Pub Date : 1995-05-21DOI: 10.1109/ROBOT.1995.525581
K. Young, S. Shiah
In this paper, we propose a novel scheme for governing similar robot motions by using learning mechanisms. Most learning schemes need to repeat the learning process each time a new trajectory is encountered. The main reason for this deficiency is that the learning space for executing general motions of multi-joint robot manipulators is too large. To reduce the complexity in learning, we first classify robot motions according to their similarity. A new learning structure, which is motivated by the concept of a motor program, is then used to learn a class of motions. The proposed structure consists mainly of a fuzzy system and a CMAC-type neural network. The fuzzy system is used for learning of the samples in a class of motions. The CMAC-type neural network is used to generalize the parameters of the fuzzy system, which are appropriate for the control of the sampled motions, to deal with the whole class of motions. The learning process is performed only once and the learning effort is dramatically reduced for a wide range of robot motions.
{"title":"Learning control for similar robot motions","authors":"K. Young, S. Shiah","doi":"10.1109/ROBOT.1995.525581","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525581","url":null,"abstract":"In this paper, we propose a novel scheme for governing similar robot motions by using learning mechanisms. Most learning schemes need to repeat the learning process each time a new trajectory is encountered. The main reason for this deficiency is that the learning space for executing general motions of multi-joint robot manipulators is too large. To reduce the complexity in learning, we first classify robot motions according to their similarity. A new learning structure, which is motivated by the concept of a motor program, is then used to learn a class of motions. The proposed structure consists mainly of a fuzzy system and a CMAC-type neural network. The fuzzy system is used for learning of the samples in a class of motions. The CMAC-type neural network is used to generalize the parameters of the fuzzy system, which are appropriate for the control of the sampled motions, to deal with the whole class of motions. The learning process is performed only once and the learning effort is dramatically reduced for a wide range of robot motions.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127128663","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525572
M. Matsumura, S. Itou, H. Hibi, M. Hattori
A screw tightening robot with AC servomotors, without any torque sensor was developed for a variety of screws. In order to detect the accurate tightening torque, we developed a new torque estimation method by measuring the electrical current of the motor and calculating it in real time. The screw-driving process is controlled by the 4th joint's motion of the robot. Thus, this robot can tighten screws accurately and reliably without extra cost.
{"title":"Tightening torque estimation of a screw tightening robot","authors":"M. Matsumura, S. Itou, H. Hibi, M. Hattori","doi":"10.1109/ROBOT.1995.525572","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525572","url":null,"abstract":"A screw tightening robot with AC servomotors, without any torque sensor was developed for a variety of screws. In order to detect the accurate tightening torque, we developed a new torque estimation method by measuring the electrical current of the motor and calculating it in real time. The screw-driving process is controlled by the 4th joint's motion of the robot. Thus, this robot can tighten screws accurately and reliably without extra cost.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127238409","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525732
E. Paljug, T. Ohm, S. Hayati
The Serpentine Robot is a prototype hyper-redundant (snake-like) manipulator system developed at the Jet Propulsion Laboratory. It is designed to navigate and perform tasks in obstructed and constrained environments in which conventional 6-DOF manipulators cannot similarly function. This paper describes the Serpentine Robot mechanical design, a low level inverse kinematic algorithm for the joint assembly, a brief synopsis of control development to date, and the applications of this technology.
{"title":"The JPL Serpentine Robot: a 12-DOF system for inspection","authors":"E. Paljug, T. Ohm, S. Hayati","doi":"10.1109/ROBOT.1995.525732","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525732","url":null,"abstract":"The Serpentine Robot is a prototype hyper-redundant (snake-like) manipulator system developed at the Jet Propulsion Laboratory. It is designed to navigate and perform tasks in obstructed and constrained environments in which conventional 6-DOF manipulators cannot similarly function. This paper describes the Serpentine Robot mechanical design, a low level inverse kinematic algorithm for the joint assembly, a brief synopsis of control development to date, and the applications of this technology.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131025505","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525721
A. Mohri, Xiang D. Yang, Motoji Yamamoto
This paper proposes a method for planning the collision free trajectory of a manipulator. In this method, geometrical constraints to avoid obstacles are represented by restrictive potential functions. The dynamic equation of the manipulator is expressed by a path parameter 's' which is the generalized length along the path. The driving torque/force is improved by taking shorter travelling time and collision avoidance into considerations. Finally, the proposed method is applied to a manipulator with three links and is shown to be effective.
{"title":"Collision free trajectory planning for manipulator using potential function","authors":"A. Mohri, Xiang D. Yang, Motoji Yamamoto","doi":"10.1109/ROBOT.1995.525721","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525721","url":null,"abstract":"This paper proposes a method for planning the collision free trajectory of a manipulator. In this method, geometrical constraints to avoid obstacles are represented by restrictive potential functions. The dynamic equation of the manipulator is expressed by a path parameter 's' which is the generalized length along the path. The driving torque/force is improved by taking shorter travelling time and collision avoidance into considerations. Finally, the proposed method is applied to a manipulator with three links and is shown to be effective.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123697859","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525332
Haoxun Chen, C. Chu, J. Proth
Lagrangian relaxation consists of relaxing capacity constraints using Lagrangian multipliers and of decomposing the problem into job level subproblems. In the literature, when job shop scheduling problems are considered, these subproblems are further decomposed into operation level subproblems by relaxing precedence constraints. Unfortunately, this results in solution oscillation and often prevents convergence of the algorithm. Although several methods have been proposed to avoid solution oscillation, none of them is really satisfactory. In this paper, we propose an efficient pseudopolynomial time dynamic programming algorithm to solve relaxed job level subproblems. This makes the relaxation of precedence constraints unnecessary. The solution oscillation can then be avoided. This algorithm also results in a much more efficient Lagrangian relaxation approach to job-shop scheduling problems. Computational results on randomly generated problems are given to demonstrate the efficiency of the algorithm.
{"title":"A more efficient Lagrangian relaxation approach to job-shop scheduling problems","authors":"Haoxun Chen, C. Chu, J. Proth","doi":"10.1109/ROBOT.1995.525332","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525332","url":null,"abstract":"Lagrangian relaxation consists of relaxing capacity constraints using Lagrangian multipliers and of decomposing the problem into job level subproblems. In the literature, when job shop scheduling problems are considered, these subproblems are further decomposed into operation level subproblems by relaxing precedence constraints. Unfortunately, this results in solution oscillation and often prevents convergence of the algorithm. Although several methods have been proposed to avoid solution oscillation, none of them is really satisfactory. In this paper, we propose an efficient pseudopolynomial time dynamic programming algorithm to solve relaxed job level subproblems. This makes the relaxation of precedence constraints unnecessary. The solution oscillation can then be avoided. This algorithm also results in a much more efficient Lagrangian relaxation approach to job-shop scheduling problems. Computational results on randomly generated problems are given to demonstrate the efficiency of the algorithm.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130566495","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.526028
W. S. Howard, Vijay Kumar
We address the stability and performance of enveloping grasps. An enveloping grasp is defined in which robot fingers or arms grasp an object by making contact at points other than just the fingertips or end-effectors. Previous work has demonstrated that enveloping grasps are more robust. However their analysis is difficult because they are usually statically indeterminate and overconstrained. In this paper we develop a method for modeling the stiffness of a grasp. It is based on a model of compliance at each contact and a model of the joint compliance at each joint. It incorporates the kinematics of three-dimensional contact in addition to the kinematics of the robot arm/finger. In particular the methodology is used to show that force closure does not necessarily imply stability.
{"title":"Modeling and analysis of the compliance and stability of enveloping grasps","authors":"W. S. Howard, Vijay Kumar","doi":"10.1109/ROBOT.1995.526028","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.526028","url":null,"abstract":"We address the stability and performance of enveloping grasps. An enveloping grasp is defined in which robot fingers or arms grasp an object by making contact at points other than just the fingertips or end-effectors. Previous work has demonstrated that enveloping grasps are more robust. However their analysis is difficult because they are usually statically indeterminate and overconstrained. In this paper we develop a method for modeling the stiffness of a grasp. It is based on a model of compliance at each contact and a model of the joint compliance at each joint. It incorporates the kinematics of three-dimensional contact in addition to the kinematics of the robot arm/finger. In particular the methodology is used to show that force closure does not necessarily imply stability.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132430090","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525534
He-Kyung Cho, B. Lee, M. Ko
This paper deals with a systematic analysis of the time-optimal motion of a multiple robot system carrying an object along a prescribed path. In our approach, the time-optimal motion planning problem is formulated in a concise form by employing a parameter describing the movement along the path and a vector representing the internal force. Various constraints governing the motion yield the so-called admissible region in the phase plane of the parameter. The orthogonal projection technique and the theory of multiple objective optimization make it possible to construct the admissible region, while taking into account the load distribution problem that is coupled with the motion. Furthermore, our approach provides a way of detailed investigation for the admissible region that is not simply connected. The resulting velocity profile of the path parameter and the internal force at every instant determine the optimal actuator torques for each robot.
{"title":"Path constrained time-optimal motion of multiple robots holding a common object","authors":"He-Kyung Cho, B. Lee, M. Ko","doi":"10.1109/ROBOT.1995.525534","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525534","url":null,"abstract":"This paper deals with a systematic analysis of the time-optimal motion of a multiple robot system carrying an object along a prescribed path. In our approach, the time-optimal motion planning problem is formulated in a concise form by employing a parameter describing the movement along the path and a vector representing the internal force. Various constraints governing the motion yield the so-called admissible region in the phase plane of the parameter. The orthogonal projection technique and the theory of multiple objective optimization make it possible to construct the admissible region, while taking into account the load distribution problem that is coupled with the motion. Furthermore, our approach provides a way of detailed investigation for the admissible region that is not simply connected. The resulting velocity profile of the path parameter and the internal force at every instant determine the optimal actuator torques for each robot.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132052884","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525649
Y. Ando, S. Yuta
Presents a robust method for an autonomous mobile robot with a sonar-ring to follow walls. The sonar-ring consists of multiple ultrasonic range sensors. The proposed wall-following algorithm makes a robot able to follow a wall in various shapes such as a square wall, a circular wall etc. The autonomous mobile robot "Yamabico" is used for experiments after being equipped with a 12 directional sonar-ring. The on-board controller of the robot decides its motion based on sonar-ring range data every 3 centimeters going forward. The authors carried out many experiments with this autonomous mobile robot, and investigated the validity and the limits of this method.
{"title":"Following a wall by an autonomous mobile robot with a sonar-ring","authors":"Y. Ando, S. Yuta","doi":"10.1109/ROBOT.1995.525649","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525649","url":null,"abstract":"Presents a robust method for an autonomous mobile robot with a sonar-ring to follow walls. The sonar-ring consists of multiple ultrasonic range sensors. The proposed wall-following algorithm makes a robot able to follow a wall in various shapes such as a square wall, a circular wall etc. The autonomous mobile robot \"Yamabico\" is used for experiments after being equipped with a 12 directional sonar-ring. The on-board controller of the robot decides its motion based on sonar-ring range data every 3 centimeters going forward. The authors carried out many experiments with this autonomous mobile robot, and investigated the validity and the limits of this method.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132327638","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525486
G. Burel, F. Bernard, W. J. Venema
The paper describes an approach to include vision control and neural networks in the assembly process of surface mounted devices (SMD). The need of vision feedback is due to the decreasing size of SMD. The proposed approach includes image processing, estimation of positioning error by a neural network, and geometrical computations. The hardware implementation to achieve real time constraints is also described.
{"title":"Vision feedback for SMD placement using neural networks","authors":"G. Burel, F. Bernard, W. J. Venema","doi":"10.1109/ROBOT.1995.525486","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525486","url":null,"abstract":"The paper describes an approach to include vision control and neural networks in the assembly process of surface mounted devices (SMD). The need of vision feedback is due to the decreasing size of SMD. The proposed approach includes image processing, estimation of positioning error by a neural network, and geometrical computations. The hardware implementation to achieve real time constraints is also described.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130873396","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 : 1995-05-21DOI: 10.1109/ROBOT.1995.525698
S. Betgé-Brezetz, R. Chatila, M. Devy
Mobile robot navigation in natural environments requires incremental scene modelling and robot self-localization. These two capacities are discussed in this paper. A scene model is built with heterogeneous representations to match the diversity of the environment. We focus on object-based representations, using coarse models (ellipsoids) or volumic primitives (superquadrics), and their topological relations. The method for extracting the models from a range image to provide geometrical and topological representations, and the matching of successive views during the robot's movement are presented. For robot localization, two procedures are proposed based on the coarse or fine models. Experimental results are given.
{"title":"Object-based modelling and localization in natural environments","authors":"S. Betgé-Brezetz, R. Chatila, M. Devy","doi":"10.1109/ROBOT.1995.525698","DOIUrl":"https://doi.org/10.1109/ROBOT.1995.525698","url":null,"abstract":"Mobile robot navigation in natural environments requires incremental scene modelling and robot self-localization. These two capacities are discussed in this paper. A scene model is built with heterogeneous representations to match the diversity of the environment. We focus on object-based representations, using coarse models (ellipsoids) or volumic primitives (superquadrics), and their topological relations. The method for extracting the models from a range image to provide geometrical and topological representations, and the matching of successive views during the robot's movement are presented. For robot localization, two procedures are proposed based on the coarse or fine models. Experimental results are given.","PeriodicalId":432931,"journal":{"name":"Proceedings of 1995 IEEE International Conference on Robotics and Automation","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130486049","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：