{"title":"Humanoid Robot Motion Control for Ramps and Stairs","authors":"Tommy Truong, A. Weitzenfeld","doi":"10.5038/qdna1747","DOIUrl":"https://doi.org/10.5038/qdna1747","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131728305","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}
Sean Bridges, Garhett Smith, Rene Preston, H. Sevil, Michael Reynolds
Brushless Direct Current (BLDC) actuators are recognized for their combined torque capabilities, precision control, and operational versatility, especially in regards to their smaller size. Actuators of this caliber are commonly implemented in high-performance industrial robotic arms, development in exoskeletal technologies, and quadrupedal robotic platforms. Professionally-developed brushless actuators available in the commercial sector deliver in their performance, however at a significant monetary expense. Our aim is to produce cost-efficient robotic actuators which are capable of replicating the design specifications and performance of commercial models. Our research focuses on the understanding and validation of fundamental principles of how brushless motors operate, and how the manipulation of respected variables can be combined to produce an optimized, robotic actuator design. The design and manufacturing process for each actuator prototype for this research revolves around a modular approach, where specific components can be repaired or replaced without compromising the structural integrity or robustness of the system. Each prototype utilizes a unique rotor and embedded planetary gearbox design as a mechanical means for increasing the potential torque output. Design constraints were set in place to properly analyze multi-variable combinations, which would ultimately maximize the electric torque density generated from induced electromagnetic forces. We believe that the results from our project can make cost-effective actuators available to the robotics community for advancing legged-locomotion robotic research.
{"title":"BLDC Actuators Revisited: A New Cost-Effective Design and Manufacturing for Robotic Applications","authors":"Sean Bridges, Garhett Smith, Rene Preston, H. Sevil, Michael Reynolds","doi":"10.5038/olhy7331","DOIUrl":"https://doi.org/10.5038/olhy7331","url":null,"abstract":"Brushless Direct Current (BLDC) actuators are recognized for their combined torque capabilities, precision control, and operational versatility, especially in regards to their smaller size. Actuators of this caliber are commonly implemented in high-performance industrial robotic arms, development in exoskeletal technologies, and quadrupedal robotic platforms. Professionally-developed brushless actuators available in the commercial sector deliver in their performance, however at a significant monetary expense. Our aim is to produce cost-efficient robotic actuators which are capable of replicating the design specifications and performance of commercial models. Our research focuses on the understanding and validation of fundamental principles of how brushless motors operate, and how the manipulation of respected variables can be combined to produce an optimized, robotic actuator design. The design and manufacturing process for each actuator prototype for this research revolves around a modular approach, where specific components can be repaired or replaced without compromising the structural integrity or robustness of the system. Each prototype utilizes a unique rotor and embedded planetary gearbox design as a mechanical means for increasing the potential torque output. Design constraints were set in place to properly analyze multi-variable combinations, which would ultimately maximize the electric torque density generated from induced electromagnetic forces. We believe that the results from our project can make cost-effective actuators available to the robotics community for advancing legged-locomotion robotic research.","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"B1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126836330","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}
Sebastian Story, Reinel Mota, Osmany Gonzalez, Kyle Reynolds, David Perez, Berry Lamy, I. Tansel
{"title":"Granular Material Extruder for Autonomous Asphalt Layer","authors":"Sebastian Story, Reinel Mota, Osmany Gonzalez, Kyle Reynolds, David Perez, Berry Lamy, I. Tansel","doi":"10.5038/vput8743","DOIUrl":"https://doi.org/10.5038/vput8743","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124988455","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}
Anthony L. Michel, Brandon Chacon, Matthew Laurent, David Perez, Berry Lamy, I. Tansel
Asphalt laying is a labor-intensive process and creates extensive air pollution. Next generation environment friendly machines need to minimize the emissions and necessary manual labor. Autonomously operating machines are expected to replace the current ones. These machines will need to measure the road profile to perform their operation. Laser based road profile measurement sensors are expensive and require a clean environment to perform their single point or line inspection with a fraction of micron accuracy. Recently, stereoscopic imaging has been selected by the automobile manufacturers for autonomous driving. In this study performance of the stereoscopic imaging technique of Intel RealSense D455 camera was evaluated for estimation of the surface profile in the narrow strip at the back of the asphalt laying machine. Laboratory and field tests were performed in the study. At the laboratory tests, four different heights were created on the floor by using boxes with different heights. RealSense D455 was used to take pictures. The height distribution of the images along a line on the floor was estimated by the camera after single shutter action. The manufacturer’s 2% accuracy at 4 m distance was verified in the study. At the field test, the profile of an actual pothole was evaluated, and similar performance was observed. The study indicated that stereoscopic imaging methods could be used to estimate the road profile if the expected accuracy is around plus minus 1 cm when the strip length is about 50 cm or less. The main advantage is getting the data from single shutter action in a very short time without any need for point to point or line scanning.
{"title":"Machine Vision System for Autonomous Asphalt Layer","authors":"Anthony L. Michel, Brandon Chacon, Matthew Laurent, David Perez, Berry Lamy, I. Tansel","doi":"10.5038/egru5600","DOIUrl":"https://doi.org/10.5038/egru5600","url":null,"abstract":"Asphalt laying is a labor-intensive process and creates extensive air pollution. Next generation environment friendly machines need to minimize the emissions and necessary manual labor. Autonomously operating machines are expected to replace the current ones. These machines will need to measure the road profile to perform their operation. Laser based road profile measurement sensors are expensive and require a clean environment to perform their single point or line inspection with a fraction of micron accuracy. Recently, stereoscopic imaging has been selected by the automobile manufacturers for autonomous driving. In this study performance of the stereoscopic imaging technique of Intel RealSense D455 camera was evaluated for estimation of the surface profile in the narrow strip at the back of the asphalt laying machine. Laboratory and field tests were performed in the study. At the laboratory tests, four different heights were created on the floor by using boxes with different heights. RealSense D455 was used to take pictures. The height distribution of the images along a line on the floor was estimated by the camera after single shutter action. The manufacturer’s 2% accuracy at 4 m distance was verified in the study. At the field test, the profile of an actual pothole was evaluated, and similar performance was observed. The study indicated that stereoscopic imaging methods could be used to estimate the road profile if the expected accuracy is around plus minus 1 cm when the strip length is about 50 cm or less. The main advantage is getting the data from single shutter action in a very short time without any need for point to point or line scanning.","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126456466","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}
David Perez, Berry Lamy, Alireza Modir, Arnaud Casterman, I. Tansel
{"title":"Detection of Internal Voids of Additively Manufactured Parts with Structual Health Monitoring Methods","authors":"David Perez, Berry Lamy, Alireza Modir, Arnaud Casterman, I. Tansel","doi":"10.5038/msuo7502","DOIUrl":"https://doi.org/10.5038/msuo7502","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114916527","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}
Hunter Smatla, Robert Shaw, Samuel Esse, Landen Rhodes
{"title":"Implementing Nonelinear Control of a Six Degree of Freedom Robotic Arm on a Raspberry Pi 3","authors":"Hunter Smatla, Robert Shaw, Samuel Esse, Landen Rhodes","doi":"10.5038/uaje6514","DOIUrl":"https://doi.org/10.5038/uaje6514","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116851064","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}
Christian Janke, Stefan Kleinke, Kimberly T. Luthi, Yuetong Lin
{"title":"Using Small UAS for STEM Education: Introducing Robotics and Mechatronics with Drones","authors":"Christian Janke, Stefan Kleinke, Kimberly T. Luthi, Yuetong Lin","doi":"10.5038/qqgn3785","DOIUrl":"https://doi.org/10.5038/qqgn3785","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125612704","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}
Advancements in robotics, artificial intelligence, and other automation have highlighted the need for humans to work together with machines in a more flexible and collaborative fashion than previously possible. To formulate effective human-robot teams, it is critical to understand which factors play important roles in enhancing human-robot teamwork. To gain preliminary insights into key factors of effective human-robot teams, we carried out an experiment using an enhanced version of the “Lunar Lander” game, where the goal is to safely land a spacecraft on the moon’s surface in concert with an AI teammate. We specifically attempted to observe some patterns of communication across high-performing teams in the experiment. Due to the limited number of experimental participants, the results of the experiment did not definitively identify the factors that account for effective teams. Instead, the experiment indicated potential avenues to further investigate, including intent-oriented communication and trust in teams with human and non-human entities. This paper presents findings from the experiment and discusses future work to extend the scope of the study to include teleoperation of unmanned vehicles with communication delay.
{"title":"Preliminary Insights into Enhancing Human-Robot Teamwork","authors":"Kazuhiko Momose, T. Weekes, T. Eskridge","doi":"10.5038/yexl3996","DOIUrl":"https://doi.org/10.5038/yexl3996","url":null,"abstract":"Advancements in robotics, artificial intelligence, and other automation have highlighted the need for humans to work together with machines in a more flexible and collaborative fashion than previously possible. To formulate effective human-robot teams, it is critical to understand which factors play important roles in enhancing human-robot teamwork. To gain preliminary insights into key factors of effective human-robot teams, we carried out an experiment using an enhanced version of the “Lunar Lander” game, where the goal is to safely land a spacecraft on the moon’s surface in concert with an AI teammate. We specifically attempted to observe some patterns of communication across high-performing teams in the experiment. Due to the limited number of experimental participants, the results of the experiment did not definitively identify the factors that account for effective teams. Instead, the experiment indicated potential avenues to further investigate, including intent-oriented communication and trust in teams with human and non-human entities. This paper presents findings from the experiment and discusses future work to extend the scope of the study to include teleoperation of unmanned vehicles with communication delay.","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124029252","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":"Transposed Jacobian Control of a Mobile Robot","authors":"D. R. Isenberg","doi":"10.5038/dmpv4200","DOIUrl":"https://doi.org/10.5038/dmpv4200","url":null,"abstract":"","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114873113","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}
In this work, Machine Learning approaches were applied to attacking behaviors in RoboCup Small-Size League autonomous robot soccer. Neural networks were used in order to get a binary prediction of an attacking action’s success, while deep reinforcement learning was leveraged to learn low level skills which control the robot’s wheel speeds and kicker. A trained neural network was used to predict whether a shot would be successful, improving the number of goals scored by the attacking behavior by 84 to 186%. The reinforcement learning methodologies used in this work produced behaviors which were efficient in speed, beating manually programmed behaviors in time taken, but can benefit from future refinements to improve accuracy in shooting towards goal.
{"title":"Machine Learning Approaches for Attacking Behaviors in Robot Soccer","authors":"Justin Rodney, A. Weitzenfeld","doi":"10.5038/jhsp3238","DOIUrl":"https://doi.org/10.5038/jhsp3238","url":null,"abstract":"In this work, Machine Learning approaches were applied to attacking behaviors in RoboCup Small-Size League autonomous robot soccer. Neural networks were used in order to get a binary prediction of an attacking action’s success, while deep reinforcement learning was leveraged to learn low level skills which control the robot’s wheel speeds and kicker. A trained neural network was used to predict whether a shot would be successful, improving the number of goals scored by the attacking behavior by 84 to 186%. The reinforcement learning methodologies used in this work produced behaviors which were efficient in speed, beating manually programmed behaviors in time taken, but can benefit from future refinements to improve accuracy in shooting towards goal.","PeriodicalId":165319,"journal":{"name":"Proceedings of the 35th Florida Conference on Recent Advances in Robotics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127038485","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：