2019 7th International Conference on Robotics and Mechatronics (ICRoM)最新文献

{"title":"Robust Real time Lightweight Automatic License plate Recognition System for Iranian License Plates","authors":"Y. Alborzi, Talayeh Sarraf Mehraban, Javad Khoramdel, Ali Najafi Ardekany","doi":"10.1109/ICRoM48714.2019.9071863","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071863","url":null,"abstract":"In this paper we propose an Automatic License Plate Recognition (ALPR) system for unsupervised parking lot applications. The main objective is to develop a system which is implementable on embedded devices, specifically a Raspberry-PI3. ALPR consists of two main stages: (I) Locating the plate and (II) Optical Character Recognition (OCR). Considering the recent growth and success of deep learning methods, especially convolutional neural networks (CNN), in our system, we used the Single Shot Detection (SSD) architecture along with the MobileNet feature extractor to detect the plate in the image captured by the camera and the LPRNet network for OCR. The proposed method is robust, accurate, computationally inexpensive and able to perform in Real-time. The system achieves 79.86% end-to-end accuracy on our dataset and successfully performs in real-time on a Raspberry-PI3. For training the OCR network, we generated and used 130k synthetic license plate images. We also introduce a dataset containing 1500 images with various camera zoom, lighting and viewpoint conditions.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124731700","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}

{"title":"RoboGlove: Design of a Tendon-Driven Robotic Glove with Differential Mechanisms","authors":"M. Abbasi, S. Moosavian","doi":"10.1109/ICRoM48714.2019.9071879","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071879","url":null,"abstract":"Stroke and spinal cord injury (SCI) are two main causes of human upper-limb movement impairments. In this paper, the design of a soft robotic glove with tendon actuation for rehabilitation purposes of the human hand is presented. This robotic glove called KNTU RoboGlove is designed based on differential mechanisms. To help patients, the glove makes grasping objects with different geometries be possible using a single DC motor. To this end, the differential mechanisms are first presented, which are used in two parts of the system. The actuation unit actuates all fingers with a motor, while uses differential gears that can produce the flexion or extension motions without facing singularities. Finally, the functionality of RoboGlove is evaluated in performing two different tasks. First one is grasping a cylindrical object, while the second consists of grasping an irregular-shaped object. Obtained results reveal the merits of the proposed robotic glove.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129450003","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}

{"title":"Spatial Shape Estimation of a Tendon-Driven Continuum Robotic Arm Using a Vision-Based Algorithm","authors":"Yasaman Pedari, A. Parvaresh, S. Moosavian","doi":"10.1109/ICRoM48714.2019.9071908","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071908","url":null,"abstract":"Due to the nonlinearity of the continuum manipulators and the absence of direct relation between the actuator space and task space, shape configuration cannot be achieved by knowing the actuator position. To resolve this problem, an estimation algorithm based on vision processing is proposed in this research. In order to estimate the shape of a two-section tendon-driven continuum robotic arm, each section is considered as a circular arc of multiple curvature in the 3D space. To implement the proposed method, few LEDs are implanted along the length of the manipulator; whereas two webcams are used to capture the photos of LEDs which are exploited to determine their position. These positons are next used for shape estimation using the proposed algorithm. Finally, the efficiency of the proposed algorithm is experimentally evaluated on a calibration setup of the robot and the results are discussed.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127520173","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}

{"title":"A Nonlinear Controller Based on the Convolutional Neural Networks","authors":"H. Nobahari, Yousef Seifouripour","doi":"10.1109/ICRoM48714.2019.9071803","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071803","url":null,"abstract":"This paper focuses on developing a nonlinear controller based on the convolutional neural networks to control different plants. It is assumed that the prior knowledge about the plants is very limited and there are only sensory input-output data history of them. The neural network is trained in supervised learning method without having a target controller. As manipulating data are not picture frames, they are preprocessed and concatenated to form adequate frames required by the convolutional neural networks. A convolutional neural network with a simple structure is proposed for the problem. The trained controller is applied to six different linear and nonlinear plants, one of which is inherently unstable and different from the plants utilized in the training process. Furthermore, an important parameter of this unstable plant is considerably changed and the controller performance is analyzed. The simulation results show that the proposed controller can properly control all plants.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125864579","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}

{"title":"Human Body Modeling for Ground Contact Force Estimation of RoboWalk","authors":"Farshid Absalan, S. Moosavian","doi":"10.1109/ICRoM48714.2019.9071836","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071836","url":null,"abstract":"RoboWalk is a lower limb rehabilitation robot for Human body weight assistance. To achieve a proper design of RoboWalk, there is a need to understand the dynamics of human and foot contact forces with the ground that is the focus of this paper. In fact, an important component of human-Robo Walk forward dynamics simulation is foot-ground contact modelling. Different models have been proposed to simulate the contact of the foot with the ground. In this study, the dynamic equations of human body is developed with 19 degrees of freedom, while three points of collision with the ground are considered for each foot. Next, the kinematics information obtained from the experimental data are introduced to the dynamical equations, and the joint torques are estimated by solving the inverse dynamics of the human model. The results are compared to the experimental data for model validation. However, it is assumed that the numerical value of the foot contact model parameters are not available, so the pelvis is constrained in such a way that the human model foot does not hit the ground. Therefore, these uncertain parameters does not affect the validation results. Next, a model is selected from the existing models to express the foot contact behavior with the ground, while such models should provide stable walking with selecting the appropriate parameters. To determine the shear and normal contact force, numerical values of the parameters are required while these values depend on the shoe and the ground material and surface. Then, the path traveled by the pelvis in the human dynamic model was compared with the path of the actual pelvic motion and their difference was used to form a cost function to determine the parameters. In the next step, by choosing appropriate values for the contact parameters of the foot and the springs and the damping of the toe joint, the path of the pelvis becomes closely identical to the actual pelvis motion. Finally, after the human gait stabilized, the developed dynamics model is compared with the experimental data.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127728945","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}

{"title":"A novel.gyroscopic stabilizer for a controlled unmanned bicycle","authors":"Mohamad Hanachi, M. Mahjoob, M. Tofigh","doi":"10.1109/ICRoM48714.2019.9071910","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071910","url":null,"abstract":"External devices have been applied as actuators to stabilize autonomous bicycles. Gyrostabilizer is an effective stabilizer due to its ability in producing large and fast gyroscopic torques. However, conventional gyros are not naturally able to maintain constant moments and directions to stabilize the vehicle against constant ‘heel’. We present an innovative gyrostabilizer with a twin-flywheel arrangement that can provide any desired gyroscopic roll-moment. The dynamical model of a bicycle together with the gyrostabilizer is obtained using Newton-Euler formulation. A gain-scheduled LQ tracker controller is then designed to provide stability and trajectory tracking in a range of forward velocities. Several numerical simulations are conducted To evaluate the proposed method,. The results show that the proposed controller has appropriate performance and generates smooth signals which are feasible to produce by the gyro.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133915692","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}

{"title":"Robust Fuzzy Nonlinear Control of Microbeams Vibration with Piezoelectric Actuator and Electrostatic Force","authors":"A. Vali, R. Vatankhah, E. A. Yazdi","doi":"10.1109/ICRoM48714.2019.9071830","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071830","url":null,"abstract":"In this paper, transverse vibration control of a microbeam with nonlinear governing equations is investigated. The non-classical modified strain gradient theory is used to derive the governing differential equations of motion. The dynamic model considers the electrostatic force and the nonlinear effect of mid-plane stretching. Piezoelectric layers are laminated on the beam and the piezoelectric voltage is defined as the actuating control signal. Because of the existence of nonlinear terms due to mid-plane stretching and electrostatic force, the governing partial differential equation is nonlinear. The control aim is to stabilize microbeam's transverse vibrations. In the present study, the governing partial differential equations are simplified using the Galerkin method. A robust nonlinear sliding mode controller is designed and implemented to compensate for the effects of higher modes in the closed-loop system. To prevent the chattering phenomenon near the sliding surface, a fuzzy logic controller is mixed with the sliding mode controller. The closed-loop response of the system is investigated in the presence of disturbances and uncertainties through numerical simulations. The innovations in this research include using the effect of electrostatic force, mid-plane stretch and the effect of piezoelectric all together in a model, providing exact mode shapes for Galerkin method, using Taylor's third-order expansion for electrostatic force that improves accuracy and designing terminal sliding mode and fuzzy-terminal sliding mode controller.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131766040","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}

{"title":"Coverage Control of Multi-Robot System for Dynamic Cleaning of Oil Spills","authors":"S. Kaviri, Ahmadreza Tahsiri, H. Taghirad","doi":"10.1109/ICRoM48714.2019.9071805","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071805","url":null,"abstract":"This paper addressed the dynamic cleaning of oil spills using a multi-robot system. The cleaning process is performed using a group of aerial agents adaptively covering an oil spill considering its advection and spreading on the sea surface. The concept of Voronoi Tessellation is employed to command the autonomous vehicles on how to adapt its configuration with the dynamic oil spill. Once the spill tracking error reduces to the desired value, all of the agents spray dispersant on the oil spill. This solution prevents wasting the excess amount of dispersant that is often being sprayed in conventional methods by aircraft. A distributed sliding mode control scheme is proposed to navigate the agents to the near-optimal Centroidal Voronoi Tessellation (CVT) by targeting the thick layers. Simulation results demonstrate that the proposed strategy can efficiently track the trajectory of the polluted area, and adaptively cover the time-varying shape of the oil spill.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117071323","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}

{"title":"ARAS-IREF: An Open-Source Low-Cost Framework for Pose Estimation","authors":"H. Damirchi, R. Khorrambakht, H. Taghirad","doi":"10.1109/ICRoM48714.2019.9071852","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071852","url":null,"abstract":"Despite the amount of research reported on state estimation and sensor fusion in the field of robotics, there are no well known low-cost solutions for a referencing system to determine the accuracy of developed methods by providing a suitable ground truth for them. In this paper an efficient and accurate 6-DoF pose measurement system is proposed and implemented on a spherical parallel robot using IR LEDs. This approach uses the perspective-n-point algorithm to derive the transformation matrix representing the accurate relative pose of the end-effector with respect to an inertial frame. Exploiting a visible light filter in front of the camera has rendered this approach robust against illumination changes. Furthermore, it allows for mitigating the rolling shutter effects by reducing the exposure time. Finally, a custom made testing module is proposed to verify the accuracy of the proposed device, and the calibration process proves the accuracy and efficiency of the system.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123118934","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}

{"title":"Assessment of the Adaptive Sliding Mode Control of an Active Ankle Foot Orthosis with an Impedance Reference","authors":"A. Bagheri, Davood Dorostkar, M. Zakerzadeh, M. Sadigh, M. Mahjoob","doi":"10.1109/ICRoM48714.2019.9071905","DOIUrl":"https://doi.org/10.1109/ICRoM48714.2019.9071905","url":null,"abstract":"Patients suffering from impairment in the ankle lose the ability to walk properly. The requirements of the ankle during a healthy gait cycle, accurately follow an impedance profile. The properties of the environment the orthosis is in contact with however are unknown and may change. Disturbances from both the user and the environment are also common. The ankle requirements have been found to imitate an impedance profile and an adaptive sliding mode controller with an impedance reference is proposed in order to assess these issues. The effectiveness of the controller has been assessed by carrying out simulations on a model of the ankle orthosis developed previously. Various bodies (soft, hard and medium stiffness) have been considered with and without the sliding mode control. The results show that the adaptive control responds very well and manages to model the body the actuator is in contact with, despite the presence of an external force. The results also show the controller manages to follow the desired impedance reference after the adaption is complete. The sliding mode control however, is found to be inessential in these working conditions due to the actuator motor reaching its limits.","PeriodicalId":191113,"journal":{"name":"2019 7th International Conference on Robotics and Mechatronics (ICRoM)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123576347","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}