{"title":"Detection and Localizing of Rumex Seedlings for Robotic Weeding","authors":"Niko Känsäkoski, T. Heikkilä, Jarkko Kotaniemi","doi":"10.1109/MESA55290.2022.10004464","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004464","url":null,"abstract":"Weeds are causing substantial losses for livestock farming and decrease land cultivability in farming. Treating weeds with herbicides is harmful for the environment and we are targeting automatic mechanical weeding of Rumex longifolius in pastures using mobile field robot technologies. We are relying on 2D/3D computer vision technologies and have developed an algorithmic solution for detecting seedlings of Rumex weeds. We show promising test results on weed detecting and lozalizing for robotic removal.","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":"123701729","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}
Abdullah Ahmed, Yasser F. O. Mohammad, V. Parque, Haitham El-Hussieny, S. Ahmed
{"title":"End-to-End Mobile Robot Navigation using a Residual Deep Reinforcement Learning in Dynamic Human Environments","authors":"Abdullah Ahmed, Yasser F. O. Mohammad, V. Parque, Haitham El-Hussieny, S. Ahmed","doi":"10.1109/MESA55290.2022.10004394","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004394","url":null,"abstract":"Safe navigation through human crowds is key to enabling practical mobility ubiquitously. The Deep Reinforcement Learning (DRL) and the End-to-End (E2E) approaches to goal-oriented robot navigation have the potential to render policies able to tackle localization, path planning, obstacle avoidance, and adaptation to change in unison. In this paper, we report an architecture based on convolutional units and residual blocks being able to enhance adaptability to unseen and dynamic human environments. In particular, our scheme outperformed the state-of-the-art baselines SOADRL and NAVREP by about 13% and 18% on average success rate, respectively, throughout 27 unseen and dynamic navigation instances. Furthermore, our approach avoids the explicit encoding of positions and trajectories of moving humans compared to the standard models. Our results show the potential to render adaptive and generalizable policies for unknown and dynamic human environments.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"114 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":"133226152","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 Digital Twin Enabled Internet of Living Things (IoLT) Framework for Soil Carbon Management","authors":"Di An, Yangquan Chen","doi":"10.1109/MESA55290.2022.10004406","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004406","url":null,"abstract":"Due to the lack of cost-effective methods for soil carbon content accounting, soil carbon emissions cannot be managed properly for a long time. The traditional methods are labor intensive which usually need tedious preprocessing and expensive analyzers to quantify the total soil carbon content. In this paper, we propose that a Digital Twin with AIoLT framework could perfectly solve the challenge mentioned above. By using an AIoLT-enabled proximity radar sensor to measure soil carbon content in real-time, our proposed soil carbon management digital twin (SCMDT) has the ability to deal with these soil carbon data to be “smart” big data, which are from missionaware sampling strategies. We also provide an evaluation metric for our proposed SCMDT in order to quantify its performance.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"30 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":"131808092","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":"Conference Schedule","authors":"","doi":"10.1109/mesa55290.2022.10004471","DOIUrl":"https://doi.org/10.1109/mesa55290.2022.10004471","url":null,"abstract":"","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"61 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":"116595396","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":"XAIoT - The Future of Wearable Internet of Things","authors":"Rafal Krzysiak, Shalyn Nguyen, Yangquan Chen","doi":"10.1109/MESA55290.2022.10004460","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004460","url":null,"abstract":"The addition of Machine Learning and other Artificial Intelligent (AI) algorithms has expanded the capabilities of the Internet of Things (IoT) framework. However, the Artificial Internet of Things (AIoT), has also brought forward many issues with the combination, mainly lack of explanations and transparency. This lack of explanations of what AI models are doing is problematic in many fields, especially in the medical field. Explainable Artificial Intelligence (XAI) allows users to be given more in depth knowledge with the background processes of the model prediction. Enabling XAI into the IoT framework would develop a system that would not only capture Big Data more effectively, but also allow the system to be more transparent and explainable, causing wider adoption of the framework. This review focuses on current work done in AIoT and how it can be vastly improved with XAIoT. We propose an Explainable Artificial Intelligent Internet of Things (XAIoT) framework for monitoring physiological health using a smart watch.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"602 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":"133918048","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}
Ayaulym Nurpeissova, Asset Malik, Sanzhar Kabitkanov, Alikhan Zhilisbayev, A. Shintemirov
{"title":"An Open-Source Reconfigurable Robotic Gripper with Detachable Fingers","authors":"Ayaulym Nurpeissova, Asset Malik, Sanzhar Kabitkanov, Alikhan Zhilisbayev, A. Shintemirov","doi":"10.1109/MESA55290.2022.10004392","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004392","url":null,"abstract":"This paper presents a new open-source 3-fingered robotic gripper with a reconfigurable modular structure for extending the choice of reconfigurable robotic gripper designs freely available to robotics research community. Combination of unique design solutions, such as independent and modular (detachable) finger modules, which provide finger position and orientation reconfigurability and adaptivity to different shape objects, is experimentally demonstrated in a functional 3D-printed robotic gripper prototype. The proposed gripper prototype was built using off-the-shelf inexpensive components and 3D printing technology, ensuring low manufacturing cost and replicability. The paper also outlines the gripper control and demonstrates its performance in grasping different shape objects. The open-source design of the presented robotic gripper will be freely available for downloading from the authors' research lab web-site https://www.alaris.kz and https://github.com/alarisnu/alaris_LCRDF_Gripper upon further modernization, outlined in the future work discussion.","PeriodicalId":410029,"journal":{"name":"2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","volume":"27 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":"123728571","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}
M. C. Moreno, Yerson Duvan Angulo, Oscar J. Suarez
{"title":"Teleoperated robot prototype for the manipulation and transport of chemical substances in laboratory: a low-cost adaptation","authors":"M. C. Moreno, Yerson Duvan Angulo, Oscar J. Suarez","doi":"10.1109/MESA55290.2022.10004393","DOIUrl":"https://doi.org/10.1109/MESA55290.2022.10004393","url":null,"abstract":"Service robots are mechatronic systems designed to perform tasks partially or autonomously at the service of the well-being of humans, either due to the degree of complexity they represent or because they are executed in hostile environments. New control strategies and techniques have been implemented to reduce the accident rate in chemical laboratories, including robots with handling and mobility capabilities. This paper aims to implement a differential-type mobile robot and a robotic arm with two degrees-of-freedom (DoF) controlled through a mobile application that allows the adjustment of the speed parameters, the direction of the mobile robot, or the value of the manipulator's joint coordinates. In addition, a method for remote communication using the Internet of Things (IoT) on a Raspberry Pi 3 and a Raspberry Pi 3 Camera Rev 1.3 module is described. For the above, a web page developed in HyperText Markup Language (HTML) is presented to control the prototype and visualize the environment where it is executed. The experiments highlight the advantages of the system related to mobility and versatility.","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":"117019111","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}