Pub Date : 2019-11-01DOI: 10.1109/ICMEAE.2019.00030
A. Ortega-Gonzalez, U. Robles-Cervantes, I.N. Espiritu-Lopez, M. Ibarra-Manzano
This article presents the implementation of an algorithm for the classification of flexion angles in the joints. The proposed algorithm statistical models the data coming from a fiber sensor to detect flexion in a join. The system filters, models and classifies the signals of a fiber sensor, in addition to comparing the results of the classification for different joints.
{"title":"Identification of joints and their positions","authors":"A. Ortega-Gonzalez, U. Robles-Cervantes, I.N. Espiritu-Lopez, M. Ibarra-Manzano","doi":"10.1109/ICMEAE.2019.00030","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00030","url":null,"abstract":"This article presents the implementation of an algorithm for the classification of flexion angles in the joints. The proposed algorithm statistical models the data coming from a fiber sensor to detect flexion in a join. The system filters, models and classifies the signals of a fiber sensor, in addition to comparing the results of the classification for different joints.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"105 6 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":"115764205","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00021
P. Vargas-Chable, C. A. Ferrara-Bello, J. O. Sandoval-Reyes, M. Tecpoyotl-Torres, J. Varona
In this paper, a novel microgripper based on two perpendicular arrangements of beams and a chevron actuator is shown. In each perpendicular arrangement, the constrained displacement of the double clamped beams, joined at their endpoint, produces a buckling in each beam, which favors the displacement of each arm of the microgripper, normally open. These arrangements constitute the highly flexible structures of the microgripper. Their buckling is produced by the force applied by chevron arrow, producing a reaction force in the range of 174.44 $mu$ N in the microgripper jaws. Chevron actuator is fed by a thermal source. Temperature in microgripper tips is of 34.42°C and the operation frequency is 33.966 kHz, at maximum load thermal applied of 200°C. The mechanical, thermal and modal analyses of this integrated structure was supported by SIMSOLIDTM, based on Finite Element Analysis. The simulation was developed with Polysilicon as structural material.
{"title":"A novel electrothermal compliance microgripper","authors":"P. Vargas-Chable, C. A. Ferrara-Bello, J. O. Sandoval-Reyes, M. Tecpoyotl-Torres, J. Varona","doi":"10.1109/ICMEAE.2019.00021","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00021","url":null,"abstract":"In this paper, a novel microgripper based on two perpendicular arrangements of beams and a chevron actuator is shown. In each perpendicular arrangement, the constrained displacement of the double clamped beams, joined at their endpoint, produces a buckling in each beam, which favors the displacement of each arm of the microgripper, normally open. These arrangements constitute the highly flexible structures of the microgripper. Their buckling is produced by the force applied by chevron arrow, producing a reaction force in the range of 174.44 $mu$ N in the microgripper jaws. Chevron actuator is fed by a thermal source. Temperature in microgripper tips is of 34.42°C and the operation frequency is 33.966 kHz, at maximum load thermal applied of 200°C. The mechanical, thermal and modal analyses of this integrated structure was supported by SIMSOLIDTM, based on Finite Element Analysis. The simulation was developed with Polysilicon as structural material.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","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":"127699737","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00036
Carlos A. Piedrahita-Velásquez, Gustavo Patiño, Juan Pablo Urrea Duque
The estimation of performance metrics of a Network-on-Chip (NoC) is an increasingly important aspect of Multiprocessor System-on-Chip (MPSoC) design. As systems grow in number of components and features, the correct design of the Network-on-Chip has a central role in meeting the performance requirements of the system, because it is responsible for the efficient movement of data inside the MPSoC. In this paper a software tool called NoCSimulator which is based in queueing theory for the estimation of latency and throughput of a NoC is proposed. The contribution of this tool is its ability to generate stochastic traffic patterns based on real data traffic of scientific applications, not only synthetic traffic as similar tools reported in literature. This makes it possible to study NoC performance under real working conditions, which gives better insights about NoC behavior, and improves the design space exploration at early stages of system development. NoCSimulator was validated using two state-of-the-art cycle-accurate simulators (BookSim and Garnet). NoCSimulator, based in queueing theory, does not model hardware aspects of the NoC as a cycle-accurate simulator, so, long simulation times of complex systems can be avoided during design space exploration.
{"title":"NoC Performance Estimation Based on Queueing Theory for Real Scientific Applications","authors":"Carlos A. Piedrahita-Velásquez, Gustavo Patiño, Juan Pablo Urrea Duque","doi":"10.1109/ICMEAE.2019.00036","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00036","url":null,"abstract":"The estimation of performance metrics of a Network-on-Chip (NoC) is an increasingly important aspect of Multiprocessor System-on-Chip (MPSoC) design. As systems grow in number of components and features, the correct design of the Network-on-Chip has a central role in meeting the performance requirements of the system, because it is responsible for the efficient movement of data inside the MPSoC. In this paper a software tool called NoCSimulator which is based in queueing theory for the estimation of latency and throughput of a NoC is proposed. The contribution of this tool is its ability to generate stochastic traffic patterns based on real data traffic of scientific applications, not only synthetic traffic as similar tools reported in literature. This makes it possible to study NoC performance under real working conditions, which gives better insights about NoC behavior, and improves the design space exploration at early stages of system development. NoCSimulator was validated using two state-of-the-art cycle-accurate simulators (BookSim and Garnet). NoCSimulator, based in queueing theory, does not model hardware aspects of the NoC as a cycle-accurate simulator, so, long simulation times of complex systems can be avoided during design space exploration.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","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":"127625051","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00017
Edgar Cortés-Gallardo, C. Moreno-García, Alfredo Zhu, Daniela. Chípuli-Silva, J. A. Gonzalez-Gonzalez, Domenico. Morales-Ortiz, Sebastian Fernandez, Bernardo. Urriza, Juan. Valverde-López, Arath Marín, Hugo Pérez, J. Izquierdo-Reyes, Rogelio Bustamante-Bello
Panorama stitching consists on frames being merged to create a 360° view. This technique is proposed for its implementation in autonomous vehicles instead of the use of an external 360-degree camera, mostly due to its reduced cost and improved aerodynamics. This strategy requires a fast and robust set of features to be extracted from the images obtained by the cameras located around the inside of the car, in order to effectively compute the panoramic view in real time and avoid hazards on the road. This paper compares and creates discussion of three feature extraction methods (i.e. SIFT, BRISK and SURF) for image feature extraction, in order to decide which one is more suitable for a panorama stitching application in an autonomous car architecture. Experimental validation shows that SURF exhibits an improved performance under a variety of image transformations, and thus appears to be the most suitable of these three methods, given its accuracy when comparing features between both images, while maintaining a low time consumption. Furthermore, a comparison of the results obtained with respect to similar work allows us to increase the reliability of our methodology and the reach of our conclusions.
{"title":"A Comparison of Feature Extractors for Panorama Stitching in an Autonomous Car Architecture","authors":"Edgar Cortés-Gallardo, C. Moreno-García, Alfredo Zhu, Daniela. Chípuli-Silva, J. A. Gonzalez-Gonzalez, Domenico. Morales-Ortiz, Sebastian Fernandez, Bernardo. Urriza, Juan. Valverde-López, Arath Marín, Hugo Pérez, J. Izquierdo-Reyes, Rogelio Bustamante-Bello","doi":"10.1109/ICMEAE.2019.00017","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00017","url":null,"abstract":"Panorama stitching consists on frames being merged to create a 360° view. This technique is proposed for its implementation in autonomous vehicles instead of the use of an external 360-degree camera, mostly due to its reduced cost and improved aerodynamics. This strategy requires a fast and robust set of features to be extracted from the images obtained by the cameras located around the inside of the car, in order to effectively compute the panoramic view in real time and avoid hazards on the road. This paper compares and creates discussion of three feature extraction methods (i.e. SIFT, BRISK and SURF) for image feature extraction, in order to decide which one is more suitable for a panorama stitching application in an autonomous car architecture. Experimental validation shows that SURF exhibits an improved performance under a variety of image transformations, and thus appears to be the most suitable of these three methods, given its accuracy when comparing features between both images, while maintaining a low time consumption. Furthermore, a comparison of the results obtained with respect to similar work allows us to increase the reliability of our methodology and the reach of our conclusions.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"41 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":"115088989","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00010
C.R. Estrivero-Chavez, M. A. Contreras-Teran, J.A. Miranda-Hernandez, J. Cardenas-Cornejo, M. Ibarra-Manzano, D. Almanza-Ojeda
This article presents a new algorithm that serves as support for people interested in learning sign language base on the Mexican Sign Language Dictionary provided by the CONAPRED (National Council to Prevent Discrimination) in the 2011 edition. The system uses the Leap Motion machine shadow interaction system to capture the position of each finger of both hands, and by geometric modeling up to 27 signs can be statically modeled with an accuracy of 99.80%.
{"title":"Toward a Mexican Sign Language System using Human Computer Interface","authors":"C.R. Estrivero-Chavez, M. A. Contreras-Teran, J.A. Miranda-Hernandez, J. Cardenas-Cornejo, M. Ibarra-Manzano, D. Almanza-Ojeda","doi":"10.1109/ICMEAE.2019.00010","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00010","url":null,"abstract":"This article presents a new algorithm that serves as support for people interested in learning sign language base on the Mexican Sign Language Dictionary provided by the CONAPRED (National Council to Prevent Discrimination) in the 2011 edition. The system uses the Leap Motion machine shadow interaction system to capture the position of each finger of both hands, and by geometric modeling up to 27 signs can be statically modeled with an accuracy of 99.80%.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"6 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":"133530255","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00014
O. Almanza-Conejo, M. Ibarra-Manzano
Telepresence is a necessity in today’s world, and it is very important to develop it with great precision for assisted robot. Analyzed the movement during the flexion in joins is important to adapt them to robots. This paper presents the signal processing to synthetize the finger movements applied to service robot. Fiber optics sensor is used to detect the angle in the join, after that Recursive Least Square algorithm was carried out to reduce the noise in the signal. Furthermore, statistical feature extraction and machine learning algorithm was performed to classifying the thresholds angle in the join. Comparative analysis was developed to select the best algorithm to detect the angle in the join.
{"title":"Flexion Detection Algorithm’s Applied to Classifying Joint Movements Based on Fiber Sensors","authors":"O. Almanza-Conejo, M. Ibarra-Manzano","doi":"10.1109/ICMEAE.2019.00014","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00014","url":null,"abstract":"Telepresence is a necessity in today’s world, and it is very important to develop it with great precision for assisted robot. Analyzed the movement during the flexion in joins is important to adapt them to robots. This paper presents the signal processing to synthetize the finger movements applied to service robot. Fiber optics sensor is used to detect the angle in the join, after that Recursive Least Square algorithm was carried out to reduce the noise in the signal. Furthermore, statistical feature extraction and machine learning algorithm was performed to classifying the thresholds angle in the join. Comparative analysis was developed to select the best algorithm to detect the angle in the join.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"62 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":"121946239","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00029
O. Sandre-Hernández, P. Ordaz-Oliver, C. Cuvas-Castillo
This paper presents the sensorless field oriented control of a brushless direct current motor (BLDC). A sliding mode observer is used to estimate the phase currents, after the current observer, a back-EMF observer is proposed to estimate the electrical position and speed of the rotor. The back-EMF sensorless operation is intended for medium to high speed. A comparison with a conventional observer and the proposed observer is carried out. Numerical simulations are presented to validate the proposed sliding mode observer for the sensorless field oriented control of a BLDC motor.
{"title":"Sensorless Field Oriented Control of BLDC motor based on Sliding Mode Observer","authors":"O. Sandre-Hernández, P. Ordaz-Oliver, C. Cuvas-Castillo","doi":"10.1109/ICMEAE.2019.00029","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00029","url":null,"abstract":"This paper presents the sensorless field oriented control of a brushless direct current motor (BLDC). A sliding mode observer is used to estimate the phase currents, after the current observer, a back-EMF observer is proposed to estimate the electrical position and speed of the rotor. The back-EMF sensorless operation is intended for medium to high speed. A comparison with a conventional observer and the proposed observer is carried out. Numerical simulations are presented to validate the proposed sliding mode observer for the sensorless field oriented control of a BLDC motor.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"85 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":"123337856","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00013
Alejandro Salinas-Medina, Humberto Poblano-Rosas, M. Bustamante-Bello, Luis A. Curiel-Ramirez, Sergio A. Navarro-Tuch, J. Izquierdo-Reyes
Facial expression recognition has been an active research area, with an increasing number of applications like avatar animation, cyber security, and neuromarketing. The use of neural networks and data science are having a strong growth in research centers and universities; the field of machine learning is booming because it is a strong tool and it has an immense amount of applications. The purpose of this paper is the development of a Live Emotions Predictor using Convolutional Neural Networks, this was developed in different sections, the part of data processing and its own training using a Convolutional Neural Network (CNN) that generates accurate and precise predictions of the 5 main emotions in a graphical way. For the processing part it is important to have data that can be trained, preprocessing, and thus be able to have better results. The data generated by iMotion® are CSV files and the first part was to be able to have a clean database for its training. In the training part, the challenge was to generate a sufficiently robust CNN so we can obtain highly reliable "accuracy's" (percentages greater than 88%), determining the main architecture and all its layers to obtain these results.
{"title":"A Live Emotions Predictor System Using Convolutional Neural Networks","authors":"Alejandro Salinas-Medina, Humberto Poblano-Rosas, M. Bustamante-Bello, Luis A. Curiel-Ramirez, Sergio A. Navarro-Tuch, J. Izquierdo-Reyes","doi":"10.1109/ICMEAE.2019.00013","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00013","url":null,"abstract":"Facial expression recognition has been an active research area, with an increasing number of applications like avatar animation, cyber security, and neuromarketing. The use of neural networks and data science are having a strong growth in research centers and universities; the field of machine learning is booming because it is a strong tool and it has an immense amount of applications. The purpose of this paper is the development of a Live Emotions Predictor using Convolutional Neural Networks, this was developed in different sections, the part of data processing and its own training using a Convolutional Neural Network (CNN) that generates accurate and precise predictions of the 5 main emotions in a graphical way. For the processing part it is important to have data that can be trained, preprocessing, and thus be able to have better results. The data generated by iMotion® are CSV files and the first part was to be able to have a clean database for its training. In the training part, the challenge was to generate a sufficiently robust CNN so we can obtain highly reliable \"accuracy's\" (percentages greater than 88%), determining the main architecture and all its layers to obtain these results.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","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":"127468229","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00019
C. A. Ferrara-Bello, J. O. Sandoval-Reyes, P. Vargas-Chable, M. Tecpoyotl-Torres, J. Varona
This article presents the design and implementation of a microgripper device actuated by a piezoelectric stack. In order to reduce fabrication costs, conventional piezoelectric buzzers are used that are easily found in the market at very low cost. Polylactic Acid (PLA) was chosen as the structural material for the design of the mechanisms of the microgripper, the choice of this material considerably reduces the total implementation cost. The originality of this work resides in the material used and in the stacked piezoelectric actuator. The main contribution is the demonstration of a design methodology that implements prototype compliance mechanisms at millimeter scale for validation purposes before proceeding to the fabrication in micrometric scale. Even so, the system in mm scale can also be used for micromanipulation due to the range of its microgripper jaws’ aperture and its reliability. ANSYSTM was used as the software tool for simulation.
{"title":"Design and 3D printed implementation of a microgripper actuated by a piezoelectric stack","authors":"C. A. Ferrara-Bello, J. O. Sandoval-Reyes, P. Vargas-Chable, M. Tecpoyotl-Torres, J. Varona","doi":"10.1109/ICMEAE.2019.00019","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00019","url":null,"abstract":"This article presents the design and implementation of a microgripper device actuated by a piezoelectric stack. In order to reduce fabrication costs, conventional piezoelectric buzzers are used that are easily found in the market at very low cost. Polylactic Acid (PLA) was chosen as the structural material for the design of the mechanisms of the microgripper, the choice of this material considerably reduces the total implementation cost. The originality of this work resides in the material used and in the stacked piezoelectric actuator. The main contribution is the demonstration of a design methodology that implements prototype compliance mechanisms at millimeter scale for validation purposes before proceeding to the fabrication in micrometric scale. Even so, the system in mm scale can also be used for micromanipulation due to the range of its microgripper jaws’ aperture and its reliability. ANSYSTM was used as the software tool for simulation.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"2 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":"114484278","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 : 2019-11-01DOI: 10.1109/ICMEAE.2019.00015
Bernardo A. Urriza-Arellano, Edgar Cortés-Gallardo, Rogelio Bustamante-Bello, Antonio C. Rivera-Corona, Areli Rodriguez-Tirado, Christian Tena-Padilla
The endeavor on this paper aims to present a physical robotic platform with the main purpose of addressing the subject of autonomous mobility for both people and goods. The platform, which runs on ROS (Robot Operating System) and VESC Project resources, contains a basic implementation of a behavioral cloning deep neural network in order to achieve a certain level of autonomy, which will be further developed in a series of subsequent papers. Use cases for the autonomous platform are warehouse commodity management, medical material transportation in hospitals, airport luggage logistics and personal mobility for handicapped people. The progress landed in this regard goes in hand with self-driving cars, another key target use case for the proposed platform as test bench. Mobility tests are carried out to assert adequate physical operation, resulting in effective performance at up to 17km/h and secure current, voltage and temperature values for the brushless DC motors, battery and controllers. As for artificial intelligence testing, training accuracy for the neural network presents a value of 0.9536, whereas validation settles at 0.9481, which provides a confident trained model for later implementation.
{"title":"Autonomous Robotic Platform Training on Behavioral Cloning Neural Networks using ROS and VESC Project Resources","authors":"Bernardo A. Urriza-Arellano, Edgar Cortés-Gallardo, Rogelio Bustamante-Bello, Antonio C. Rivera-Corona, Areli Rodriguez-Tirado, Christian Tena-Padilla","doi":"10.1109/ICMEAE.2019.00015","DOIUrl":"https://doi.org/10.1109/ICMEAE.2019.00015","url":null,"abstract":"The endeavor on this paper aims to present a physical robotic platform with the main purpose of addressing the subject of autonomous mobility for both people and goods. The platform, which runs on ROS (Robot Operating System) and VESC Project resources, contains a basic implementation of a behavioral cloning deep neural network in order to achieve a certain level of autonomy, which will be further developed in a series of subsequent papers. Use cases for the autonomous platform are warehouse commodity management, medical material transportation in hospitals, airport luggage logistics and personal mobility for handicapped people. The progress landed in this regard goes in hand with self-driving cars, another key target use case for the proposed platform as test bench. Mobility tests are carried out to assert adequate physical operation, resulting in effective performance at up to 17km/h and secure current, voltage and temperature values for the brushless DC motors, battery and controllers. As for artificial intelligence testing, training accuracy for the neural network presents a value of 0.9536, whereas validation settles at 0.9481, which provides a confident trained model for later implementation.","PeriodicalId":422872,"journal":{"name":"2019 International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE)","volume":"2 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":"128529271","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}