Pub Date : 2018-09-01DOI: 10.1109/COMROB.2018.8689406
Jesus De Anda, J. A. Pámanes, J. Ollervides
This paper deals with the motion planning problem of an industrial robot to achieve welding tasks working in cooperation with a positioning table. We consider that sequential displacements must be achieved by the robot and the table until finish the whole task. Thus, a method is proposed to find the successive placements that must be attained by the cooperative table in order to locate the workpiece in such a way that the kinematic performance of the robot be optimized during the task. The method is applied for a welding robot during the tracking of a 3D path. Simulation studies show the efficacy of the proposed method.
{"title":"Motion Planning of a Welding Robot for Cooperative Tasks with a Sequential Positioning Device","authors":"Jesus De Anda, J. A. Pámanes, J. Ollervides","doi":"10.1109/COMROB.2018.8689406","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689406","url":null,"abstract":"This paper deals with the motion planning problem of an industrial robot to achieve welding tasks working in cooperation with a positioning table. We consider that sequential displacements must be achieved by the robot and the table until finish the whole task. Thus, a method is proposed to find the successive placements that must be attained by the cooperative table in order to locate the workpiece in such a way that the kinematic performance of the robot be optimized during the task. The method is applied for a welding robot during the tracking of a 3D path. Simulation studies show the efficacy of the proposed method.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133470294","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689413
M. Flores-Geronimo, E. G. Hernández-Martínez, E. D. Ferreira-Vazquez, J. Flores-Godoy, G. Fernández‐Anaya
Inspired on the focus of multi-agent systems used in groups of robots, this paper describes a novel modeling methodology for urban traffic networks based on the interconnections of simple generic differential equations about distinct streets and intersections. These nonlinear fluid equations represent features like vehicular density, average vehicle velocities, occupation capacities and the interconnections between adjacent street segments and intersections. In order to enable more realistic traffic light actions, individual petri nets are defined for each the intersections, enabling or disabling the flow of vehicles. Therefore, the main contribution is the definition of a hybrid modular scheme of continuous differential equations with discrete-event systems. A numerical simulation of a simple intersection using Matlab shows the performance of the approach and its scalability to more complex traffic networks.
{"title":"Modular Modelling for Urban Traffic Networks based on Multi-Agent Systems and Petri Nets","authors":"M. Flores-Geronimo, E. G. Hernández-Martínez, E. D. Ferreira-Vazquez, J. Flores-Godoy, G. Fernández‐Anaya","doi":"10.1109/COMROB.2018.8689413","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689413","url":null,"abstract":"Inspired on the focus of multi-agent systems used in groups of robots, this paper describes a novel modeling methodology for urban traffic networks based on the interconnections of simple generic differential equations about distinct streets and intersections. These nonlinear fluid equations represent features like vehicular density, average vehicle velocities, occupation capacities and the interconnections between adjacent street segments and intersections. In order to enable more realistic traffic light actions, individual petri nets are defined for each the intersections, enabling or disabling the flow of vehicles. Therefore, the main contribution is the definition of a hybrid modular scheme of continuous differential equations with discrete-event systems. A numerical simulation of a simple intersection using Matlab shows the performance of the approach and its scalability to more complex traffic networks.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115548079","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689415
A. Ortiz, J. Ibarra
This paper presents a self-calibration method to compensate the long-time degradation of the ground-foot sensory systems implemented on robots. The method is designed for specific self-designed and commercial humanoid robots, but it can be easily applied to any robot taking a few considerations.
{"title":"Self-calibration stage for performance improvement of ground-foot contact force sensory systems","authors":"A. Ortiz, J. Ibarra","doi":"10.1109/COMROB.2018.8689415","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689415","url":null,"abstract":"This paper presents a self-calibration method to compensate the long-time degradation of the ground-foot sensory systems implemented on robots. The method is designed for specific self-designed and commercial humanoid robots, but it can be easily applied to any robot taking a few considerations.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123270352","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689123
Romeo Falcón, H. Ríos, M. Mera, A. Dzul
This paper deals with the tracking control problem for a Quad-Rotor in the presence of external disturbances and only by means of the measurable positions and angles. To this aims, a constructive output-based robust control is designed based on: 1) sliding-mode observation theory, for state estimation; and 2) the attractive ellipsoid method, for control design. The closed-loop robust stability is proven through Lyapunov methods. The synthesis of the robust output-based control is expressed in terms of Linear Matrix Inequalities. Simulation results illustrate the feasibility of the proposed approach.
{"title":"Output-based Robust Control for Quad-Rotor Tracking: An Attractive Ellipsoid Approach","authors":"Romeo Falcón, H. Ríos, M. Mera, A. Dzul","doi":"10.1109/COMROB.2018.8689123","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689123","url":null,"abstract":"This paper deals with the tracking control problem for a Quad-Rotor in the presence of external disturbances and only by means of the measurable positions and angles. To this aims, a constructive output-based robust control is designed based on: 1) sliding-mode observation theory, for state estimation; and 2) the attractive ellipsoid method, for control design. The closed-loop robust stability is proven through Lyapunov methods. The synthesis of the robust output-based control is expressed in terms of Linear Matrix Inequalities. Simulation results illustrate the feasibility of the proposed approach.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115433462","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689424
S. Orozco-Soto, J. M. Ibarra-Zannatha, A. J. Malo-Tamayo, Andres Cureno-Ramirez
This paper presents an alternative for UAVs hover regulation by means of ADRC approach. The proposed control strategy was designed using Lyapunov's method to ensure asymptotic stability for vertical motion of the vehicle, including a sliding-observer for disturbance detection. The proposed controller was implemented in a Bebop 2 quadrotor using ROS middleware, and it was compared with a PD controller, showing successful results for altitude regulation even in presence of disturbances and unconsidered dynamics.
{"title":"Active Disturbance Rejection Control for UAV Hover using ROS","authors":"S. Orozco-Soto, J. M. Ibarra-Zannatha, A. J. Malo-Tamayo, Andres Cureno-Ramirez","doi":"10.1109/COMROB.2018.8689424","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689424","url":null,"abstract":"This paper presents an alternative for UAVs hover regulation by means of ADRC approach. The proposed control strategy was designed using Lyapunov's method to ensure asymptotic stability for vertical motion of the vehicle, including a sliding-observer for disturbance detection. The proposed controller was implemented in a Bebop 2 quadrotor using ROS middleware, and it was compared with a PD controller, showing successful results for altitude regulation even in presence of disturbances and unconsidered dynamics.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124744779","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689419
Alan Maldonado-Ramirez, I. López-Juárez, R. Rios-Cabrera
Reinforcement Learning has become a very powerful technique in the last decade thanks to the technological advances in computational power and efficient learning algorithms in neuronal networks. Reinforcement Learning allows an autonomous agent to learn through experience how to solve a problem in an optimal way, with a minimal information of its environment, just a reward signal. This approach has lightened the way to an artificial intelligence capable of reaching superhuman performance in games such as Go and Backgammon, beating world champion players. Unfortunately this is far from a real world robot application due to many technological challenges. So in this paper we propose how to get a low-dimensional state representation for industrial robot manipulators, using visual information and Convolutional Autoencoders to speed up the information processing in the Reinforcement Learning training phase.
{"title":"Deep Convolutional AutoEncoders as a Minimal State Representation for Reinforcement Learning in Industrial Robot Manipulators","authors":"Alan Maldonado-Ramirez, I. López-Juárez, R. Rios-Cabrera","doi":"10.1109/COMROB.2018.8689419","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689419","url":null,"abstract":"Reinforcement Learning has become a very powerful technique in the last decade thanks to the technological advances in computational power and efficient learning algorithms in neuronal networks. Reinforcement Learning allows an autonomous agent to learn through experience how to solve a problem in an optimal way, with a minimal information of its environment, just a reward signal. This approach has lightened the way to an artificial intelligence capable of reaching superhuman performance in games such as Go and Backgammon, beating world champion players. Unfortunately this is far from a real world robot application due to many technological challenges. So in this paper we propose how to get a low-dimensional state representation for industrial robot manipulators, using visual information and Convolutional Autoencoders to speed up the information processing in the Reinforcement Learning training phase.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128986642","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 : 2018-09-01DOI: 10.1109/COMROB.2018.8689422
Daniel Treviño-Sánchez, J. Guerrero-Castellanos, V. R. G. Díaz
This work presents the mathematical model of an ornithopter and the forces acting on it to achieve flight, especially mention the impact of the tail movement, which has two degrees of freedom, for the generation of torques that will allow the control of posture and direction of the vehicle.
{"title":"Modeling an Ornithopter to Design its Attitude Control","authors":"Daniel Treviño-Sánchez, J. Guerrero-Castellanos, V. R. G. Díaz","doi":"10.1109/COMROB.2018.8689422","DOIUrl":"https://doi.org/10.1109/COMROB.2018.8689422","url":null,"abstract":"This work presents the mathematical model of an ornithopter and the forces acting on it to achieve flight, especially mention the impact of the tail movement, which has two degrees of freedom, for the generation of torques that will allow the control of posture and direction of the vehicle.","PeriodicalId":446027,"journal":{"name":"2018 XX Congreso Mexicano de Robótica (COMRob)","volume":"94 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129046597","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：