2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)最新文献

{"title":"Development and testing of a collision avoidance algorithm for industrial applications","authors":"Lorenzo Palermino, A. Fathy, M. Carnevale, H. Giberti","doi":"10.1109/MESA55290.2022.10004397","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004397","url":null,"abstract":"Safe interaction of the operator and the cobot in the co-working space is one fundamental requirement for introducing automation in small and medium enterprises characterized by unstructured cell layouts. In addition to the exploitation of cobots, a fully safe interaction requires the adoption of collision avoidance systems, to enable the real-time re-planning of the end-effector trajectories thus avoiding to stop the machine in case of collision with humans. This is fundamental for industrial applications, in order to maintain the production rate as constant as possible even in unstructured production environments. However, collision avoidance applications in actual industrial production cells are still limited, due to some limitations which are not yet completely solved. It is indeed still likely to happen that the recalculation of the obstacle-free trajectory takes a too long time, not compatible with industrial applications. This paper describes the development of a collision avoidance program using the Lazy PRM* algorithm. The program is tested on a physical robot, the Mitsubishi Melfa RV-5AS-D, to perform some exemplary pick and place tasks. The developed algorithm can alter online, during the execution, the road-map from dense to sparse in those cases in which the search for an alternative trajectory is detected to take too long time. Compared to other commercial collision avoidance systems, in which the evaluation of road-maps can only be done offline once and for all, this feature would prevent the robot to get stucked in case a feasible solution is not found in a fast enough way. Furthermore, the developed program guarantees greater flexibility in creating the road-map, trying to match the user's needs, and eliminating the superfluous parts of the road-map to reduce computational time. This marks a difference with present-day solutions for commercial collision avoidance systems which, to the author knowledge, connects all the nodes together.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129333871","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":"On Force Control for Robot Manipulators in Contact with Uneven Planar Surfaces","authors":"A. Rosales, T. Heikkilä","doi":"10.1109/MESA55290.2022.10004391","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004391","url":null,"abstract":"This paper studies a robot manipulator in contact with an uneven planar surface. The robot contact-task is to exert a desired force on normal direction to the surface while a desired reference is tracked along the surface. The uneven characteristic of the surface is modeled with ramp disturbances in the position, on normal direction to the surface. The magnitude of the ramp is proportional to the speed of the trajectory along the surface. Also, uncertainty in the stiffness is analyzed. Considering delays and filters commonly found in practical applications, a force control system based on admittance is analyzed. Disturbance rejection in terms of steady-state error is considered, and a tuning method for disturbance attenuation is developed. Furthermore, the relative stability of the system is studied giving a metric of how much uncertainty in the stiffness the control system can handle. The analysis and methods are verified by simulations.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"188 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120987743","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":"Digital Twin of Piezoelectric Effect at Microscale and Macroscale PVDF Film","authors":"Yu-Hsiang Huang, Tsung-Han Huang, W. Hung, Ching-Yuan Chang","doi":"10.1109/MESA55290.2022.10004450","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004450","url":null,"abstract":"This study uses computer tomography (CT) and a finite element method (FEM) criterion to establish a digital twin (DT) model for Polyvinylidene fluoride (PVDF) film. The CT provides sliced images of the PVDF film with 50 μm, and we have developed a standard procedure to rebuild the stereo and interior model of the PVDF film. We also use a d33 meter to measure the piezoelectric effect of the PVDF film and utilize the value in the FEM model. The primary material of the piezoelectric film is polyvinylidene fluoride, which has a unique dielectric effect, piezoelectric effect, and pyroelectric effect. In this study, computer tomography was used to establish the microstructure model of the film, and ANSYS software was used to establish the microstructure model. The primary purpose of simulating the piezoelectric effect of the self-made piezoelectric film is to compare the small holes contained in the film structure and the forward and reverse piezoelectric responses of different structures in the same environment. This study has established three different DT-FEM models and simulated the piezoelectric effect of the thin film. The DT-FEM model contributes to the emerging technology of material science and helps scientists to investigate the piezoelectric effect at the micro- and macro-scale.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131278994","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":"Benchmarking of Dual-Step Neural Networks for Detection of Dangerous Weapons on Edge Devices","authors":"Daniele Berardini, A. Galdelli, A. Mancini, P. Zingaretti","doi":"10.1109/MESA55290.2022.10004469","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004469","url":null,"abstract":"Nowadays, criminal activities involving hand-held weapons are widespread throughout the world and pose a significant problem for the community. The development of Video Surveillance Systems (VSV) and Artificial Intelligence (AI) approaches have made it possible to implement automatic systems for detecting dangerous weapons even in crowded environments. However, the detection of hand-held weapons - usually very small in size with respect to the Field of View (FoV) of the camera - is still an open challenge. The use of complex hardware systems and deep learning (DL) architectures have mitigated this problem and achieved excellent results, but involve high costs and high performance that hinder the deployment of such systems. In this contest, we present a comprehensive performance comparison in terms of inference time and detection accuracy of two low-cost edge devices: Google Coral Dev board and NVIDIA Jetson Nano. We deployed and run on both boards a dual-step DL framework for hand-held weapons detection exploiting half-precision floating-point (FP16) quantization on Jetson Nano and 8-bit signed integer (INT8) quantization on Coral Dev. Our results show that both in terms of PASCAL VOC mean Average Precision (mAP) and Frames per Second (FPS), the framework running on Jetson Nano (mAP = 99.6, FPS = 4.5, 2.5, 1.7, 1.4 from 1 to 4 people in the camera FoV, respectively) slightly outperform the Coral's one (mAP = 98.8 and FPS = 2.9. 1.5, 1.1, 0.9 from 1 to 4 people in the camera FoV, respectively). The Coral Dev obtained the highest inference speed (FPS = 36.5) overcoming the Jetson Nano (FPS=23.8) only when running the dual-step framework with no people in the camera FoV. In conclusion, the benchmark on the two edge devices points out that both allow to run the framework with satisfactory results, pushing towards the diffusion of such on-the-edge systems in a real-world scenario.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128543097","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":"ROAM: A Remotely Operated Accelerator Monitor","authors":"Thomas C. Thayer, M. A. Montironi, A. Ratti","doi":"10.1109/MESA55290.2022.10004449","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004449","url":null,"abstract":"Monitoring accelerators in operation is a wellknown challenge due to the radiation environment. However, there are significant benefits in being able to deploy particular sensors in specific locations of accelerator enclosures for monitoring or troubleshooting purposes. Learning from experience at other labs, we used Commercial Off The Shelf (COTS) components and an open source robot control software framework (ROS) to build a remotely controlled robot platform including a standard suite of instruments such as cameras, LIDAR, and ultrasound, with the ability to incorporate other ad-hoc sensors for specific measurements, such as a Gamma radiation monitor. Special attention was given to the robot's ability to maintain safety in the high risk environment of an accelerator, with multiple failure contingencies in place to ensure collision free operation. Testing was performed to prove the platform's viability and showcase its capability for accelerator monitoring.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131702037","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":"Learning Algebra with Robotics in Math Classes","authors":"Ching-Wei Chuang, Harry H. Cheng","doi":"10.1109/MESA55290.2022.10004399","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004399","url":null,"abstract":"An increasing number of tools have been created to assist students in learning mathematics. Robots have been regarded as an especially powerful tool to help students master mathematics since students can simultaneously learn mathematics, programming, robotic control, and computational thinking. Although a number of educational robots and curricula have been developed, some of them do not comply with math standards, so they are primarily suitable for after-school programs, camps, or workshops. Students might not be able to focus on learning mathematics now that writing a program might be difficult for them due to debugging. In this paper, mathematics curricula that meet math standards are developed with a block-based programming platform, Roboblocky. Linkbots are utilized as robots in the curricula to teach and learn mathematics in school settings. Students learn mathematics by observing the motions of robots in simulations or on real mats. Most students improved greatly in mathematics after using the curricula. It is expected that the curricula based on Roboblocky will continue to be improved to enable more middle and high school students to be successful in learning mathematics.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"46 15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123761560","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":"Introductory Experiential Learning Projects Using Soft Robotics and Embedded Systems","authors":"A. Nagchaudhuri, Anthony Reyna, A. Das, Jackson Cuppett","doi":"10.1109/MESA55290.2022.10004395","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004395","url":null,"abstract":"This paper will outline experiential learning project efforts that undergraduate exchange students who participated in the summers of 2021 and 2022 involving soft robotics, embedded systems, and other automation endeavors ongoing at the Robotics Automation and Manufacturing (RAM) Laboratory at the University of Maryland Eastern Shore (UMES). The exchange students worked under the supervision of the primary author during the 10-week internship program sponsored by Maryland Space Grant Consortium. During the 2022 summer, they also supported a UMES graduate student with some of the ongoing field efforts related to agricultural automation and robotics.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130520088","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":"Trunk Movement Analysis with FDA: Exploratory Study for the Healthy Subject","authors":"C. Amici, Martina Mosso, F. Vérité, M. Tiboni, A. Borboni, S. Negrini","doi":"10.1109/MESA55290.2022.10004476","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004476","url":null,"abstract":"In this work, 48 acquisitions of trunk flexion-extension in healthy subjects are evaluated with the Functional Data Analysis (FDA) approach. Signals are registered with different strategies: i) assigning to the registering function two and three landmark points, and ii) aligning signals to a target profile externally imposed. The results are compared, and the normality profile for the analyzed sample is computed, revealing that the registration with three landmark points represents the best compromise between accuracy and computational burden for the current dataset. The reliability of FDA for the current purpose is investigated with the Leave-One-Out method, and the obtained results suggest the suitability of FDA for the analysis of this kind of data, although further studies should be performed increasing the original dataset in quantity and quality to extend the reliability of the normality profile to the whole healthy population.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121040650","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":"Deep Learning based Gesture Recognition for Drones","authors":"Min-Fan Ricky Lee, C. Chung, Adalberto Sergio Montania Espinola, Marcelo Javier Gómez Vera, Guillermo Federico Pallares Caballero","doi":"10.1109/MESA55290.2022.10004404","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004404","url":null,"abstract":"With the development of UAV, more and more people use the lens of drones for image recognition. Among them, the application of gesture recognition does not systematically sort out relevant information, and for gesture recognition, its accuracy will be a problem. In addition, during the recognition process, different scenes will also affect the judgment result of the gesture, so how to achieve the reduction of the interference brought by the venue is also a challenge. This paper summarizes recent papers on the application of gesture recognition on drones and applies it to gesture recognition. For the training module, the RNN and CNN architecture will be used for training. For the interference caused by the environment, we add more environment maps for the training. This paper summarizes the recent gesture recognition solutions and applies them to gesture recognition to improve the accuracy of gesture recognition, which will provide an additional option for gesture recognition control.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132920155","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":"Dynamics analysis of a fractional Chaotic relaxation econometric oscillator","authors":"Ake N'Gbo, N'Gbo N'Gbo, Jianhua Tang","doi":"10.1109/MESA55290.2022.10004401","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004401","url":null,"abstract":"In this article, a fractional Rocard's relaxation econometric oscillator is considered. Based on the fact that fractional derivatives incorporate memory factors, the integer order derivative is replaced by the Caputo fractional derivative. Stability and Hopf bifurcation conditions are obtained. Chaos in the fractional differential system is assessed by analyzing the Lyapunov characteristic exponents of the aforementioned system. Investigations show that the fractional system is chaotic and possesses similar dynamics, however, the bifurcation values differ from that of the classical system with a higher chaos occurrence probability.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115511441","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}