{"title":"Cooperative behavior acquisition in multi-mobile robots environment by reinforcement learning based on state vector estimation","authors":"E. Uchibe, M. Asada, K. Hosoda","doi":"10.1109/ROBOT.1998.677351","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.677351","url":null,"abstract":"This paper proposes a method that acquires robots' behaviors based on the estimation of the state vectors. In order to acquire the cooperative behaviors in multi-robot environments, each learning robot estimates the local predictive model between the learner and the other objects separately. Based on the local predictive models, the robots learn the desired behaviors using reinforcement learning. The proposed method is applied to a soccer playing situation, where a rolling ball and other moving robots are well modeled and the learner's behaviors are successfully acquired by the method. Computer simulations and real experiments are shown and a discussion is given.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"9 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121010946","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":"Toward 3D uncalibrated monocular visual servo","authors":"Bradley E. Bishop, M. Spong","doi":"10.1109/ROBOT.1998.680748","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.680748","url":null,"abstract":"This work is an initial step toward combining control theory with computer vision for the case of uncalibrated monocular (or single-camera) three-dimensional manipulation. We investigate an achievable control goal using a novel image measure and derive a sampled-data control system that results in quick convergence of the end-effector trajectory to a depth-invariant velocity subspace in the camera coordinate frame. We also discuss how this uncalibrated behavior can be used to perform online calibration.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121037535","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":"Gait controllability for legged robots","authors":"B. Goodwine, J. Burdick","doi":"10.1109/ROBOT.1998.677021","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.677021","url":null,"abstract":"We present a general method for determining controllability of a class of kinematic legged robots. The method is general in that it is independent of the robot's morphology; in particular, it does not depend upon the number of legs. Our method is based on an extension of a nonlinear controllability test for smooth systems to the legged case, where the relevant mechanics are not smooth. Our extension is based on the realization that legged robot configuration spaces are stratified. The result is illustrated with a simple example.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121201300","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":"Environmental complexity control for vision-based learning mobile robot","authors":"E. Uchibe, M. Asada, K. Hosoda","doi":"10.1109/ROBOT.1998.680514","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.680514","url":null,"abstract":"Discusses how a robot can develop its state vector according to the complexity of the interactions with its environment. A method for controlling the complexity is proposed for a vision-based mobile robot whose task is to shoot a ball into a goal avoiding collisions with a goalkeeper. First, we provide the most difficult situation (the maximum speed of the goalkeeper with chasing-a-ball behavior), and the robot estimates the full set of state vectors with the order of the major vector components by a method of system identification. The environmental complexity is defined in terms of the speed of the goalkeeper while the complexity of the state vector is the number of the dimensions of the state vector. According to the increase of the speed of the goalkeeper, the dimension of the state vector is increased by taking a trade-off between the size of the state space (the dimension) and the learning time. Simulations are shown, and other issues for the complexity control are discussed.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116641070","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":"A graphical method for evaluating static characteristics of the human finger by force manipulability","authors":"K. Hara, R. Yokogawa, A. Yokogawa","doi":"10.1109/ROBOT.1998.677383","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.677383","url":null,"abstract":"Static characteristics of the human finger are investigated using a mechanical planar model of the finger. They are represented by mapping a tendon force vector to a manipulating force vector of the fingertip. Force manipulability of the fingertip is defined as a force manipulability set obtained from the mapping under the condition that the norm of the tendon force vector is not more than a unit value. The shapes of the sets are geometrically obtained and graphically represented in the simulation results. The simulation visually demonstrates the static characteristics of the finger.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116573543","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":"Computing distances between NURBS-defined convex objects","authors":"Colin Turnbull, S. Cameron","doi":"10.1109/ROBOT.1998.681406","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.681406","url":null,"abstract":"Computing the distance between modelled objects is proving to be a fundamental operation for solving many problems in robotics and elsewhere. Most of the previous work in this area has focused on computing the distance between polyhedra, as the problem is easier to solve than the general case and the answer is sufficient for many problems. Here we focus on computing the distance between convex objects defined by NURBS curves or patches, for which the critical step is the evaluation of the support mapping. Experimental results are given for the two-dimensional case.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122493044","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":"Synthesis of impedance control laws at higher control levels: algorithms and experiments","authors":"D. Surdilovic","doi":"10.1109/ROBOT.1998.676375","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.676375","url":null,"abstract":"Describes the algorithms for the integration of a position based impedance control scheme in conventional industrial robot control systems. The new control functions which support programming, specification and monitoring compliance motion control are presented. These control functions constitute a powerful framework for executing most contact tasks with relatively low efforts. The experiments with SPARCO control systems and the CAT arm are included to demonstrate the performance of the control algorithms.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"311 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122702253","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":"High speed tracking control of Stewart platform manipulator via enhanced sliding mode control","authors":"Nag-in Kim, C. Lee","doi":"10.1109/ROBOT.1998.680756","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.680756","url":null,"abstract":"High speed tracking control of a 6-6 Stewart platform manipulator is performed by employing an enhanced sliding mode control with reduced manipulator dynamics when the manipulator is assumed to be operated on a low frequency planar motion unit. The high-performance tracking control strategy normally requires the complex full dynamics of 6-6 Stewart platform manipulator. The dynamics becomes even more complicated in the presence of the base motion of the manipulator, requiring additional sensors for measurement of the base motion. It is shown that enhanced sliding mode control implemented with perturbation compensation and reaching phase alleviation functions can effectively remove the use of the complex full dynamics and the additional sensors in the control system for high performance tracking control of the Stewart platform manipulator under the effects of virtual base motion.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131165101","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":"Stable inversion control for flexible link manipulators","authors":"Alessandro De Luca, S. Panzieri, G. Ulivi","doi":"10.1109/ROBOT.1998.677083","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.677083","url":null,"abstract":"We consider the inverse dynamics problem for robot arms with flexible links, i.e., the computation of the input torque that allows exact tracking of a trajectory defined for the manipulator end-effector. A stable inversion controller is derived numerically, based on the computation of bounded link deformations and, from these, of the required feedforward torque associated with the desired tip motion. For a general class of multi-link flexible manipulators, three alternative computational algorithms are presented, all defined on the second-order robot dynamic equations. Trajectory tracking is obtained by adding a (partial) state feedback, within a nonlinear regulation approach. Experimental results are reported for the FLEXARM robot.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131215196","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":"Dynamic model for high-speed pushing as a manipulator operation","authors":"S. Su, I. Uzmay","doi":"10.1109/ROBOT.1998.677091","DOIUrl":"https://doi.org/10.1109/ROBOT.1998.677091","url":null,"abstract":"In a planar pushing operation, particularly at higher pushing velocities, the object's inertia can not be ignored. This paper so determines dynamics aspect of the pushing mechanics for the case of four-points of support. If the object's inertia is neglected in the case of high-speed pushing, the object translates along the pushing line. However, when the object's inertia is considered, there is a tendency for the object to rotate.","PeriodicalId":272503,"journal":{"name":"Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126999817","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}