5302/j.icros.2023.23.0067","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0067","url":null,"abstract":"","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0131
Dong-Hyun Park, Jong-seo Kim, Jae-Hyeon Park, Dong-Eui Chang
As the use of robots such as unmanned aerial vehicles (UAVs), unmanned ground vehicles, and robot arms in industry and leisure continues to grow, it becomes increasingly important to maintain these robots in a stable condition to prevent potential danger, including actuator, sensor, and system faults. Consequently, researchers have developed various algorithms to address these faults. In this study, we propose a deep learning-based fault recovery system designed to ensure the safe flight of UAVs in situations where position sensors freeze. When a position sensor freezing event is detected, this fault recovery system rectifies the issue by enabling the UAV to utilize values from a long short-term memory-based position prediction model, thus replacing the frozen sensor data. We tested our fault recovery system with a UAV in a Gazebo simulation and validated its effectiveness by comparing it with an inertial measurement unit kinematic model-based fault recovery system. The proposed deep learning-based fault recovery system demonstrated superior performance.
{"title":"A Deep Learning-based Fault Recovery System for Safe Flight of UAV in the Position Sensor Freezing Situation","authors":"Dong-Hyun Park, Jong-seo Kim, Jae-Hyeon Park, Dong-Eui Chang","doi":"10.5302/j.icros.2023.23.0131","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0131","url":null,"abstract":"As the use of robots such as unmanned aerial vehicles (UAVs), unmanned ground vehicles, and robot arms in industry and leisure continues to grow, it becomes increasingly important to maintain these robots in a stable condition to prevent potential danger, including actuator, sensor, and system faults. Consequently, researchers have developed various algorithms to address these faults. In this study, we propose a deep learning-based fault recovery system designed to ensure the safe flight of UAVs in situations where position sensors freeze. When a position sensor freezing event is detected, this fault recovery system rectifies the issue by enabling the UAV to utilize values from a long short-term memory-based position prediction model, thus replacing the frozen sensor data. We tested our fault recovery system with a UAV in a Gazebo simulation and validated its effectiveness by comparing it with an inertial measurement unit kinematic model-based fault recovery system. The proposed deep learning-based fault recovery system demonstrated superior performance.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a new navigation algorithm that integrates a magnetic pose estimation system (MPS), an IMU, and a range sensor to provide stable navigation performance in unstructured indoor environment. Moreover, we implement a real-time navigation system to apply these navigation algorithms to aerial vehicle. In this paper, the magnetic field vector is modeled using an algorithm called MPS, and the position and attitude are estimated through the least squares method. However, while analyzing the results of this system, it was confirmed that navigation performance deteriorated due to magnetic field distortion in an unstructured indoor environment. To improve these limitations, we present a new type of EKF (Extended Kalman Filter) algorithm that integrates an MPS, an IMU and a range sensor. Finally, in order to verify the algorithm proposed in this paper, a real-time navigation system is designed, and ground and flight experiments are conducted.
{"title":"Design and Real-time Performance Verification of MPS/INS/Range Navigation System under Indoor Magnetic Distortion","authors":"Jae-Hyun Yun, Dae-Hyun Jung, Byungjin Lee, Sangkyung Sung","doi":"10.5302/j.icros.2023.23.0103","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0103","url":null,"abstract":"This paper proposes a new navigation algorithm that integrates a magnetic pose estimation system (MPS), an IMU, and a range sensor to provide stable navigation performance in unstructured indoor environment. Moreover, we implement a real-time navigation system to apply these navigation algorithms to aerial vehicle. In this paper, the magnetic field vector is modeled using an algorithm called MPS, and the position and attitude are estimated through the least squares method. However, while analyzing the results of this system, it was confirmed that navigation performance deteriorated due to magnetic field distortion in an unstructured indoor environment. To improve these limitations, we present a new type of EKF (Extended Kalman Filter) algorithm that integrates an MPS, an IMU and a range sensor. Finally, in order to verify the algorithm proposed in this paper, a real-time navigation system is designed, and ground and flight experiments are conducted.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0119
Cheol-Hoon Park, Hyun-Duck Choi
{"title":"Enhanced Parallel sparse-MLP for Monocular Depth Estimation of Autonomous UAV","authors":"Cheol-Hoon Park, Hyun-Duck Choi","doi":"10.5302/j.icros.2023.23.0119","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0119","url":null,"abstract":"","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"36 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0066
Min-Chang Kim, Eder Guerra Padilla Giancarlo, Kee-Ho Yu
{"title":"Flight Path Planning Method for UAM Considering Urban Airflow Based on A* Algorithm","authors":"Min-Chang Kim, Eder Guerra Padilla Giancarlo, Kee-Ho Yu","doi":"10.5302/j.icros.2023.23.0066","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0066","url":null,"abstract":"","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"35 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.5302/j.icros.2023.23.0135
Junho Choi, Christiansen Marsim Kevin, Myeongwoo Jeong, Kihwan Ryoo, Jeewon Kim, Hyun Myung
Multi-robot state estimation is crucial for real-time and accurate operation, especially in complex environments where a global navigation satellite system cannot be used. Many researchers employ multiple sensor modalities, including cameras, LiDAR, and ultra-wideband (UWB), to achieve real-time state estimation. However, each sensor has specific requirements that might limit its usage. While LiDAR sensors demand a high payload capacity, camera sensors must have matching image features between robots, and UWB sensors require known fixed anchor locations for accurate positioning. This study introduces a robust localization system with a minimal sensor setup that eliminates the need for the previously mentioned requirements. We used an anchor-free UWB setup to establish a global coordinate system, unifying all robots. Each robot performs visual-inertial odometry to estimate its ego-motion in its local coordinate system. By optimizing the local odometry from each robot using inter-robot range measurements, the positions of the robots can be robustly estimated without relying on an extensive sensor setup or infrastructure. Our method offers a simple yet effective solution for achieving accurate and real-time multi-robot state estimation in challenging environments without relying on traditional sensor requirements.
{"title":"Multi-unmanned Aerial Vehicle Pose Estimation Based on Visual-inertial-range Sensor Fusion","authors":"Junho Choi, Christiansen Marsim Kevin, Myeongwoo Jeong, Kihwan Ryoo, Jeewon Kim, Hyun Myung","doi":"10.5302/j.icros.2023.23.0135","DOIUrl":"https://doi.org/10.5302/j.icros.2023.23.0135","url":null,"abstract":"Multi-robot state estimation is crucial for real-time and accurate operation, especially in complex environments where a global navigation satellite system cannot be used. Many researchers employ multiple sensor modalities, including cameras, LiDAR, and ultra-wideband (UWB), to achieve real-time state estimation. However, each sensor has specific requirements that might limit its usage. While LiDAR sensors demand a high payload capacity, camera sensors must have matching image features between robots, and UWB sensors require known fixed anchor locations for accurate positioning. This study introduces a robust localization system with a minimal sensor setup that eliminates the need for the previously mentioned requirements. We used an anchor-free UWB setup to establish a global coordinate system, unifying all robots. Each robot performs visual-inertial odometry to estimate its ego-motion in its local coordinate system. By optimizing the local odometry from each robot using inter-robot range measurements, the positions of the robots can be robustly estimated without relying on an extensive sensor setup or infrastructure. Our method offers a simple yet effective solution for achieving accurate and real-time multi-robot state estimation in challenging environments without relying on traditional sensor requirements.","PeriodicalId":38644,"journal":{"name":"Journal of Institute of Control, Robotics and Systems","volume":"36 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136227443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：