Pub Date : 2006-04-01DOI: 10.2316/Journal.206.2006.2.206-2791
H. Ghenniwa, Joseph Eze, W. Shen
This paper reports on ongoing research to design coordination and cooperation ubiquitous to the control and tasking of multiple heterogeneous physical robot agents (PRAs) using a real-time agent architecture. The primary objective of the work presented here is to develop a real-time agent architecture and a distributed architectural framework that enables multiple PRAs to coordinate time-constrained high-level tasks in a collaborative manner. At the abstract level, we identify two layers, cognitive and action, based on the type of the PRA's responsibilities. At the cognitive layer we propose an extended version of the coordinated, intelligent rational agent (CIR-agent) model for complex real-time systems. The architecture facilitates integration between the cognitive layer and the action layer through the controller and functional modules. Our architecture also recognizes the coexistence of agent-oriented frameworks, such as JADE, and non-agent frameworks, like CORBA, to accommodate the cognitive and the action layers respectively.
{"title":"Physical robot Agents: Coordinated Intelligent and Rational Agents for Collaborative robots","authors":"H. Ghenniwa, Joseph Eze, W. Shen","doi":"10.2316/Journal.206.2006.2.206-2791","DOIUrl":"https://doi.org/10.2316/Journal.206.2006.2.206-2791","url":null,"abstract":"This paper reports on ongoing research to design coordination and cooperation ubiquitous to the control and tasking of multiple heterogeneous physical robot agents (PRAs) using a real-time agent architecture. The primary objective of the work presented here is to develop a real-time agent architecture and a distributed architectural framework that enables multiple PRAs to coordinate time-constrained high-level tasks in a collaborative manner. At the abstract level, we identify two layers, cognitive and action, based on the type of the PRA's responsibilities. At the cognitive layer we propose an extended version of the coordinated, intelligent rational agent (CIR-agent) model for complex real-time systems. The architecture facilitates integration between the cognitive layer and the action layer through the controller and functional modules. Our architecture also recognizes the coexistence of agent-oriented frameworks, such as JADE, and non-agent frameworks, like CORBA, to accommodate the cognitive and the action layers respectively.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121600385","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 : 2006-04-01DOI: 10.2316/Journal.206.2006.2.206-2795
A.M. Tehrani, M. Kamel, A. Khamis
The work presented in this paper aims at combining fuzzy function approximation and reinforcement learning in order to create robotic soccer agents that are able to coordinate their behaviours locally and socially while learning from experience. This simultaneous coordination and learning ability can play a crucial role in improving the behaviour usage of robotic soccer agents. To achieve this goal, a fuzzy reinforcement learning technique for a single agent is first examined and then this technique is applied to multiple agents. The conducted experiments through a soccer simulation system show that the performance of robot scoring speed is improved using the proposed approach.
{"title":"Fuzzy Reinforcement Learning for Embedded Soccer Agents in a Multi-Agent Context","authors":"A.M. Tehrani, M. Kamel, A. Khamis","doi":"10.2316/Journal.206.2006.2.206-2795","DOIUrl":"https://doi.org/10.2316/Journal.206.2006.2.206-2795","url":null,"abstract":"The work presented in this paper aims at combining fuzzy function approximation and reinforcement learning in order to create robotic soccer agents that are able to coordinate their behaviours locally and socially while learning from experience. This simultaneous coordination and learning ability can play a crucial role in improving the behaviour usage of robotic soccer agents. To achieve this goal, a fuzzy reinforcement learning technique for a single agent is first examined and then this technique is applied to multiple agents. The conducted experiments through a soccer simulation system show that the performance of robot scoring speed is improved using the proposed approach.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114680628","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 : 2006-04-01DOI: 10.2316/Journal.206.2006.2.206-2793
Anmin Zhu, Simon X. Yang
In this paper, a self-organizing map (SOM)-based multi-agent architecture is proposed for multirobot systems. It is capable of controlling a group of mobile robots to complete multiple tasks simultaneously. By cooperative and competitive behaviours, the group of mobile robots can automatically arrange the total task, and dynamically adjust their motion whenever the environment is changed. As an implementation, it can control a group of mobile robots to complete multiple tasks at different locations, such that the desired number of robots will arrive at every target location from arbitrary initial locations. The proposed approach integrates the task requirement of robots and the robot motion planning, such that the robots can start to move before their destinations are finalized. The robot navigation can be dynamically adjusted to guarantee that each target location has the desired number of robots, even under unexpected uncertainties, such as when some robots break down, some robots and/or some tasks are added, or some tasks are changed. Unlike most conventional models that are suitable to static environments only, the proposed approach is capable of dealing with changing environments. In addition, the proposed algorithm can be applied to the path planning of multirobot systems, where a group of robots is coordinated to visit a set of depots. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.
{"title":"A SOM-Based Multi-Agent Architecture for Multirobot Systems","authors":"Anmin Zhu, Simon X. Yang","doi":"10.2316/Journal.206.2006.2.206-2793","DOIUrl":"https://doi.org/10.2316/Journal.206.2006.2.206-2793","url":null,"abstract":"In this paper, a self-organizing map (SOM)-based multi-agent architecture is proposed for multirobot systems. It is capable of controlling a group of mobile robots to complete multiple tasks simultaneously. By cooperative and competitive behaviours, the group of mobile robots can automatically arrange the total task, and dynamically adjust their motion whenever the environment is changed. As an implementation, it can control a group of mobile robots to complete multiple tasks at different locations, such that the desired number of robots will arrive at every target location from arbitrary initial locations. The proposed approach integrates the task requirement of robots and the robot motion planning, such that the robots can start to move before their destinations are finalized. The robot navigation can be dynamically adjusted to guarantee that each target location has the desired number of robots, even under unexpected uncertainties, such as when some robots break down, some robots and/or some tasks are added, or some tasks are changed. Unlike most conventional models that are suitable to static environments only, the proposed approach is capable of dealing with changing environments. In addition, the proposed algorithm can be applied to the path planning of multirobot systems, where a group of robots is coordinated to visit a set of depots. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130808806","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 : 2006-04-01DOI: 10.2316/Journal.206.2006.2.206-2796
R. Wegner, J. Anderson
Today's artificial intelligence technology is insufficient to support autonomous task performance in complex domains such as urban search and rescue, forcing extensive reliance on human teleoperation of robots. This, however, also has problems: humans quickly suffer from cognitive overload and have difficulties in constructing a representation of the space around a remotely placed robot. In this paper we describe an approach to multirobot control for such environments that focuses on combining the limited abilities of modern autonomous control systems together with human control. At the centre of this approach is a pair of software agents running on each robot: one to recognize problems in the environment from the perspective of a robot, and another to mediate the interaction between a robot and a human controller. The intent of this approach is to allow a human to better control a team of robots, being interrupted only when the situation demands. We describe the implementation of this approach using simulated Pioneer robots, and evaluate the approach in comparison to autonomous and teleoperated mobile robots in a rescue domain.
{"title":"Agent-Based Support for Balancing teleoperation and Autonomy in Urban Search and Rescue","authors":"R. Wegner, J. Anderson","doi":"10.2316/Journal.206.2006.2.206-2796","DOIUrl":"https://doi.org/10.2316/Journal.206.2006.2.206-2796","url":null,"abstract":"Today's artificial intelligence technology is insufficient to support autonomous task performance in complex domains such as urban search and rescue, forcing extensive reliance on human teleoperation of robots. This, however, also has problems: humans quickly suffer from cognitive overload and have difficulties in constructing a representation of the space around a remotely placed robot. In this paper we describe an approach to multirobot control for such environments that focuses on combining the limited abilities of modern autonomous control systems together with human control. At the centre of this approach is a pair of software agents running on each robot: one to recognize problems in the environment from the perspective of a robot, and another to mediate the interaction between a robot and a human controller. The intent of this approach is to allow a human to better control a team of robots, being interrupted only when the situation demands. We describe the implementation of this approach using simulated Pioneer robots, and evaluate the approach in comparison to autonomous and teleoperated mobile robots in a rescue domain.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133109638","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 : 2005-09-14DOI: 10.2316/Journal.206.2006.4.206-2976
R. Gregorio
A wide family of parallel manipulators (PMs) is the one that groups all the PMs with three legs where the legs become kinematic chains constituted of a passive spherical pair (S) in series with either a passive prismatic pair (P) or a passive revolute pair (R) when the actuators are locked. The topologies of the structures generated by these manipulators, when the actuators are locked, are ten. One out of these topologies is the SP-PS-RS topology. This paper presents an algorithm that determines all the assembly modes of the structures with topology SP-PS-RS in analytical form. The presented algorithm can be applied without changes to solve, in analytical form, the forward position analysis of any parallel manipulator (SP-PS-RS architecture) which generates a SP-PS-RS structure when the actuators are locked. In particular, the closure equations of a generic SP-PS-RS structure are written. The eliminant of this system of equations is determined and the solution procedure is presented. Finally, the proposed procedure is applied to a real case. This work demonstrates that the solutions of the forward position analysis of any parallel manipulator which generates a SP-PS-RS structure when the actuators are locked are at most twelve. Index Terms — kinematics, position analysis, parallel mechanisms, parallel structure.
{"title":"Forward Position Analysis of the SP-PS-RS Architectures","authors":"R. Gregorio","doi":"10.2316/Journal.206.2006.4.206-2976","DOIUrl":"https://doi.org/10.2316/Journal.206.2006.4.206-2976","url":null,"abstract":"A wide family of parallel manipulators (PMs) is the one that groups all the PMs with three legs where the legs become kinematic chains constituted of a passive spherical pair (S) in series with either a passive prismatic pair (P) or a passive revolute pair (R) when the actuators are locked. The topologies of the structures generated by these manipulators, when the actuators are locked, are ten. One out of these topologies is the SP-PS-RS topology. This paper presents an algorithm that determines all the assembly modes of the structures with topology SP-PS-RS in analytical form. The presented algorithm can be applied without changes to solve, in analytical form, the forward position analysis of any parallel manipulator (SP-PS-RS architecture) which generates a SP-PS-RS structure when the actuators are locked. In particular, the closure equations of a generic SP-PS-RS structure are written. The eliminant of this system of equations is determined and the solution procedure is presented. Finally, the proposed procedure is applied to a real case. This work demonstrates that the solutions of the forward position analysis of any parallel manipulator which generates a SP-PS-RS structure when the actuators are locked are at most twelve. Index Terms — kinematics, position analysis, parallel mechanisms, parallel structure.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122778418","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 : 2005-08-29DOI: 10.2316/Journal.206.2005.3.206-2810
R. Garrido, A. Soria
A method is propcmed for estimating the gravity terms in robot manipulators. It is applied in closed loop and uses steady-state meesurernents of joint positions and input voltages, and does not need force or torque measurements. It is well suited for setting up controllers requiring gravity compensation. Experimental resulta are shown for a one-degree-of-freedom robot in closed loop with a proportional derivative controller and for a two-degree robot controlled in a visual sewoing framework.
{"title":"Estimating the Gravity Terms in Robot Manipulatiors for PD Control","authors":"R. Garrido, A. Soria","doi":"10.2316/Journal.206.2005.3.206-2810","DOIUrl":"https://doi.org/10.2316/Journal.206.2005.3.206-2810","url":null,"abstract":"A method is propcmed for estimating the gravity terms in robot manipulators. It is applied in closed loop and uses steady-state meesurernents of joint positions and input voltages, and does not need force or torque measurements. It is well suited for setting up controllers requiring gravity compensation. Experimental resulta are shown for a one-degree-of-freedom robot in closed loop with a proportional derivative controller and for a two-degree robot controlled in a visual sewoing framework.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122637569","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 : 2005-02-16DOI: 10.2316/Journal.206.2005.1.206-2772
T. Caelli, Li Cheng, Q. Fang
{"title":"Bayesian Image Understanding: From Images to Virtual Forests","authors":"T. Caelli, Li Cheng, Q. Fang","doi":"10.2316/Journal.206.2005.1.206-2772","DOIUrl":"https://doi.org/10.2316/Journal.206.2005.1.206-2772","url":null,"abstract":"","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115822930","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 : 2004-07-01DOI: 10.2316/Journal.206.2004.4.206-2802
A. Seth, J. McKinstry, G. Edelman, J. Krichmar
We describe the construction and performance of `brain-based devices? (BBDs), physical devices whose behaviour is controlled by simulated nervous systems modelled on vertebrate neuroanatomy and neurophysiology, that carry out perceptual categorization and selective conditioning to visual and textural stimuli. BBDs take input from the environment through on-board sensors including cameras, microphones and artificial whiskers, and take action based on experiential learning. BBDs have a large-scale neural simulation, a phenotype, a body plan, and the means to learn through autonomous exploration. Key neural mechanisms in the present BBDs include synaptic plasticity, reward or value systems, reentrant connectivity, the dynamic synchronization of neuronal activity, and neuronal units with spatiotemporal response properties. With our BBDs, as with animals, it is the interaction of these neural mechanisms with the sensorimotor correlations generated by active sensing and self motion that is responsible for adaptive behaviour. BBDs permit analysis of activity at all levels of the nervous system during behaviour, and as such they provide a rich source of heuristics for generating hypotheses regarding brain function. Moreover, by taking inspiration from systems neuroscience, BBDs provide a novel architecture for the design of neuromorphic systems.
{"title":"Active Sensing of Visual and Tactile Stimuli by Brain-based Devices","authors":"A. Seth, J. McKinstry, G. Edelman, J. Krichmar","doi":"10.2316/Journal.206.2004.4.206-2802","DOIUrl":"https://doi.org/10.2316/Journal.206.2004.4.206-2802","url":null,"abstract":"We describe the construction and performance of `brain-based devices? (BBDs), physical devices whose behaviour is controlled by simulated nervous systems modelled on vertebrate neuroanatomy and neurophysiology, that carry out perceptual categorization and selective conditioning to visual and textural stimuli. BBDs take input from the environment through on-board sensors including cameras, microphones and artificial whiskers, and take action based on experiential learning. BBDs have a large-scale neural simulation, a phenotype, a body plan, and the means to learn through autonomous exploration. Key neural mechanisms in the present BBDs include synaptic plasticity, reward or value systems, reentrant connectivity, the dynamic synchronization of neuronal activity, and neuronal units with spatiotemporal response properties. With our BBDs, as with animals, it is the interaction of these neural mechanisms with the sensorimotor correlations generated by active sensing and self motion that is responsible for adaptive behaviour. BBDs permit analysis of activity at all levels of the nervous system during behaviour, and as such they provide a rich source of heuristics for generating hypotheses regarding brain function. Moreover, by taking inspiration from systems neuroscience, BBDs provide a novel architecture for the design of neuromorphic systems.","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128122283","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 : 2004-05-10DOI: 10.2316/Journal.206.2004.2.206-2720
M. Tsai, J. Fang, Jau-Lung Chang
{"title":"Robotic Path Planning for an Automatic Mold Polishing System","authors":"M. Tsai, J. Fang, Jau-Lung Chang","doi":"10.2316/Journal.206.2004.2.206-2720","DOIUrl":"https://doi.org/10.2316/Journal.206.2004.2.206-2720","url":null,"abstract":"","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128472641","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":"Implementation of piecewise sine Functions on Limbless robot locomotion","authors":"P. Chattopadhyay, S. Ghoshal, A. Majumder","doi":"10.2316/j.2020.206-0159","DOIUrl":"https://doi.org/10.2316/j.2020.206-0159","url":null,"abstract":"","PeriodicalId":206015,"journal":{"name":"Int. J. Robotics Autom.","volume":"440 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":"115613727","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：