This paper mainly studies the accurate height jumping control of wheeled-bipedal robots based on torque planning and energy consumption optimization. Due to the characteristics of underactuated, nonlinear estimation, and instantaneous impact in the jumping process, accurate control of the wheeled-bipedal robot’s jumping height is complicated. In reality, robots often jump at excessive height to ensure safety, causing additional motor loss, greater ground reaction force and more energy consumption. To solve this problem, a novel wheeled-bipedal jumping dynamical model(W-JBD) is proposed to achieve accurate height control. It performs well but not suitable for the real robot because the torque has a striking step. Therefore, the Bayesian optimization for torque planning method(BOTP) is proposed, which can obtain the optimal torque planning without accurate dynamic model and within few iterations. BOTP method can reduce 82.3% height error, 26.9% energy cost with continuous torque curve. This result is validated in the Webots simulation platform. Based on the torque curve obtained in the W-JBD model to narrow the searching space, BOTP can quickly converge (40 times on average). Cooperating W-JBD model and BOTP method, it is possible to achieve the height control of real robots with reasonable times of experiments.
{"title":"Height Control and Optimal Torque Planning for Jumping With Wheeled-Bipedal Robots","authors":"Yulun Zhuang, Yuan Xu, Binxin Huang, Mandan Chao, Guowei Shi, Xin Yang, Kuangen Zhang, Chenglong Fu","doi":"10.1109/ICARM52023.2021.9536196","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536196","url":null,"abstract":"This paper mainly studies the accurate height jumping control of wheeled-bipedal robots based on torque planning and energy consumption optimization. Due to the characteristics of underactuated, nonlinear estimation, and instantaneous impact in the jumping process, accurate control of the wheeled-bipedal robot’s jumping height is complicated. In reality, robots often jump at excessive height to ensure safety, causing additional motor loss, greater ground reaction force and more energy consumption. To solve this problem, a novel wheeled-bipedal jumping dynamical model(W-JBD) is proposed to achieve accurate height control. It performs well but not suitable for the real robot because the torque has a striking step. Therefore, the Bayesian optimization for torque planning method(BOTP) is proposed, which can obtain the optimal torque planning without accurate dynamic model and within few iterations. BOTP method can reduce 82.3% height error, 26.9% energy cost with continuous torque curve. This result is validated in the Webots simulation platform. Based on the torque curve obtained in the W-JBD model to narrow the searching space, BOTP can quickly converge (40 times on average). Cooperating W-JBD model and BOTP method, it is possible to achieve the height control of real robots with reasonable times of experiments.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131013457","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536129
Luzhen Ma, Kaiqi Chen, Jialing Liu, Jianhua Zhang
The significance of feature matching is self-evident in the tasks of applying Simultaneous Localization and Mapping (SLAM) technology. However, existing methods mainly focus on nonplanar features and do not deal well with the matching of plane features. To elegantly handle this situation, we introduce a new constraint based on the homography matrix, called symmetric transfer error. The restriction is added to a feature matching model to form a new model named homography-driven classification network(HDCN). The model matches plane features by finding correspondence and eliminating outliers. Because of the particularity of the plane feature, we make an indoor plane dataset to train this model effectively, which consists of a large number of text labels. Through end-to-end training, the inliers ratio and the accuracy of camera pose are greatly improved. Our approach far exceeds other methods of learning and traditional algorithms in the pose estimation task of the indoor environment.
{"title":"Homography-Driven Plane Feature Matching and Pose Estimation","authors":"Luzhen Ma, Kaiqi Chen, Jialing Liu, Jianhua Zhang","doi":"10.1109/ICARM52023.2021.9536129","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536129","url":null,"abstract":"The significance of feature matching is self-evident in the tasks of applying Simultaneous Localization and Mapping (SLAM) technology. However, existing methods mainly focus on nonplanar features and do not deal well with the matching of plane features. To elegantly handle this situation, we introduce a new constraint based on the homography matrix, called symmetric transfer error. The restriction is added to a feature matching model to form a new model named homography-driven classification network(HDCN). The model matches plane features by finding correspondence and eliminating outliers. Because of the particularity of the plane feature, we make an indoor plane dataset to train this model effectively, which consists of a large number of text labels. Through end-to-end training, the inliers ratio and the accuracy of camera pose are greatly improved. Our approach far exceeds other methods of learning and traditional algorithms in the pose estimation task of the indoor environment.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133787928","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536197
Junling Fu, Junhao Zhang, Ziyu She, S. E. Ovur, Wenjie Li, Wen Qi, Hang Su, G. Ferrigno, E. De Momi
Considering the lack of autonomy and the uncertainties of the external environment, manipulating robots in an unstructured environment remains a critical issue. By combining human intelligence, teleoperation control has been considered as a significant solution for enhancing the manipulation capability. In this paper, the whole-body spatial teleoperation control strategy of a hexapod robot in an unstructured environment is investigated. Firstly, the forward and inverse kinematics modeling of the hexapod robot leg is analyzed. In addition, three gaits planning, namely straight, swivel, and transverse gaits, are implemented based on the tripod method. Then, a teleoperation control scheme is developed, by integrating variable motion mapping, incremental motion control strategy, as well as visual and haptic feedback. Finally, preliminary experiments are designed and implemented to verify the feasibility and performance of the developed whole-body spatial teleoperation control strategy.
{"title":"Whole-body Spatial Teleoperation Control of a Hexapod Robot in Unstructured Environment","authors":"Junling Fu, Junhao Zhang, Ziyu She, S. E. Ovur, Wenjie Li, Wen Qi, Hang Su, G. Ferrigno, E. De Momi","doi":"10.1109/ICARM52023.2021.9536197","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536197","url":null,"abstract":"Considering the lack of autonomy and the uncertainties of the external environment, manipulating robots in an unstructured environment remains a critical issue. By combining human intelligence, teleoperation control has been considered as a significant solution for enhancing the manipulation capability. In this paper, the whole-body spatial teleoperation control strategy of a hexapod robot in an unstructured environment is investigated. Firstly, the forward and inverse kinematics modeling of the hexapod robot leg is analyzed. In addition, three gaits planning, namely straight, swivel, and transverse gaits, are implemented based on the tripod method. Then, a teleoperation control scheme is developed, by integrating variable motion mapping, incremental motion control strategy, as well as visual and haptic feedback. Finally, preliminary experiments are designed and implemented to verify the feasibility and performance of the developed whole-body spatial teleoperation control strategy.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124317428","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}
In recent years, the Magnetic Resonance Imaging (MRI) offers high-contrast images of soft tissue to monitor the ablation procedure, an MRI-compatible robotic system aiming to target the lesions with high precision inside the MRI scanner for better intraoperative procedure is necessary. This paper presents an MRI-compatible hydraulic drive needle insertion robot for in-bore MRI-guided minimally invasive stereotactic neurosurgery. According to the principle of communicating vessel, we designed an actuator based on linear pistons and cylinders to drive the robot. A Scotch yoke mechanism is utilized to change the linear motion of the pistons into rotational. To achieve accurate control of the designed robotic system, we utilize grating scales and optical fiber to constitute a MRI-compatible linear encoder. Intensive experimental studies have been performed, the obtained average positional accuracy of the designed robotic system on X-axis, Y-axis, Z-axis, Pitch-axis and Roll-axis is 0.518mm, 1.21mm, 0.898mm, 1.32° and 1.64° respectively.
{"title":"MRI-Compatible Hydraulic Drive Needle Insertion Robot","authors":"Yufu Qiu, Longfei Wu, Fang Huang, Zhifeng Huang, Q. Yan, Jing Guo","doi":"10.1109/ICARM52023.2021.9536120","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536120","url":null,"abstract":"In recent years, the Magnetic Resonance Imaging (MRI) offers high-contrast images of soft tissue to monitor the ablation procedure, an MRI-compatible robotic system aiming to target the lesions with high precision inside the MRI scanner for better intraoperative procedure is necessary. This paper presents an MRI-compatible hydraulic drive needle insertion robot for in-bore MRI-guided minimally invasive stereotactic neurosurgery. According to the principle of communicating vessel, we designed an actuator based on linear pistons and cylinders to drive the robot. A Scotch yoke mechanism is utilized to change the linear motion of the pistons into rotational. To achieve accurate control of the designed robotic system, we utilize grating scales and optical fiber to constitute a MRI-compatible linear encoder. Intensive experimental studies have been performed, the obtained average positional accuracy of the designed robotic system on X-axis, Y-axis, Z-axis, Pitch-axis and Roll-axis is 0.518mm, 1.21mm, 0.898mm, 1.32° and 1.64° respectively.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114952527","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536210
Huayan Pu, Hao Cheng, Jie Ma, Jin Yi, Jinglei Zhao, Zhijiang Xie, Shilong Wang, Tao Zhu, Jun Luo
The applications of parallel robots in various fields are increasing. In this paper, a research on the design optimization of a 6-PSS parallel manipulator for motion simulating is presented. The optimization problem of maximizing the workspace is formulated according to geometric and kinematic analysis. In particular, the workspace is a totally flexible workspace with 6 degrees-of-freedom (DOF). To maximize the workspace of the 6-PSS parallel robot, we investigated the differential evolution algorithm (DE), and the genetic algorithm (GA) is also adopted as a comparison. Computational results show DE algorithm outperforms GA algorithm at about 48.3% in optimal solution providing and 9.3% in time consuming.
{"title":"Optimal Design of 6-DOF Parallel Manipulator with Workspace Maximization using a Constrained Differential Evolution","authors":"Huayan Pu, Hao Cheng, Jie Ma, Jin Yi, Jinglei Zhao, Zhijiang Xie, Shilong Wang, Tao Zhu, Jun Luo","doi":"10.1109/ICARM52023.2021.9536210","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536210","url":null,"abstract":"The applications of parallel robots in various fields are increasing. In this paper, a research on the design optimization of a 6-PSS parallel manipulator for motion simulating is presented. The optimization problem of maximizing the workspace is formulated according to geometric and kinematic analysis. In particular, the workspace is a totally flexible workspace with 6 degrees-of-freedom (DOF). To maximize the workspace of the 6-PSS parallel robot, we investigated the differential evolution algorithm (DE), and the genetic algorithm (GA) is also adopted as a comparison. Computational results show DE algorithm outperforms GA algorithm at about 48.3% in optimal solution providing and 9.3% in time consuming.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124691475","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536136
Qimin Li, Tong Wang, Huayan Pu, Jin Yi, Jie Ma, Ruqing Bai, Jinglei Zhao, Shilong Wang, Jun Luo, Tao Zhu
Precise positioning and vibration isolation are the key technologies in modern precision engineering, such as the precise assembly manipulators and UV lithography, where isolating precision components from the environmental disturbances during positioning is required. In this paper, a novel magnetic levitation gravity compensator employed in a precise assembly system is proposed, which can carry out high-precise positioning in ±5 mm stroke and superior vibration isolation performance attributed to its low levitation stiffness (72.11 N/m) and natural frequency (0.698 Hz). In order to design the gravity compensator with ultra-low stiffness and natural frequency, the analytical model of levitation force is deduced by equivalent surface current model and validated by FEM model. Moreover, a hybrid optimization strategy is utilized to obtain the optimal dimensional parameters of gravity compensator.
{"title":"A Novel Tunable Electromagnetic Gravity Compensator with Low Natural Frequency for Precision Assembly","authors":"Qimin Li, Tong Wang, Huayan Pu, Jin Yi, Jie Ma, Ruqing Bai, Jinglei Zhao, Shilong Wang, Jun Luo, Tao Zhu","doi":"10.1109/ICARM52023.2021.9536136","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536136","url":null,"abstract":"Precise positioning and vibration isolation are the key technologies in modern precision engineering, such as the precise assembly manipulators and UV lithography, where isolating precision components from the environmental disturbances during positioning is required. In this paper, a novel magnetic levitation gravity compensator employed in a precise assembly system is proposed, which can carry out high-precise positioning in ±5 mm stroke and superior vibration isolation performance attributed to its low levitation stiffness (72.11 N/m) and natural frequency (0.698 Hz). In order to design the gravity compensator with ultra-low stiffness and natural frequency, the analytical model of levitation force is deduced by equivalent surface current model and validated by FEM model. Moreover, a hybrid optimization strategy is utilized to obtain the optimal dimensional parameters of gravity compensator.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128930167","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536170
Wenbin Zha, Xiangrong Xu, Zhaoxing Chen, A. Rodic, P. Petrovic
In order to solve the buffeting problem of 7 DOF Manipulator caused by external disturbance in the motion process, the dynamic equation of the manipulator is given, the estimated inertia matrix is selected, and the RBF neural network fitting characteristics are used to fit the required items to reduce the difficulty of modeling. Based on the estimated dynamic model, a neural network adaptive control method with time-varying constraint state is proposed; The control law is designed, and the Lyapunov function equation and asymmetric term are established to derive its convergence. The angular displacement, angular velocity, angular acceleration, input torque and disturbance fitting are analyzed according to the joint state tracking results of the manipulator by using Simulink and gazebo simulation. The system simulation results show that the chattering phenomenon can be suppressed by using this method in the case of disturbance.
{"title":"Manipulator Tracking Algorithm Based on Estimated Dynamics and Time-Varying Output Constraint State","authors":"Wenbin Zha, Xiangrong Xu, Zhaoxing Chen, A. Rodic, P. Petrovic","doi":"10.1109/ICARM52023.2021.9536170","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536170","url":null,"abstract":"In order to solve the buffeting problem of 7 DOF Manipulator caused by external disturbance in the motion process, the dynamic equation of the manipulator is given, the estimated inertia matrix is selected, and the RBF neural network fitting characteristics are used to fit the required items to reduce the difficulty of modeling. Based on the estimated dynamic model, a neural network adaptive control method with time-varying constraint state is proposed; The control law is designed, and the Lyapunov function equation and asymmetric term are established to derive its convergence. The angular displacement, angular velocity, angular acceleration, input torque and disturbance fitting are analyzed according to the joint state tracking results of the manipulator by using Simulink and gazebo simulation. The system simulation results show that the chattering phenomenon can be suppressed by using this method in the case of disturbance.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125570239","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536149
A. Khan, Ke Li, Na Wei
This study proposed a novel system with an integrated design of functional electrical stimulator (FES) and transcutaneous electrical nerve stimulator (TENS) on a single prototype. The novel component of the device involves two modes of operation – the FES and TENS, with controllable frequency, pulse-width, stimulation intensity, and multi-shape pulses on a single device. A boost converter controls the stimulation intensity; an Arduino Uno microcontroller controls the frequency and pulse width; an H-bridge produces square pulses, a toggle switch monitors the mode of operation, and RC filters generate multiple shape pulses. The FES and TENS modes of the device were analyzed with variable parameters and multiple shape pulses. This new design realized a low cost (less than 50 $), low inputs (9 V), and multi-shape stimulation pulses for the FES and TENS, with variable frequency control, controllable pulse-width, and smaller size of the device on a single prototype. This design makes the FES and TENS more practically switched and safer with lower voltage outputs (less than 35 V) than the single-mode stimulators.
{"title":"Integrated Design of Functional Electrical Stimulator and Transcutaneous Electrical Nerve Stimulator on a Single Prototype","authors":"A. Khan, Ke Li, Na Wei","doi":"10.1109/ICARM52023.2021.9536149","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536149","url":null,"abstract":"This study proposed a novel system with an integrated design of functional electrical stimulator (FES) and transcutaneous electrical nerve stimulator (TENS) on a single prototype. The novel component of the device involves two modes of operation – the FES and TENS, with controllable frequency, pulse-width, stimulation intensity, and multi-shape pulses on a single device. A boost converter controls the stimulation intensity; an Arduino Uno microcontroller controls the frequency and pulse width; an H-bridge produces square pulses, a toggle switch monitors the mode of operation, and RC filters generate multiple shape pulses. The FES and TENS modes of the device were analyzed with variable parameters and multiple shape pulses. This new design realized a low cost (less than 50 $), low inputs (9 V), and multi-shape stimulation pulses for the FES and TENS, with variable frequency control, controllable pulse-width, and smaller size of the device on a single prototype. This design makes the FES and TENS more practically switched and safer with lower voltage outputs (less than 35 V) than the single-mode stimulators.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122216150","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536081
Zengqi Peng, Jian Huang
It is an urgent social problem that the rehabilitation needs of the elderly and the disabled can hardly be satisfied. The human-centered rehabilitation robot is a potential solution. In this paper, an auxiliary control scheme based on adaptive dynamic programming is proposed for a class of pneumatic artificial muscles. The improved proxy-based sliding mode controller is used as the basic controller, and an adaptive dynamic programming controller is used to provide auxiliary control signals. To ensure the reliability of the control strategy, the Lyapunov theorem is used to analyze the stability of the control scheme. The simulation results of the proposed method are compared with those of PID, proxy-based sliding mode control, and adaptive proxy-based sliding mode control without the auxiliary controller. Numerical results verify the effectiveness of the control scheme.
{"title":"Improved Proxy-based Sliding Mode Control Integrated Adaptive Dynamic Programming For Pneumatic Muscle Actuators","authors":"Zengqi Peng, Jian Huang","doi":"10.1109/ICARM52023.2021.9536081","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536081","url":null,"abstract":"It is an urgent social problem that the rehabilitation needs of the elderly and the disabled can hardly be satisfied. The human-centered rehabilitation robot is a potential solution. In this paper, an auxiliary control scheme based on adaptive dynamic programming is proposed for a class of pneumatic artificial muscles. The improved proxy-based sliding mode controller is used as the basic controller, and an adaptive dynamic programming controller is used to provide auxiliary control signals. To ensure the reliability of the control strategy, the Lyapunov theorem is used to analyze the stability of the control scheme. The simulation results of the proposed method are compared with those of PID, proxy-based sliding mode control, and adaptive proxy-based sliding mode control without the auxiliary controller. Numerical results verify the effectiveness of the control scheme.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116662445","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536084
Jiaqi Xu, H. Xia, Yueyue Liu, Zhijun Li
Wearable sensing and feedback device could provide useful information for the people with visual impairments. In this paper, we develop a real-time, multifunctional electronic eyeglasses (E-Glasses) for vision-based indoor navigation. Our proposed E-glasses has two main functions, which are indoor navigation through navigation algorithm, and object of interest detection through deep learning technology. The safe motion trajectory and the object information are summarized and feedback will be given to the people with visual impairments. The system can run at 39 fps and achieve mean average precision of 84.77% in the test set of images we collected. Detailed experiments of "Navigation" and "Find the target" had an overall success rate above 91%, demonstrating the feasibility of E-Glasses.
{"title":"Multi-functional Smart E-Glasses for Vision-Based Indoor Navigation","authors":"Jiaqi Xu, H. Xia, Yueyue Liu, Zhijun Li","doi":"10.1109/ICARM52023.2021.9536084","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536084","url":null,"abstract":"Wearable sensing and feedback device could provide useful information for the people with visual impairments. In this paper, we develop a real-time, multifunctional electronic eyeglasses (E-Glasses) for vision-based indoor navigation. Our proposed E-glasses has two main functions, which are indoor navigation through navigation algorithm, and object of interest detection through deep learning technology. The safe motion trajectory and the object information are summarized and feedback will be given to the people with visual impairments. The system can run at 39 fps and achieve mean average precision of 84.77% in the test set of images we collected. Detailed experiments of \"Navigation\" and \"Find the target\" had an overall success rate above 91%, demonstrating the feasibility of E-Glasses.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122506351","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：