Pub Date : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649945
Hyo-chan Lee, Heoncheol Lee
When facial masks are produced, various types of defects may appear on mask filters. These defects may include the hair of the inspectors and unexpected raw materials in the production processes. This paper proposes a new method for detecting anomaly regardless of the size and shape of defects. The proposed method uses two-step image processing to detect anomaly. The first step is to use Average Blurring on the mask filter image for image blurring. The most important thing in this step is the kernel size of the Average Blurring is increased to extend the pixel value with defects to the surrounding pixels. In the second step, the Pearson correlation coefficient between the normal mask filter image and the input mask filter image is used according to kernel size. The larger the kernel size of Average Blurring, the lower their correlation coefficient. If the correlation coefficient at a particular kernel size is lower than the threshold value, it is decided as defective image.
{"title":"Average Blurring-based Anomaly Detection for Vision-based Mask Inspection Systems","authors":"Hyo-chan Lee, Heoncheol Lee","doi":"10.23919/ICCAS52745.2021.9649945","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649945","url":null,"abstract":"When facial masks are produced, various types of defects may appear on mask filters. These defects may include the hair of the inspectors and unexpected raw materials in the production processes. This paper proposes a new method for detecting anomaly regardless of the size and shape of defects. The proposed method uses two-step image processing to detect anomaly. The first step is to use Average Blurring on the mask filter image for image blurring. The most important thing in this step is the kernel size of the Average Blurring is increased to extend the pixel value with defects to the surrounding pixels. In the second step, the Pearson correlation coefficient between the normal mask filter image and the input mask filter image is used according to kernel size. The larger the kernel size of Average Blurring, the lower their correlation coefficient. If the correlation coefficient at a particular kernel size is lower than the threshold value, it is decided as defective image.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114173882","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649976
Soori Im, Donghoon Kim, Hoiyoung Cheon, J. Ryu
Unmanned Surface Vehicle(USV) is a promising solution for missions that happened on the ocean such as patrolling, rescuing. It is necessary to detect obstacles for autonomous navigation. However, marine radar has some limitations, which is normally used for USV. Low update rates and the dead band for the local area concerning sensors are weak points, so that USV can hardly cope with close obstacles with high speed. Compares to marine radar, FMCW radar has opposite features. Hight update rates and available for close obstacle detection. This paper proposes an algorithm for detecting close obstacles with FMCW radar using the clustering method. Suggested algorithm compute spatial data from the Range-Doppler map given by FMCW radar. And apply Density-based spatial clustering of applications with noise(DBSCAN) algorithm considering radar energy signal level. Using radar data, the algorithm computes representative clusters and track the clusters with the Nearest Neighbor algorithm. This paper also shows the field experiment result of the proposed algorithm with USV. The field experiment is conducted in Chungcheongnam-do Taean Coastal Pier with USV called Sea Sword III. The results show obstacles are well detected and USV behaves collision avoidance.
{"title":"Object Detection and Tracking System with Improved DBSCAN Clustering using Radar on Unmanned Surface Vehicle","authors":"Soori Im, Donghoon Kim, Hoiyoung Cheon, J. Ryu","doi":"10.23919/ICCAS52745.2021.9649976","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649976","url":null,"abstract":"Unmanned Surface Vehicle(USV) is a promising solution for missions that happened on the ocean such as patrolling, rescuing. It is necessary to detect obstacles for autonomous navigation. However, marine radar has some limitations, which is normally used for USV. Low update rates and the dead band for the local area concerning sensors are weak points, so that USV can hardly cope with close obstacles with high speed. Compares to marine radar, FMCW radar has opposite features. Hight update rates and available for close obstacle detection. This paper proposes an algorithm for detecting close obstacles with FMCW radar using the clustering method. Suggested algorithm compute spatial data from the Range-Doppler map given by FMCW radar. And apply Density-based spatial clustering of applications with noise(DBSCAN) algorithm considering radar energy signal level. Using radar data, the algorithm computes representative clusters and track the clusters with the Nearest Neighbor algorithm. This paper also shows the field experiment result of the proposed algorithm with USV. The field experiment is conducted in Chungcheongnam-do Taean Coastal Pier with USV called Sea Sword III. The results show obstacles are well detected and USV behaves collision avoidance.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"114 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113977530","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649762
Seongbin An, Hyunjin Choi, Kyoungchul Kong
In many research areas, such as biomedical engineering, rehabilitation medicine, and sports science, electromyography (EMG) is used as a key indicator of muscle activity. While EMG provides information about active muscle activation, it does not provide information on passive activation. Muscle contraction is the result of active and passive actuation. Muscle contractions are directly related to muscle strength and provide a general understanding of muscle performance. In this paper, a real-time muscle contraction observation method using pneumatic myography (pMMG) is introduced. A modular system was developed to measure pMMG wirelessly for comparison with EMG signals. As a result, the proposed method allowed observation of activation-independent muscle contractions, including manual contractions/extensions or stationary contractions. Experimental results of real-time terminal swing phase detection of gait using the proposed methodology were also introduced.
{"title":"Development of Wireless Pneumatic Myography Sensor for Real-time Muscle Contraction Measurement","authors":"Seongbin An, Hyunjin Choi, Kyoungchul Kong","doi":"10.23919/ICCAS52745.2021.9649762","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649762","url":null,"abstract":"In many research areas, such as biomedical engineering, rehabilitation medicine, and sports science, electromyography (EMG) is used as a key indicator of muscle activity. While EMG provides information about active muscle activation, it does not provide information on passive activation. Muscle contraction is the result of active and passive actuation. Muscle contractions are directly related to muscle strength and provide a general understanding of muscle performance. In this paper, a real-time muscle contraction observation method using pneumatic myography (pMMG) is introduced. A modular system was developed to measure pMMG wirelessly for comparison with EMG signals. As a result, the proposed method allowed observation of activation-independent muscle contractions, including manual contractions/extensions or stationary contractions. Experimental results of real-time terminal swing phase detection of gait using the proposed methodology were also introduced.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114814146","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9650049
T. Kano, Liang Li, N. Ko, Woong Choi
In recent years, declining birth rates and aging populations had become more serious in developed countries such as Europe, the United States, and Asian countries, including Japan. Therefore, in this research, we focused on mahjong, which was effective in preventing dementia. However, it was difficult for beginners and even intermediate players to proceed with the game instantly because mahjong has complicated yaku (hand), and the calculation of scores using them is even more complicated. Therefore, we were developing a mahjong progression support system using computer vision aiming at helping players with dementia who have difficulty in calculating mahjong scores. Since simple learning did not produce results that could be used in the proposed system, we achieved significant results by changing the size of the mahjong tiles in the images to be learned, and the system is now able to calculate mahjong scores from the images of mahjong tiles.
{"title":"Calculation of Mahjong Score using AI","authors":"T. Kano, Liang Li, N. Ko, Woong Choi","doi":"10.23919/ICCAS52745.2021.9650049","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9650049","url":null,"abstract":"In recent years, declining birth rates and aging populations had become more serious in developed countries such as Europe, the United States, and Asian countries, including Japan. Therefore, in this research, we focused on mahjong, which was effective in preventing dementia. However, it was difficult for beginners and even intermediate players to proceed with the game instantly because mahjong has complicated yaku (hand), and the calculation of scores using them is even more complicated. Therefore, we were developing a mahjong progression support system using computer vision aiming at helping players with dementia who have difficulty in calculating mahjong scores. Since simple learning did not produce results that could be used in the proposed system, we achieved significant results by changing the size of the mahjong tiles in the images to be learned, and the system is now able to calculate mahjong scores from the images of mahjong tiles.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124311650","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649829
Gyuho Eoh, T. Park
This paper presents a deep reinforcement learning (DRL)-based object transportation technique using a region-partitioning curriculum. Previous studies on object transportation using DRL algorithms have suffered a sparse reward problem where a robot cannot gain success experiences frequently due to random actions at the learning stage. To solve the sparse reward problem, we partition pose-initialization regions based on the distance between an object and goal, then a robot gradually extends the partitioned regions as training episodes increase. The robot has more success opportunities using this method, and thus, it can learn effective object transportation methods quickly. We demonstrate simulations to verify the proposed method.
{"title":"Curriculum Learning-based Object Transportation using Region Partitioning","authors":"Gyuho Eoh, T. Park","doi":"10.23919/ICCAS52745.2021.9649829","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649829","url":null,"abstract":"This paper presents a deep reinforcement learning (DRL)-based object transportation technique using a region-partitioning curriculum. Previous studies on object transportation using DRL algorithms have suffered a sparse reward problem where a robot cannot gain success experiences frequently due to random actions at the learning stage. To solve the sparse reward problem, we partition pose-initialization regions based on the distance between an object and goal, then a robot gradually extends the partitioned regions as training episodes increase. The robot has more success opportunities using this method, and thus, it can learn effective object transportation methods quickly. We demonstrate simulations to verify the proposed method.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123992878","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649779
D. Kato, N. Maeda, T. Hirogaki, E. Aoyama, K. Takahashi
Most industrial robots are unsuitable for variable production systems because they are taught using the teaching playback method. In contrast, the offline teaching method has been developed, but it has not progressed because of the low positioning accuracy. Therefore, several studies have proposed methods to calibrate for positioning errors using neural networks. However, it is difficult to identify the factors of positioning errors because the structure of neural networks is not clear. Herein, we applied the random forest method, which is a type of machine learning method, and constructed a prediction model for positioning errors. A large industrial robot was used, and three-dimensional coordinates of the end-effector were obtained using a laser tracker. The model to predict the positioning error from end-effector coordinates, joint angles, and joint torques was constructed using the random forest method, and the positioning error was predicted with high accuracy. The random forest analysis demonstrated that joint 2 was the primary factor of the X. and Z-axis errors. This suggested that the air cylinder used as an auxiliary to the servo motor of joint 2 was the error factor. The positioning error norm was reduced at all points using the proposed calibration.
{"title":"Position Calibration Method for Large size Industrial Robots Based on Random Forest","authors":"D. Kato, N. Maeda, T. Hirogaki, E. Aoyama, K. Takahashi","doi":"10.23919/ICCAS52745.2021.9649779","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649779","url":null,"abstract":"Most industrial robots are unsuitable for variable production systems because they are taught using the teaching playback method. In contrast, the offline teaching method has been developed, but it has not progressed because of the low positioning accuracy. Therefore, several studies have proposed methods to calibrate for positioning errors using neural networks. However, it is difficult to identify the factors of positioning errors because the structure of neural networks is not clear. Herein, we applied the random forest method, which is a type of machine learning method, and constructed a prediction model for positioning errors. A large industrial robot was used, and three-dimensional coordinates of the end-effector were obtained using a laser tracker. The model to predict the positioning error from end-effector coordinates, joint angles, and joint torques was constructed using the random forest method, and the positioning error was predicted with high accuracy. The random forest analysis demonstrated that joint 2 was the primary factor of the X. and Z-axis errors. This suggested that the air cylinder used as an auxiliary to the servo motor of joint 2 was the error factor. The positioning error norm was reduced at all points using the proposed calibration.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124078847","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649751
H. Seren, E. Buzi, M. Deffenbaugh
Downhole tools used in the oil and gas industry are usually controlled by an operator and tethered to the surface equipment via a few kilometers of long steel cable. Due to the total weight and volume of this steel cable, operating downhole tools requires a truck for transportation, winch, crane, and lubricator for placing into a well, and full time supervision by a trained crew. The large footprint of the operations brings time and cost inefficiency even when the task can be as simple as measuring the pressure and temperature downhole. There is a big opportunity to apply robotics and automation technologies to increase the efficiency of wellsite operations. Currently, robots have limited use in downhole applications mainly because of harsh environment and challenging working space. There are a number of robotic extensions designed as attachments to the tethered tools that can work semi-autonomously. By means of miniaturization and automation, it's possible to make an untethered downhole robot that can significantly reduce the operation footprint and increase time and cost efficiency. Here, we show a miniature untethered well logging robot that can autonomously travel and measure temperature and pressure. A key to miniaturization was to reduce energy consumption. Robots use their energy storage predominantly for locomotion. We exploited potential energies arising from gravity and buoyancy for the passively moving the robot inside vertical wells. We investigated the passive locomotion design considerations to avoid downhole obstacles.
{"title":"Autonomous Well Logging Robot with Passive Locomotion","authors":"H. Seren, E. Buzi, M. Deffenbaugh","doi":"10.23919/ICCAS52745.2021.9649751","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649751","url":null,"abstract":"Downhole tools used in the oil and gas industry are usually controlled by an operator and tethered to the surface equipment via a few kilometers of long steel cable. Due to the total weight and volume of this steel cable, operating downhole tools requires a truck for transportation, winch, crane, and lubricator for placing into a well, and full time supervision by a trained crew. The large footprint of the operations brings time and cost inefficiency even when the task can be as simple as measuring the pressure and temperature downhole. There is a big opportunity to apply robotics and automation technologies to increase the efficiency of wellsite operations. Currently, robots have limited use in downhole applications mainly because of harsh environment and challenging working space. There are a number of robotic extensions designed as attachments to the tethered tools that can work semi-autonomously. By means of miniaturization and automation, it's possible to make an untethered downhole robot that can significantly reduce the operation footprint and increase time and cost efficiency. Here, we show a miniature untethered well logging robot that can autonomously travel and measure temperature and pressure. A key to miniaturization was to reduce energy consumption. Robots use their energy storage predominantly for locomotion. We exploited potential energies arising from gravity and buoyancy for the passively moving the robot inside vertical wells. We investigated the passive locomotion design considerations to avoid downhole obstacles.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"2003 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126353915","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649926
Nwe Zin Oo, P. Chaikan
Today's modern computers support multi-core processors architecture that enhances parallel computing with single instruction multiple data computing. According to memory structure, the CPU core performance is a vital role in power-saving profiling across the multi-core architecture. Although CPU parking was controlled entirely by the operating system of both laptops and desktops computers, the performance can be boost by tweaking CPU core parking and changing frequency scaling in real-time. In this paper, the effect of core parking for parallel matrix-matrix multiplication on shared memory is proposed by utilizing AVX and OpenMP. When the large matrix sizes are multiplied parallelly on shared memory, the overheads of memory capacity and data transferring become the main issues not only for increased power consumption but also for decrease performance. The large square matrix multiplications are tested that range from 1024×1024 to 16384×16384 by utilizing Advanced Vector Extensions (AVX) intrinsics and OpenMP, and varying the different power-saving profiling dynamically. The default power-saving profile in a computer is the balanced mode and we tested for performance by tweaking CPU parking with four different modes (Balanced, High Performance, Bitsum Highest Performance, and Power Saving). According to tested results, the Bitsum Highest Performance mode obtained the maximum performance and minimum power and energy consumption than other profiling modes.
{"title":"The Effect of Core Parking for Energy-efficient Matrix-Matrix Multiplication by using AVX and OpenMP","authors":"Nwe Zin Oo, P. Chaikan","doi":"10.23919/ICCAS52745.2021.9649926","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649926","url":null,"abstract":"Today's modern computers support multi-core processors architecture that enhances parallel computing with single instruction multiple data computing. According to memory structure, the CPU core performance is a vital role in power-saving profiling across the multi-core architecture. Although CPU parking was controlled entirely by the operating system of both laptops and desktops computers, the performance can be boost by tweaking CPU core parking and changing frequency scaling in real-time. In this paper, the effect of core parking for parallel matrix-matrix multiplication on shared memory is proposed by utilizing AVX and OpenMP. When the large matrix sizes are multiplied parallelly on shared memory, the overheads of memory capacity and data transferring become the main issues not only for increased power consumption but also for decrease performance. The large square matrix multiplications are tested that range from 1024×1024 to 16384×16384 by utilizing Advanced Vector Extensions (AVX) intrinsics and OpenMP, and varying the different power-saving profiling dynamically. The default power-saving profile in a computer is the balanced mode and we tested for performance by tweaking CPU parking with four different modes (Balanced, High Performance, Bitsum Highest Performance, and Power Saving). According to tested results, the Bitsum Highest Performance mode obtained the maximum performance and minimum power and energy consumption than other profiling modes.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126534914","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 : 2021-10-12DOI: 10.1299/jsmermd.2021.1p1-g03
Koichiro Kato, Yukihiro Nakamura, N. Matsuhira, M. Narita
In this study, we developed a robot teleoperation function using a robot service network protocol (RSNP) unit and common operation interface, and experimented using 12 robots. From the teleoperation screen on the web page, the robot can be remotely controlled by buttons while checking the camera image on the robot side. We have confirmed that RSNP communication can be introduced by connecting the developed RSNP unit to the robots in various ways. This allowed us to remotely control not only mobile robots but also communication robots, robot arms, and various other robots from a common communication method and operation screen. In addition, the experiment confirmed the teleoperation of 12 robots and 17 operators. However, the operation method was not sufficient because there was no feedback of the operation amount on the operation screen. We will continue to improve the remote-control system to make it easier for an operator to control robot systems.
{"title":"Remote control experiment of multiple robots using RSNP unit","authors":"Koichiro Kato, Yukihiro Nakamura, N. Matsuhira, M. Narita","doi":"10.1299/jsmermd.2021.1p1-g03","DOIUrl":"https://doi.org/10.1299/jsmermd.2021.1p1-g03","url":null,"abstract":"In this study, we developed a robot teleoperation function using a robot service network protocol (RSNP) unit and common operation interface, and experimented using 12 robots. From the teleoperation screen on the web page, the robot can be remotely controlled by buttons while checking the camera image on the robot side. We have confirmed that RSNP communication can be introduced by connecting the developed RSNP unit to the robots in various ways. This allowed us to remotely control not only mobile robots but also communication robots, robot arms, and various other robots from a common communication method and operation screen. In addition, the experiment confirmed the teleoperation of 12 robots and 17 operators. However, the operation method was not sufficient because there was no feedback of the operation amount on the operation screen. We will continue to improve the remote-control system to make it easier for an operator to control robot systems.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127915739","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 : 2021-10-12DOI: 10.23919/ICCAS52745.2021.9649743
Jin Ho Yang, Dae Jung Kim, C. Chung
Recently, interest in autonomous vehicles has increased. Among autonomous driving control technologies, waypoint tracking is a method of driving along a global route created by a global navigation satellite system and is essential from the perspective of lateral motion control. In waypoint tracking control, if an ego vehicle's position and/or direction angle has a sizeable lateral offset with the planned route, the control input may diverge or cannot be computed. There may also be an initial situation when the ego vehicle starts to track the waypoints opposite to the desired direction. In this study, we propose a way for settling to the global route robustly with respect to the initial pose via model predictive control. We derived an integrated motion model of longitudinal and lateral direction. For validation of the proposed method, the experiment was conducted through computational simulation. We confirmed that the vehicle smoothly entered the reference route regardless of the initial position and heading of the ego vehicle.
{"title":"Predictive Control for Waypoint Path Settling Maneuver with Robustness to Initial Vehicle Pose","authors":"Jin Ho Yang, Dae Jung Kim, C. Chung","doi":"10.23919/ICCAS52745.2021.9649743","DOIUrl":"https://doi.org/10.23919/ICCAS52745.2021.9649743","url":null,"abstract":"Recently, interest in autonomous vehicles has increased. Among autonomous driving control technologies, waypoint tracking is a method of driving along a global route created by a global navigation satellite system and is essential from the perspective of lateral motion control. In waypoint tracking control, if an ego vehicle's position and/or direction angle has a sizeable lateral offset with the planned route, the control input may diverge or cannot be computed. There may also be an initial situation when the ego vehicle starts to track the waypoints opposite to the desired direction. In this study, we propose a way for settling to the global route robustly with respect to the initial pose via model predictive control. We derived an integrated motion model of longitudinal and lateral direction. For validation of the proposed method, the experiment was conducted through computational simulation. We confirmed that the vehicle smoothly entered the reference route regardless of the initial position and heading of the ego vehicle.","PeriodicalId":411064,"journal":{"name":"2021 21st International Conference on Control, Automation and Systems (ICCAS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121779167","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：