Pub Date : 2015-04-09DOI: 10.1109/ICARA.2015.7081188
A. Ravankar, Yukinori Kobayashi, Ankit A. Ravankar, T. Emaru
This paper proposes an extended connected-components labeling algorithm for sparse Lidar (Light detection and ranging) sensor data. It is difficult to label sparse Lidar data using the general connected-component labeling algorithm. The proposed technique first increases the density of the sparse data by performing mathematical morphological operation of dilation. Next, labeling is performed on the dilated data, and the resultant labels are mapped to the input sparse Lidar data. The proposed technique does not distort the input Lidar data. We show the application of the proposed algorithm in map building using clustering. Results show that the proposed method can label sparse Lidar data to build maps.
提出了一种稀疏激光雷达(Light detection and ranging)传感器数据的扩展连通分量标记算法。使用一般的连通分量标记算法难以对稀疏激光雷达数据进行标记。该方法首先通过对稀疏数据进行数学形态学运算来增加稀疏数据的密度。接下来，对扩展后的数据进行标记，并将结果标签映射到输入的稀疏激光雷达数据。该技术不会使输入的激光雷达数据失真。我们展示了该算法在基于聚类的地图构建中的应用。实验结果表明，该方法可以对稀疏的激光雷达数据进行标记，从而建立地图。
{"title":"A connected component labeling algorithm for sparse Lidar data segmentation","authors":"A. Ravankar, Yukinori Kobayashi, Ankit A. Ravankar, T. Emaru","doi":"10.1109/ICARA.2015.7081188","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081188","url":null,"abstract":"This paper proposes an extended connected-components labeling algorithm for sparse Lidar (Light detection and ranging) sensor data. It is difficult to label sparse Lidar data using the general connected-component labeling algorithm. The proposed technique first increases the density of the sparse data by performing mathematical morphological operation of dilation. Next, labeling is performed on the dilated data, and the resultant labels are mapped to the input sparse Lidar data. The proposed technique does not distort the input Lidar data. We show the application of the proposed algorithm in map building using clustering. Results show that the proposed method can label sparse Lidar data to build maps.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121352739","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081139
Christian D. Heise, F. Holzapfel
In this paper, a novel Linear Matrix Inequality (LMI) condition for Uniform Ultimate Boundedness (UUB) of Model Reference Adaptive Control with σ-Modification in the presence of unmatched parametric uncertainties is presented. Due to the presence of unmatched uncertainties and due to the usage of the σ-Modification, the control objective of tracking a reference model may only be achieved approximately. A formulation of the UUB condition within the LMI framework provides less conservative bounds on the tracking error. This feature also enables the extension of the UUB condition towards a gain synthesis procedure, which allows the explicit specification of tracking error requirements. For a low-order system, it is demonstrated that the theoretically guaranteed bound on the tracking error of the synthesized adaptive controller is not overly conservative.
{"title":"Uniform ultimate boundedness of a Model Reference Adaptive Controller in the presence of unmatched parametric uncertainties","authors":"Christian D. Heise, F. Holzapfel","doi":"10.1109/ICARA.2015.7081139","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081139","url":null,"abstract":"In this paper, a novel Linear Matrix Inequality (LMI) condition for Uniform Ultimate Boundedness (UUB) of Model Reference Adaptive Control with σ-Modification in the presence of unmatched parametric uncertainties is presented. Due to the presence of unmatched uncertainties and due to the usage of the σ-Modification, the control objective of tracking a reference model may only be achieved approximately. A formulation of the UUB condition within the LMI framework provides less conservative bounds on the tracking error. This feature also enables the extension of the UUB condition towards a gain synthesis procedure, which allows the explicit specification of tracking error requirements. For a low-order system, it is demonstrated that the theoretically guaranteed bound on the tracking error of the synthesized adaptive controller is not overly conservative.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680150","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081207
Guillermo P. Falconi, Christian D. Heise, F. Holzapfel
A position tracking controller for a hexacopter is presented which is robust against disturbances like modeling errors or propulsion efficiency degradation. The presented controller stands out because of its simple design which does not resort to reconfiguration and avoids the necessity of a Failure Detection and Isolation (FDI) filter. The baseline controller has a cascaded structure with two loops. The outer loop corresponds to the position and velocity control and is designed using linear control. The inner loop corresponds to the attitude control which is a Nonlinear Dynamic Inversion (NDI). The baseline controller is augmented by an Extended State Observer (ESO) which provides an estimate of the disturbances and modeling errors which is then fed back to the control law. The performance as well as the robustness of the control system is significantly improved as demonstrated in simulation, where controlled flight is achieved even under severe actuator degradation.
{"title":"Fault-tolerant position tracking of a hexacopter using an Extended State Observer","authors":"Guillermo P. Falconi, Christian D. Heise, F. Holzapfel","doi":"10.1109/ICARA.2015.7081207","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081207","url":null,"abstract":"A position tracking controller for a hexacopter is presented which is robust against disturbances like modeling errors or propulsion efficiency degradation. The presented controller stands out because of its simple design which does not resort to reconfiguration and avoids the necessity of a Failure Detection and Isolation (FDI) filter. The baseline controller has a cascaded structure with two loops. The outer loop corresponds to the position and velocity control and is designed using linear control. The inner loop corresponds to the attitude control which is a Nonlinear Dynamic Inversion (NDI). The baseline controller is augmented by an Extended State Observer (ESO) which provides an estimate of the disturbances and modeling errors which is then fed back to the control law. The performance as well as the robustness of the control system is significantly improved as demonstrated in simulation, where controlled flight is achieved even under severe actuator degradation.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131579329","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081204
Y. Kuriki, T. Namerikawa
In this study, we consider cooperative control issues for a multi-unmanned aerial vehicle (UAV) system. Specifically, we present a cooperative formation control strategy for a multi-UAV system with unidirectional network links. Our strategy is to apply a consensus-based algorithm and leader-follower structure to the UAVs so that they can cooperatively fly in formation. The leader provides each UAV with commands to generate a geometric configuration of the formation. Convergence is guaranteed when the cooperative formation control algorithm is applied to the UAVs. Collisions among UAVs can occur when they are flying with the cooperative control UAVs. Our strategy for collision avoidance is to apply an artificial potential approach to the UAVs. Experiments are performed on multiple commercial small UAVs to validate the proposed formation control algorithm with collision-avoidance capability.
{"title":"Experimental validation of cooperative formation control with collision avoidance for a multi-UAV system","authors":"Y. Kuriki, T. Namerikawa","doi":"10.1109/ICARA.2015.7081204","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081204","url":null,"abstract":"In this study, we consider cooperative control issues for a multi-unmanned aerial vehicle (UAV) system. Specifically, we present a cooperative formation control strategy for a multi-UAV system with unidirectional network links. Our strategy is to apply a consensus-based algorithm and leader-follower structure to the UAVs so that they can cooperatively fly in formation. The leader provides each UAV with commands to generate a geometric configuration of the formation. Convergence is guaranteed when the cooperative formation control algorithm is applied to the UAVs. Collisions among UAVs can occur when they are flying with the cooperative control UAVs. Our strategy for collision avoidance is to apply an artificial potential approach to the UAVs. Experiments are performed on multiple commercial small UAVs to validate the proposed formation control algorithm with collision-avoidance capability.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131999703","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081181
Mauricio A. Gomez, E. Matson, Jihyun Song, SiYoung Baek, Junho Kim
Recent trends are to build tall buildings in big cities as a way out of the current housing overpopulation problem. These new structures unveil problems that if not addressed in time could cause catastrophes of unimaginable impact. One of those problems is the incidence of a fire threat happening upstairs in one of those buildings. Research solutions include implementation of multi-agent fire safety systems for fire threats in high rise buildings. Humans, agents, robots, machines and sensors communication model is used for indistinguishability of actors. This work discusses the implementation of the unmanned ground vehicles to spot the real location of the fire.
{"title":"UGVs spotting fire location for Cooperative Fire Security System using HARMS","authors":"Mauricio A. Gomez, E. Matson, Jihyun Song, SiYoung Baek, Junho Kim","doi":"10.1109/ICARA.2015.7081181","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081181","url":null,"abstract":"Recent trends are to build tall buildings in big cities as a way out of the current housing overpopulation problem. These new structures unveil problems that if not addressed in time could cause catastrophes of unimaginable impact. One of those problems is the incidence of a fire threat happening upstairs in one of those buildings. Research solutions include implementation of multi-agent fire safety systems for fire threats in high rise buildings. Humans, agents, robots, machines and sensors communication model is used for indistinguishability of actors. This work discusses the implementation of the unmanned ground vehicles to spot the real location of the fire.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128337620","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081135
Ludwig Nägele, M. Macho, A. Angerer, A. Hoffmann, M. Vistein, Manfred Schönheits, W. Reif
The automation of production processes with large process variability and a low batch size can be very difficult and non-economic. Using the example of manufacturing carbon-fibre-reinforced polymers (CFRP) which represents a complex, currently hardly automated process, we present a backward-oriented approach for offline programming of complex manufacturing tasks. We focus on an automatic process definition which is supported by expert knowledge where required. Due to domain specific software modules, user interaction is intuitive and tailored to CFRP experts. This leads to significant time-savings compared to currently used teach-in approaches. Moreover, we introduce an extensible offline programming platform which is able to meet the high requirements of CFRP manufacturing.
{"title":"A backward-oriented approach for offline programming of complex manufacturing tasks","authors":"Ludwig Nägele, M. Macho, A. Angerer, A. Hoffmann, M. Vistein, Manfred Schönheits, W. Reif","doi":"10.1109/ICARA.2015.7081135","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081135","url":null,"abstract":"The automation of production processes with large process variability and a low batch size can be very difficult and non-economic. Using the example of manufacturing carbon-fibre-reinforced polymers (CFRP) which represents a complex, currently hardly automated process, we present a backward-oriented approach for offline programming of complex manufacturing tasks. We focus on an automatic process definition which is supported by expert knowledge where required. Due to domain specific software modules, user interaction is intuitive and tailored to CFRP experts. This leads to significant time-savings compared to currently used teach-in approaches. Moreover, we introduce an extensible offline programming platform which is able to meet the high requirements of CFRP manufacturing.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124222970","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081166
Jonathan McColgan, E. McGookin, A. Mazlan
Biomimetic Autonomous Underwater Vehicles are Autonomous Underwater Vehicles (AUVs) that employ similar propulsion and steering mechanisms as real fish which result in improvements in propulsive efficiency at low speed. However, as with all AUVs the range and endurance of these biologically inspired vehicles are severally limited by the on board power supply. Nevertheless, large area scanning can still be achieved by the coordinated movement of multiple vehicles. To allow this to happen co-ordination algorithms would have to be utilised to ensure that a group of AUVs would be self-organising. The particular methodology presented in this paper again takes inspiration from nature and is based upon the behavioural mechanisms exhibited by schools of fish. Therefore, using a validated mathematical model of a robotic fish (called RoboSalmon), this paper outlines the implementation of this algorithm which similarly to the behavioural mechanisms use nearest neighbor principles to determine the movement of each member of the group. As this paper will use a mathematical model of a biomimetic AUV to implement biologically inspired coordination algorithms, the resulting group structure will be analysed with reference to the formation of a group structure and the number of AUVs within a group that are in a position to take advantage of the hydrodynamic benefits known to exist from fish swimming in close formation. The results demonstrate that the number of nearest neighbours taking into consideration greatly affects the formation of a stable school structure whereas the size of the school dictates the number of AUVs within the group benefitting hydrodynamically from the close proximity of neighbouring fish.
{"title":"Analysis of the group structure of a school of biomimetic AUVS coordinated using nearest neighbour principles","authors":"Jonathan McColgan, E. McGookin, A. Mazlan","doi":"10.1109/ICARA.2015.7081166","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081166","url":null,"abstract":"Biomimetic Autonomous Underwater Vehicles are Autonomous Underwater Vehicles (AUVs) that employ similar propulsion and steering mechanisms as real fish which result in improvements in propulsive efficiency at low speed. However, as with all AUVs the range and endurance of these biologically inspired vehicles are severally limited by the on board power supply. Nevertheless, large area scanning can still be achieved by the coordinated movement of multiple vehicles. To allow this to happen co-ordination algorithms would have to be utilised to ensure that a group of AUVs would be self-organising. The particular methodology presented in this paper again takes inspiration from nature and is based upon the behavioural mechanisms exhibited by schools of fish. Therefore, using a validated mathematical model of a robotic fish (called RoboSalmon), this paper outlines the implementation of this algorithm which similarly to the behavioural mechanisms use nearest neighbor principles to determine the movement of each member of the group. As this paper will use a mathematical model of a biomimetic AUV to implement biologically inspired coordination algorithms, the resulting group structure will be analysed with reference to the formation of a group structure and the number of AUVs within a group that are in a position to take advantage of the hydrodynamic benefits known to exist from fish swimming in close formation. The results demonstrate that the number of nearest neighbours taking into consideration greatly affects the formation of a stable school structure whereas the size of the school dictates the number of AUVs within the group benefitting hydrodynamically from the close proximity of neighbouring fish.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116903972","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081117
Alista Fow, M. Duke
The use of linear electromagnetic active damper units in the suspension system of a lightweight electric vehicle offers many advantages over conventional passive, semi-active and active hydraulic dampers. While full active hydraulic systems have been commercially available in automobiles for many years, the linear electromagnetic active damper offers a lower weight system with a much reduced power demand. However an active system requires the use of a controller to adjust the power output to the damper unit. This unit must process signal inputs and provide an output solution within a short time period, often 5 milliseconds or less. By using VISSIM REALTIME, a controller was built that controlled a scale linear electromagnetic damper using Karnopp's Skyhook algorithm. This had to deal with issues such as accelerometer drift and signal to noise ratio. These required simple but fast techniques to provide useful information to the damper in a useful timeframe. This controller-damper combination proved effective in reducing the vibration experienced by the sprung mass and was more effective than an ideal passive damper at all frequencies tested by at least a factor of three.
{"title":"The implementation in VISSIM REALTIME of an active electromagnetic damper controller for lightweight electric vehicles","authors":"Alista Fow, M. Duke","doi":"10.1109/ICARA.2015.7081117","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081117","url":null,"abstract":"The use of linear electromagnetic active damper units in the suspension system of a lightweight electric vehicle offers many advantages over conventional passive, semi-active and active hydraulic dampers. While full active hydraulic systems have been commercially available in automobiles for many years, the linear electromagnetic active damper offers a lower weight system with a much reduced power demand. However an active system requires the use of a controller to adjust the power output to the damper unit. This unit must process signal inputs and provide an output solution within a short time period, often 5 milliseconds or less. By using VISSIM REALTIME, a controller was built that controlled a scale linear electromagnetic damper using Karnopp's Skyhook algorithm. This had to deal with issues such as accelerometer drift and signal to noise ratio. These required simple but fast techniques to provide useful information to the damper in a useful timeframe. This controller-damper combination proved effective in reducing the vibration experienced by the sprung mass and was more effective than an ideal passive damper at all frequencies tested by at least a factor of three.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123372637","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081154
M. H. Farzaneh, A. Knoll, Jonas H. Pfeiffer
Developing real-time communication in various application fields such as robotics, factory automation, etc. is one the most important steps achieving a deterministic system. However, the development of this step is very complex and requires low level and advanced knowledge about the real-time communication systems. This complexity decelerates the developing process specially in cross-domain applications e.g. surgical control applications in Networked Medical Systems (NMS) requiring real-time communication and deterministic system behavior. General complexities developing real-time communication systems are classified. The architecture of an Open Platform for Abstraction of Real-Time Communication (OPART) is introduced for reducing these complexities. The architecture of OPART is based on the Ethernet-based real-time communication protocol openPOWERLINK. An experimental setup of OPART using a medical sensor and actuator is demonstrated.
{"title":"OPART: Towards an Open Platform for Abstraction of real-time communication in cross-domain applications","authors":"M. H. Farzaneh, A. Knoll, Jonas H. Pfeiffer","doi":"10.1109/ICARA.2015.7081154","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081154","url":null,"abstract":"Developing real-time communication in various application fields such as robotics, factory automation, etc. is one the most important steps achieving a deterministic system. However, the development of this step is very complex and requires low level and advanced knowledge about the real-time communication systems. This complexity decelerates the developing process specially in cross-domain applications e.g. surgical control applications in Networked Medical Systems (NMS) requiring real-time communication and deterministic system behavior. General complexities developing real-time communication systems are classified. The architecture of an Open Platform for Abstraction of Real-Time Communication (OPART) is introduced for reducing these complexities. The architecture of OPART is based on the Ethernet-based real-time communication protocol openPOWERLINK. An experimental setup of OPART using a medical sensor and actuator is demonstrated.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129926432","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 : 2015-04-09DOI: 10.1109/ICARA.2015.7081200
Mauricio A. Gomez, Yongho Kim, E. Matson
Soccer for humanoid robots has been a field of study for a long time, and the majority of the teams that compete in a tournament only focus until now in reaching the ball and drive it to score. That is the reason why we think that a more collaborative work would be a real improvement towards accomplishing the RoboCup 2050 ultimate goal of a fully autonomous humanoid team defeating the winning team of the FIFA World Cup Championship of the same year. In this paper, we propose a training system for humanoid-type soccer robot, that will learn to precisely intercept of a ball when is kicked by one robot of the same team. Vision system for ball detection is used as input to predict trajectory of the ball. A knowledge based learning algorithm enables the player to get higher chance to intercept the ball. We confirmed that the proposed approach can be a part of intelligent robot in the field of humanoid soccer.
{"title":"Iterative learning system to intercept a ball for humanoid soccer player","authors":"Mauricio A. Gomez, Yongho Kim, E. Matson","doi":"10.1109/ICARA.2015.7081200","DOIUrl":"https://doi.org/10.1109/ICARA.2015.7081200","url":null,"abstract":"Soccer for humanoid robots has been a field of study for a long time, and the majority of the teams that compete in a tournament only focus until now in reaching the ball and drive it to score. That is the reason why we think that a more collaborative work would be a real improvement towards accomplishing the RoboCup 2050 ultimate goal of a fully autonomous humanoid team defeating the winning team of the FIFA World Cup Championship of the same year. In this paper, we propose a training system for humanoid-type soccer robot, that will learn to precisely intercept of a ball when is kicked by one robot of the same team. Vision system for ball detection is used as input to predict trajectory of the ball. A knowledge based learning algorithm enables the player to get higher chance to intercept the ball. We confirmed that the proposed approach can be a part of intelligent robot in the field of humanoid soccer.","PeriodicalId":176657,"journal":{"name":"2015 6th International Conference on Automation, Robotics and Applications (ICARA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127659592","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：