Pub Date : 2018-11-01DOI: 10.1109/CACS.2018.8606728
Pei.-Fen Tsai, Yi Chang, A. H. Li
Currently, most portable cosmetics devices are single assistant skincare function products, which lack long-term using motivation because of unable to inspect using history and limit to use a single function. Nowadays people chase scientific evidence to inspect self-related products and customizer their demand. In the project, we provide a portable multifunction device combined detection sensor with two physiotherapy functions. We developed the algorithm and digital filter for the MCU and smart devices to algorithm the data through detecting currents by four probes completely contact on the skin. Otherwise, we integrated immediately replenish micro-particle water function and three wavelengths LED phototherapy to provide all domains of skin conditioning. All the detection data, environmental information and using history will record by the developed APP.
{"title":"Multifunctional skincare device system development","authors":"Pei.-Fen Tsai, Yi Chang, A. H. Li","doi":"10.1109/CACS.2018.8606728","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606728","url":null,"abstract":"Currently, most portable cosmetics devices are single assistant skincare function products, which lack long-term using motivation because of unable to inspect using history and limit to use a single function. Nowadays people chase scientific evidence to inspect self-related products and customizer their demand. In the project, we provide a portable multifunction device combined detection sensor with two physiotherapy functions. We developed the algorithm and digital filter for the MCU and smart devices to algorithm the data through detecting currents by four probes completely contact on the skin. Otherwise, we integrated immediately replenish micro-particle water function and three wavelengths LED phototherapy to provide all domains of skin conditioning. All the detection data, environmental information and using history will record by the developed APP.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"43 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":"115498911","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.2018.8606764
Wen-Shyong Yu, Chien Chih Chen
In this paper, the learning and behavior predictive control based on cloud computing is proposed for efficiently planning autonomous real time prespecifled trajectory tracking and obstacle avoidance control for an omnidirectional wheeled robot using fuzzy inference algorithm. The autonomous trajectory tracking control includes dynamic simulation according to object surface and depth measurement. The robot is equipped with three independent driven omnidirectional wheels and six ultrasonic sensors. The Jacobian between Cartesian space with respect to the joint space is setup for ellipse motion planning so that it not only can autonomously follow the prespecifled trajectory tracking but also avoid obstacles. An architecture is setup to split computation between the remote cloud and the robots so that the robots can interact with the computing cloud. Given this robot/cloud architecture, the stability of the closed loop control system using the predictive control algorithm is guaranteed with satisfactory tracking performance on the cloud during a periodically updated preprocessing phase, and manipulation queries on the robots given changes in the workspace can achieve real time trajectory tracking and obstacle avoidance. Finally, experiments are given to validate the path tracking performance and computational efficiency.
{"title":"Learning and Behavior Predictive Control for Robots Based on Cloud Computing","authors":"Wen-Shyong Yu, Chien Chih Chen","doi":"10.1109/CACS.2018.8606764","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606764","url":null,"abstract":"In this paper, the learning and behavior predictive control based on cloud computing is proposed for efficiently planning autonomous real time prespecifled trajectory tracking and obstacle avoidance control for an omnidirectional wheeled robot using fuzzy inference algorithm. The autonomous trajectory tracking control includes dynamic simulation according to object surface and depth measurement. The robot is equipped with three independent driven omnidirectional wheels and six ultrasonic sensors. The Jacobian between Cartesian space with respect to the joint space is setup for ellipse motion planning so that it not only can autonomously follow the prespecifled trajectory tracking but also avoid obstacles. An architecture is setup to split computation between the remote cloud and the robots so that the robots can interact with the computing cloud. Given this robot/cloud architecture, the stability of the closed loop control system using the predictive control algorithm is guaranteed with satisfactory tracking performance on the cloud during a periodically updated preprocessing phase, and manipulation queries on the robots given changes in the workspace can achieve real time trajectory tracking and obstacle avoidance. Finally, experiments are given to validate the path tracking performance and computational efficiency.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"72 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":"122228400","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}
3D point clouds consisting of a lot of informatively geometric data have been playing critical roles in many applications such as 3D segmentation, polyline annotation for lane tracking, and especially in manufacturing industry. In particular, this paper proposes to apply Reinforcement Learning (RL) to resolve an automated assembly task based on 3D point cloud data. To address this task, the proposed structure is separated into 2 stages including registration stage and assembly path planning stage. Firstly, in the registration stage, one of the objects is matched to an assembled model to determine the transformation between two 3D point clouds by using RANdom Sample Consensus (RANSAC) and Iterative Closet Point (ICP). Secondly, we employ Q-learning method to train a model to make optimal decisions in assemble path planning task. The entire optimized assembly path planning task has been successfully accomplished for typical objects. Finally, the performance of the approach developed in this paper has been validated by experiments.
{"title":"An Implementation of Reinforcement Learning in Assembly Path Planning based on 3D Point Clouds","authors":"Wen-Chung Chang, Dianthika Puteri Andini, Van-Toan Pham","doi":"10.1109/CACS.2018.8606737","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606737","url":null,"abstract":"3D point clouds consisting of a lot of informatively geometric data have been playing critical roles in many applications such as 3D segmentation, polyline annotation for lane tracking, and especially in manufacturing industry. In particular, this paper proposes to apply Reinforcement Learning (RL) to resolve an automated assembly task based on 3D point cloud data. To address this task, the proposed structure is separated into 2 stages including registration stage and assembly path planning stage. Firstly, in the registration stage, one of the objects is matched to an assembled model to determine the transformation between two 3D point clouds by using RANdom Sample Consensus (RANSAC) and Iterative Closet Point (ICP). Secondly, we employ Q-learning method to train a model to make optimal decisions in assemble path planning task. The entire optimized assembly path planning task has been successfully accomplished for typical objects. Finally, the performance of the approach developed in this paper has been validated by experiments.","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":"129355074","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.2018.8606755
Shou-Ming Sheng, Yan-Siun Li, Ming-Tzu Ho
This paper studies the problems of design and implementation of velocity estimators for motor velocity control. In practice, most servomotors use the encoder to measure the position of the motor and then use the conventional differential algorithm, dividing the displacement between two sampling points by the sampling time, to obtain the velocity for feedback control. However, this way can result in serious noise amplification. In this study, velocity estimators are used to solve this problem. This paper compares three velocity estimators including PI Servo-loop velocity estimator, Levant differentiator, and Kalman filter. First, MATLAB/Simulink are used to simulate these velocity estimation algorithms. For further validation, these velocity estimation algorithms are simulated and tested with the actual motor position signals. In experiments, the estimators are implemented on a digital signal processor (TMS320F28335) from Texas Instruments. As a result, the Kalman filter outperforms the other velocity estimators in velocity control.
{"title":"Design and Implementation of Velocity Estimators for Motor Velocity Control","authors":"Shou-Ming Sheng, Yan-Siun Li, Ming-Tzu Ho","doi":"10.1109/CACS.2018.8606755","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606755","url":null,"abstract":"This paper studies the problems of design and implementation of velocity estimators for motor velocity control. In practice, most servomotors use the encoder to measure the position of the motor and then use the conventional differential algorithm, dividing the displacement between two sampling points by the sampling time, to obtain the velocity for feedback control. However, this way can result in serious noise amplification. In this study, velocity estimators are used to solve this problem. This paper compares three velocity estimators including PI Servo-loop velocity estimator, Levant differentiator, and Kalman filter. First, MATLAB/Simulink are used to simulate these velocity estimation algorithms. For further validation, these velocity estimation algorithms are simulated and tested with the actual motor position signals. In experiments, the estimators are implemented on a digital signal processor (TMS320F28335) from Texas Instruments. As a result, the Kalman filter outperforms the other velocity estimators in velocity control.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"14 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":"121216232","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.2018.8606776
S. Sendari, M.S. Hadi, A. N. Handayani, Y. R. Wahyudi, Hsien-I Lin
Wall follower is a method to be used in mobile robot navigation. Here, wall follower navigation was developed using PD (Proportional and Derivative) control system implemented on six-legged robot (hexapod). This method aims to make the robot walk smoothly when following the wall and avoiding obstacles. This robot is equipped with the 7 ultrasonic range sensors to measure the distance of the robot against the wall. There are some basic movements to navigate following the wall, such as walking, avoiding obstacles, and following walls or corridors. The results of this research showed that implementing PD control system can make it walk through the wall with the success rate of 90% on the right wall following mode, and 95% on left wall following mode.
墙体跟随是一种用于移动机器人导航的方法。本文采用PD (Proportional and Derivative)控制系统在六足机器人(hexapod)上实现墙体跟随器导航。这种方法的目的是使机器人在跟随墙壁和避开障碍物时能够平稳地行走。该机器人配备了7个超声波测距传感器，用于测量机器人与墙壁的距离。有一些基本的动作可以跟随墙壁导航，如行走，避开障碍物，沿着墙壁或走廊。研究结果表明，实现PD控制系统可以使其在右墙跟随模式下穿墙成功率为90%，在左墙跟随模式下成功率为95%。
{"title":"Implementation of PD (Proportional Derivative) Control System On Six-Legged Wall Follower Robot","authors":"S. Sendari, M.S. Hadi, A. N. Handayani, Y. R. Wahyudi, Hsien-I Lin","doi":"10.1109/CACS.2018.8606776","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606776","url":null,"abstract":"Wall follower is a method to be used in mobile robot navigation. Here, wall follower navigation was developed using PD (Proportional and Derivative) control system implemented on six-legged robot (hexapod). This method aims to make the robot walk smoothly when following the wall and avoiding obstacles. This robot is equipped with the 7 ultrasonic range sensors to measure the distance of the robot against the wall. There are some basic movements to navigate following the wall, such as walking, avoiding obstacles, and following walls or corridors. The results of this research showed that implementing PD control system can make it walk through the wall with the success rate of 90% on the right wall following mode, and 95% on left wall following mode.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"43 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":"114215570","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.2018.8606740
Hsin-Chang Chen, Yu‐Chen Lin, Yu-Heng Chang
This paper is concerned with an adaptive optimal controller based an actor-critic architecture for solving discrete-time linear system with uncertainty. The actor-critic reinforcement learning progress is similar to the produce of dopamine in human brain and the mechanism which acts on the motoneuron, which dopamine enhances specific actions by reinforce the synaptic contact of the frontal lobe. As same as artificial intelligence (AI), it means the reward signal of dopamine in the neural network can be used to adjust weights in artificial neural which makes the system find the right way to solve the work. The actor-critic scheme is applied to solve the dynamic programming equation problem, using actor and critic neural networks (NNs) for solving optimal controller and optimal value function, respectively. The weights of actor and critic NNs are updated using policy gradient and recursive least squares temporal-difference learning (RLS-TD) scheme at each sampling instant. Finally, time and frequency domain simulations performed using a typical quarter-car suspension systems that an active suspension systems with the proposed control strategy is able to improve ride comfort significantly, compared with the conventional passive suspension systems.
{"title":"An Actor-Critic Reinforcement Learning Control Approach for Discrete-Time Linear System with Uncertainty","authors":"Hsin-Chang Chen, Yu‐Chen Lin, Yu-Heng Chang","doi":"10.1109/CACS.2018.8606740","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606740","url":null,"abstract":"This paper is concerned with an adaptive optimal controller based an actor-critic architecture for solving discrete-time linear system with uncertainty. The actor-critic reinforcement learning progress is similar to the produce of dopamine in human brain and the mechanism which acts on the motoneuron, which dopamine enhances specific actions by reinforce the synaptic contact of the frontal lobe. As same as artificial intelligence (AI), it means the reward signal of dopamine in the neural network can be used to adjust weights in artificial neural which makes the system find the right way to solve the work. The actor-critic scheme is applied to solve the dynamic programming equation problem, using actor and critic neural networks (NNs) for solving optimal controller and optimal value function, respectively. The weights of actor and critic NNs are updated using policy gradient and recursive least squares temporal-difference learning (RLS-TD) scheme at each sampling instant. Finally, time and frequency domain simulations performed using a typical quarter-car suspension systems that an active suspension systems with the proposed control strategy is able to improve ride comfort significantly, compared with the conventional passive suspension systems.","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":"130294319","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.2018.8606729
Ching-Chang Wong, Siang-Lin You, Ren-jie Chen, Yuesheng Liu
In this paper, a design and implementation method of a fuzzy impedance control method and an intuitive teaching system is proposed for a six-axis robot manipulator. The impedance controller with a fuzzy parameter K controller is proposed to calculate the parameter K to achieve the desired position output more precisely. In the design and implementation of the teaching system, an instructor can directly apply a push/pull force on the end-effector of robot manipulator to move its position and edit the task so that the robot manipulator can perform the movement of task position and the gripper’s state.
{"title":"Intuitive Teaching of Six-axis Robot Manipulator Based on Fuzzy Impedance Control","authors":"Ching-Chang Wong, Siang-Lin You, Ren-jie Chen, Yuesheng Liu","doi":"10.1109/CACS.2018.8606729","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606729","url":null,"abstract":"In this paper, a design and implementation method of a fuzzy impedance control method and an intuitive teaching system is proposed for a six-axis robot manipulator. The impedance controller with a fuzzy parameter K controller is proposed to calculate the parameter K to achieve the desired position output more precisely. In the design and implementation of the teaching system, an instructor can directly apply a push/pull force on the end-effector of robot manipulator to move its position and edit the task so that the robot manipulator can perform the movement of task position and the gripper’s state.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"67 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":"132138514","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.2018.8606769
W. Lai, S. Jang, Yu-cheng Chuang
Integrated continuous-time low-pass sigma delta (Σ-Δ) analog to digital converter (ADC) and Class A with Class C low consumption control oscillator (VCO) is designed and implemented in tsmc 0.18μm CMOS 1P6M process. A spread-spectrum clock generator (SSCG) with direct modulation on the voltage controlled oscillator (VCO) is presented. The proposed sigma delta ADC and VCO in SSCG can generate an accurate triangular modulation on the output frequency and thus it can achieve high electromagnetic interference (EMI) reduction with a smaller spreading ratio as compared with existing designs for automatic control application.
{"title":"Class-AC VCO and Continuous-Time Low-pass Sigma Delta ADC for Automatic Control EMI Reduction","authors":"W. Lai, S. Jang, Yu-cheng Chuang","doi":"10.1109/CACS.2018.8606769","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606769","url":null,"abstract":"Integrated continuous-time low-pass sigma delta (Σ-Δ) analog to digital converter (ADC) and Class A with Class C low consumption control oscillator (VCO) is designed and implemented in tsmc 0.18μm CMOS 1P6M process. A spread-spectrum clock generator (SSCG) with direct modulation on the voltage controlled oscillator (VCO) is presented. The proposed sigma delta ADC and VCO in SSCG can generate an accurate triangular modulation on the output frequency and thus it can achieve high electromagnetic interference (EMI) reduction with a smaller spreading ratio as compared with existing designs for automatic control application.","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":"130102799","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.2018.8606767
F. Lin, Shih-Gang Chen, Che-Wei Hsu
An intelligent backstepping control (BSC) using recurrent feature selection fuzzy neural network (RFSFNN) is proposed to construct a high-performance synchronous reluctance motor (SRM) position drive system. First, the dynamics of the SRM position drive system and the BSC are briefly introduced. However, the lumped uncertainty of the SRM is unavailable to obtain in advance. Therefore, an intelligent backstepping control using recurrent feature selection fuzzy neural network (IBSCRFSFNN), which combines the advantages of recurrent neural network, fuzzy logic system and feature selection method, is developed to approximate an idea BSC and to maintain the stability of SRM position drive system. The network structure and online learning algorithm of the IBSCRFSFNN are described in detail. At last, the proposed control system is implemented in a floating-point TMS320F28075 digital signal processor. The experimental results are illustrated to show the validity of the proposed intelligent BSC system.
{"title":"Intelligent Backstepping Control of Synchronous Reluctance Motor Drive System","authors":"F. Lin, Shih-Gang Chen, Che-Wei Hsu","doi":"10.1109/CACS.2018.8606767","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606767","url":null,"abstract":"An intelligent backstepping control (BSC) using recurrent feature selection fuzzy neural network (RFSFNN) is proposed to construct a high-performance synchronous reluctance motor (SRM) position drive system. First, the dynamics of the SRM position drive system and the BSC are briefly introduced. However, the lumped uncertainty of the SRM is unavailable to obtain in advance. Therefore, an intelligent backstepping control using recurrent feature selection fuzzy neural network (IBSCRFSFNN), which combines the advantages of recurrent neural network, fuzzy logic system and feature selection method, is developed to approximate an idea BSC and to maintain the stability of SRM position drive system. The network structure and online learning algorithm of the IBSCRFSFNN are described in detail. At last, the proposed control system is implemented in a floating-point TMS320F28075 digital signal processor. The experimental results are illustrated to show the validity of the proposed intelligent BSC system.","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":"130740435","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.2018.8606773
K. Song, Yueh-Chuan Chang
In this paper, a pose estimation system based on visual fiducial features with multi-cameras is proposed. The system aims to provide ground truth data for mobile robot indoor localization experiments. Most of the hardware components used in this system are available off the shelf, and the idea is to develop a cost-effective localization system for mobile robot tests. The embedded vision system computes fiducial feature detecting algorithm and the pose estimation results are sent through pre-synchronized distributed modules to the server. The server then retrieves the object pose by using the proposed observation decision algorithm. A glitch elimination method is applied to deal with the problems of none observation of all cameras or when the current pose data is far from the previous ones. Practical experiments on a mobile robot have been setup to verify the proposed localization system and the validation result of 6 cm accuracy is achieved.
{"title":"Design and Implementation of a Pose Estimation System Based on Visual Fiducial Features and Multiple Cameras","authors":"K. Song, Yueh-Chuan Chang","doi":"10.1109/CACS.2018.8606773","DOIUrl":"https://doi.org/10.1109/CACS.2018.8606773","url":null,"abstract":"In this paper, a pose estimation system based on visual fiducial features with multi-cameras is proposed. The system aims to provide ground truth data for mobile robot indoor localization experiments. Most of the hardware components used in this system are available off the shelf, and the idea is to develop a cost-effective localization system for mobile robot tests. The embedded vision system computes fiducial feature detecting algorithm and the pose estimation results are sent through pre-synchronized distributed modules to the server. The server then retrieves the object pose by using the proposed observation decision algorithm. A glitch elimination method is applied to deal with the problems of none observation of all cameras or when the current pose data is far from the previous ones. Practical experiments on a mobile robot have been setup to verify the proposed localization system and the validation result of 6 cm accuracy is achieved.","PeriodicalId":282633,"journal":{"name":"2018 International Automatic Control Conference (CACS)","volume":"17 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":"129232878","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：