Pub Date : 2018-11-01DOI: 10.1109/CACS.2018.8606778
Tung-Lin Hsieh, Bo-Chien Zheng, Fudi Lin, Chan-Yun Yang
Due to gradually aging lifespan of elders in human society, a lot of new demands have been brought to facilitate their daily life. The elder driving assistive technology is one of the demands. The elder driving assistive technology is not only beneficial in increasing safety of the driver and the people around his vehicle, but also advantageous in decreasing the public cost of society safety. Thus, the study set a goal to pursue a driving assistive apparatus which can respond immediately to the elder a helpful warning or arrestment during a potential accident crisis. The apparatus dynamically monitors the vehicle movement and it corresponding diver operation mode, and detects the irregularity between the driver and his vehicle. Sensory devices for detecting the behaviors were installed in the vehicle, including imaging camera, inertial measurement unit, Lidar scanner, steering wheel angle sensor, depression sensors on accelerator pedal and brake pedal to form a sensory network for collecting the signals for irregularity identification. Together with an array of ultrasonic sensors installed surrounding the vehicle to scout the suspicious objects around, a sensor harness was integrated and formed to evaluate the irregularity level of the danger. Once the risk level is significant enough, the danger classification will be delivered to the processing center to activate a corresponding ensemble of sensory feedbacks to remind adaptively the driver. The signal interface which has been designed attempts to resist automatically or even stops immediately an inaccurate operation of the driver which might cease an accident disaster.
{"title":"An IoT Peripheral Sensor Integration to Assist Elderly Drivers","authors":"Tung-Lin Hsieh, Bo-Chien Zheng, Fudi Lin, Chan-Yun Yang","doi":"10.1109/CACS.2018.8606778","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606778","url":null,"abstract":"Due to gradually aging lifespan of elders in human society, a lot of new demands have been brought to facilitate their daily life. The elder driving assistive technology is one of the demands. The elder driving assistive technology is not only beneficial in increasing safety of the driver and the people around his vehicle, but also advantageous in decreasing the public cost of society safety. Thus, the study set a goal to pursue a driving assistive apparatus which can respond immediately to the elder a helpful warning or arrestment during a potential accident crisis. The apparatus dynamically monitors the vehicle movement and it corresponding diver operation mode, and detects the irregularity between the driver and his vehicle. Sensory devices for detecting the behaviors were installed in the vehicle, including imaging camera, inertial measurement unit, Lidar scanner, steering wheel angle sensor, depression sensors on accelerator pedal and brake pedal to form a sensory network for collecting the signals for irregularity identification. Together with an array of ultrasonic sensors installed surrounding the vehicle to scout the suspicious objects around, a sensor harness was integrated and formed to evaluate the irregularity level of the danger. Once the risk level is significant enough, the danger classification will be delivered to the processing center to activate a corresponding ensemble of sensory feedbacks to remind adaptively the driver. The signal interface which has been designed attempts to resist automatically or even stops immediately an inaccurate operation of the driver which might cease an accident disaster.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126624187","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606732
Van-Tam Ngo, Yen‐Chen Liu
The use of multiple mobile manipulators (MMs) to perform collaborative object transportation is a promising solution for future industry. However, most existing control laws in this field require sensors to measure interactive force-torque between the transported object and the end-effectors of the robots, which is costly and increasing the system complexity. To overcome this problem, the present study considers the interactive force/torque to be unknown nonlinear functions and estimates them using a wavelet neural network (WNN). In particular, an adaptive-wavelet neural network control law is designed to guarantee trajectory tracking for each robot. Then an output synchronization algorithm is additionally used to coordinate the movement of the network MMs. Stability of the proposed control law is proven theoretically using Lyapunov theorem. Furthermore, the effectiveness of the control law is illustrated by simulations.
{"title":"Object Transportation Using Networked Mobile Manipulators without Force/Torque Sensors","authors":"Van-Tam Ngo, Yen‐Chen Liu","doi":"10.1109/CACS.2018.8606732","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606732","url":null,"abstract":"The use of multiple mobile manipulators (MMs) to perform collaborative object transportation is a promising solution for future industry. However, most existing control laws in this field require sensors to measure interactive force-torque between the transported object and the end-effectors of the robots, which is costly and increasing the system complexity. To overcome this problem, the present study considers the interactive force/torque to be unknown nonlinear functions and estimates them using a wavelet neural network (WNN). In particular, an adaptive-wavelet neural network control law is designed to guarantee trajectory tracking for each robot. Then an output synchronization algorithm is additionally used to coordinate the movement of the network MMs. Stability of the proposed control law is proven theoretically using Lyapunov theorem. Furthermore, the effectiveness of the control law is illustrated by simulations.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122587712","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606736
Sung-Chi Chiang, Yang-Cheng Huang, Kuan Shen, J. Yen
Laparoscopic minimally invasive surgery has been extensively used in the medical field recently years, due to the small wounds, shorter recovery time and less suffering of patients. Combined with robotic technology, laparoscopic minimally invasive surgical robots can obtain higher surgical accuracy. The main purpose of this paper is to design a force controller to achieve the angle control of an 8-DOF laparoscopic minimally invasive surgical robot.First, we introduce the design of a motor driven endoscope mechanism and deduces the kinematics and dynamic model of the manipulator arm and endoscope. Under the constraint of the celiac incision, a null-space matrix relative to the task space would be derived. Perspective space of the endoscope camera would be analyzed and a null-space impedance control architecture would be constructed so that the endoscope-holding manipulator can provide images with different perspectives in the situation where the target object does move in the picture and does not generate lateral force on the incision.
{"title":"An eight degree-of-freedom robotic endoscope holder","authors":"Sung-Chi Chiang, Yang-Cheng Huang, Kuan Shen, J. Yen","doi":"10.1109/CACS.2018.8606736","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606736","url":null,"abstract":"Laparoscopic minimally invasive surgery has been extensively used in the medical field recently years, due to the small wounds, shorter recovery time and less suffering of patients. Combined with robotic technology, laparoscopic minimally invasive surgical robots can obtain higher surgical accuracy. The main purpose of this paper is to design a force controller to achieve the angle control of an 8-DOF laparoscopic minimally invasive surgical robot.First, we introduce the design of a motor driven endoscope mechanism and deduces the kinematics and dynamic model of the manipulator arm and endoscope. Under the constraint of the celiac incision, a null-space matrix relative to the task space would be derived. Perspective space of the endoscope camera would be analyzed and a null-space impedance control architecture would be constructed so that the endoscope-holding manipulator can provide images with different perspectives in the situation where the target object does move in the picture and does not generate lateral force on the incision.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122966719","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606775
Huang Chingting, Hu Zhuqi, S. Tateno
The traffic safety has been a major concern in recent years. One of the effective approaches to prevent the traffic accident is to develop advanced driver assistance systems which can alarm driver in dangerous situation. In fact, changing lane or overtaking another vehicle is one of the most dangerous driving behaviors. Therefore, it is important for drivers to recognize current lane line types to take proper actions. However, classification systems proposed so far can only distinguish up to five types of lane lines, such as dashed and solid. Hence, the existing road classification systems are not suitable if there are more types of lane lines on the road. In this paper, an improved method is proposed to classify more lane line types by real-time image processing. In order to increase the detection accuracy of lane line types, the image stitching method is applied to reduce the misjudgment caused by blocked lane lines. A set of features about pixel distribution is utilized in the classifier to distinguish more than five lane line types. Furthermore, the results of experiments which are carried out in real road driving show high accuracy of the proposed classification method under the various situations.
{"title":"Traffic Lane Line Classification System by Real-time Image Processing","authors":"Huang Chingting, Hu Zhuqi, S. Tateno","doi":"10.1109/CACS.2018.8606775","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606775","url":null,"abstract":"The traffic safety has been a major concern in recent years. One of the effective approaches to prevent the traffic accident is to develop advanced driver assistance systems which can alarm driver in dangerous situation. In fact, changing lane or overtaking another vehicle is one of the most dangerous driving behaviors. Therefore, it is important for drivers to recognize current lane line types to take proper actions. However, classification systems proposed so far can only distinguish up to five types of lane lines, such as dashed and solid. Hence, the existing road classification systems are not suitable if there are more types of lane lines on the road. In this paper, an improved method is proposed to classify more lane line types by real-time image processing. In order to increase the detection accuracy of lane line types, the image stitching method is applied to reduce the misjudgment caused by blocked lane lines. A set of features about pixel distribution is utilized in the classifier to distinguish more than five lane line types. Furthermore, the results of experiments which are carried out in real road driving show high accuracy of the proposed classification method under the various situations.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126555583","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606734
E. Cheng, Ku-Young Young, Chin-Teng Lin
This study proposes a EEG-based prediction system that transform the measured EEG record into an image-liked data for estimating the drowsiness level of drivers. Drowsy driving is one of the main factors to the occurrence of traffic accident. Since drivers themselves may not always immediately recognize that they are in the drowsy state, the risk of traffic accident increases while the driver is in the low vigilance state. In order to address this problem, the estimation of drowsy driving state via brain-computer interfaces (BCI) becomes a major concern in the driving safety field. This study transforms the measured EEG record into a image-liked feature maps, and then passes these feature maps to a Convolutional Neural Network (CNN) to learn the discriminative representations. The proposed drowsiness prediction system is evaluated by leave-one-subject-out cross-validation. The results indicate that our approach provides impressive and robust prediction performance on the EEG dataset without artifact removal process.
{"title":"Image-based EEG signal processing for driving fatigue prediction","authors":"E. Cheng, Ku-Young Young, Chin-Teng Lin","doi":"10.1109/CACS.2018.8606734","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606734","url":null,"abstract":"This study proposes a EEG-based prediction system that transform the measured EEG record into an image-liked data for estimating the drowsiness level of drivers. Drowsy driving is one of the main factors to the occurrence of traffic accident. Since drivers themselves may not always immediately recognize that they are in the drowsy state, the risk of traffic accident increases while the driver is in the low vigilance state. In order to address this problem, the estimation of drowsy driving state via brain-computer interfaces (BCI) becomes a major concern in the driving safety field. This study transforms the measured EEG record into a image-liked feature maps, and then passes these feature maps to a Convolutional Neural Network (CNN) to learn the discriminative representations. The proposed drowsiness prediction system is evaluated by leave-one-subject-out cross-validation. The results indicate that our approach provides impressive and robust prediction performance on the EEG dataset without artifact removal process.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122765693","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606747
Jian-Hua Jhou, Yu-Po Lin, Yih-Guang Leu
In this paper, the two-wheeled robot is combined with Kinect sensor to measure obstacle distance. When the two-wheeled robot autonomously balances or moves, the ranging value will be unstable due to the shaking of the two-wheeled robots. This paper uses a smart prediction method to correct the ranging error value in order to increase the accuracy of ranging value and the obstacle avoidance decision. Finally, in order to verify the proposed method, some experiments are performed.
{"title":"Depth Image-based Distance Measurement for Two-wheeled Robots","authors":"Jian-Hua Jhou, Yu-Po Lin, Yih-Guang Leu","doi":"10.1109/CACS.2018.8606747","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606747","url":null,"abstract":"In this paper, the two-wheeled robot is combined with Kinect sensor to measure obstacle distance. When the two-wheeled robot autonomously balances or moves, the ranging value will be unstable due to the shaking of the two-wheeled robots. This paper uses a smart prediction method to correct the ranging error value in order to increase the accuracy of ranging value and the obstacle avoidance decision. Finally, in order to verify the proposed method, some experiments are performed.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126679608","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606738
Y. Osa, S. Uchikado, Kanya Tanaka
In this study a synthesis of Control Configured Vehicle (CCV) flight control system which is able to realize the spin turn for hovering Tilt Rotor Aircraft (TRA), using the forward/backward alternative same angle variations of lift vectors of both rotors, is proposed. Basically this flight control system is constructed with roll angle feedback as stability augmentation method and P and PI control as controllability augmentation method.
{"title":"A Study on Spin Turn Mode for Hovering Tilt Rotor Aircraft","authors":"Y. Osa, S. Uchikado, Kanya Tanaka","doi":"10.1109/CACS.2018.8606738","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606738","url":null,"abstract":"In this study a synthesis of Control Configured Vehicle (CCV) flight control system which is able to realize the spin turn for hovering Tilt Rotor Aircraft (TRA), using the forward/backward alternative same angle variations of lift vectors of both rotors, is proposed. Basically this flight control system is constructed with roll angle feedback as stability augmentation method and P and PI control as controllability augmentation method.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124620482","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606781
C. Lien, K. Yu, Hao‐Chin Chang
In this paper, the mixed H2/H∞ performance analysis of switched time-delay systems with time-varying random delay via a switching signal selection is considered. Some delay-dependent LMI-based criteria are proposed to achieve the design of switching signal. Our approach is proposed to guarantee the mixed performance of system under consideration by Wirtinger-based inequality. A numerical example is given to show the main contribution of this paper.
{"title":"Mixed Performance of Switched Systems with Time-varying Random Delay","authors":"C. Lien, K. Yu, Hao‐Chin Chang","doi":"10.1109/CACS.2018.8606781","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606781","url":null,"abstract":"In this paper, the mixed H2/H∞ performance analysis of switched time-delay systems with time-varying random delay via a switching signal selection is considered. Some delay-dependent LMI-based criteria are proposed to achieve the design of switching signal. Our approach is proposed to guarantee the mixed performance of system under consideration by Wirtinger-based inequality. A numerical example is given to show the main contribution of this paper.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"99 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120843337","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606763
Huang-Chih Chen, L. Fu
This paper demonstrates the approach of a direct model reference adaptive control (MRAC) to maintain the constant amplitude of the oscillating Atomic Force Microscope (AFM) cantilever. Compared with PID controllers, the MRAC strategy can improve the scan velocity without losing the image quality.
{"title":"Model Reference Adaptive Control for Atomic Force Microscope","authors":"Huang-Chih Chen, L. Fu","doi":"10.1109/CACS.2018.8606763","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606763","url":null,"abstract":"This paper demonstrates the approach of a direct model reference adaptive control (MRAC) to maintain the constant amplitude of the oscillating Atomic Force Microscope (AFM) cantilever. Compared with PID controllers, the MRAC strategy can improve the scan velocity without losing the image quality.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122437329","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 : 2018-11-01DOI: 10.1109/CACS.2018.8606754
Chi-Yi Tsai, Chien-Che Huang, Yung-Shan Chou
This paper presents a novel convolutional neural network (CNN) based high-level control architecture that uses deep learning technique to realize autonomous picking control of a six-degree-of-freedom (6-DoF) manipulator using the visual information only. The proposed manipulator control system uses a stereo camera as a measurement device to capture a stereo image of the scene in front of the robot. Then, the proposed CNN-based picking controller uses the captured stereo image as an input to predict the optimal picking control command of the manipulator directly. In the collection of the training dataset, we controlled the manipulator to pick up the object-of-interest (OOI) manually and recorded the stereo images and the corresponding control commands. In the CNN training phase, the supervised end-to-end learning technique is used to learn the mapping between the stereo image observation and the picking control commands of the 6-DoF manipulator. Experimental results show that the proposed end-to-end visual picking control system achieves an average of 70% and 60% success rate in the random single-object and multi-object picking task, respectively.
{"title":"Data-Driven Visual Picking Control of a 6-DoF Manipulator Using End-to-End Imitation Learning","authors":"Chi-Yi Tsai, Chien-Che Huang, Yung-Shan Chou","doi":"10.1109/CACS.2018.8606754","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606754","url":null,"abstract":"This paper presents a novel convolutional neural network (CNN) based high-level control architecture that uses deep learning technique to realize autonomous picking control of a six-degree-of-freedom (6-DoF) manipulator using the visual information only. The proposed manipulator control system uses a stereo camera as a measurement device to capture a stereo image of the scene in front of the robot. Then, the proposed CNN-based picking controller uses the captured stereo image as an input to predict the optimal picking control command of the manipulator directly. In the collection of the training dataset, we controlled the manipulator to pick up the object-of-interest (OOI) manually and recorded the stereo images and the corresponding control commands. In the CNN training phase, the supervised end-to-end learning technique is used to learn the mapping between the stereo image observation and the picking control commands of the 6-DoF manipulator. Experimental results show that the proposed end-to-end visual picking control system achieves an average of 70% and 60% success rate in the random single-object and multi-object picking task, respectively.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122913769","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：