Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications最新文献

{"title":"Computing 3d Road Shape From Images For A Challenge To An ill-posed Problem","authors":"K. Kanatani, Kazunari Watanabe","doi":"10.1109/IROS.1989.637933","DOIUrl":"https://doi.org/10.1109/IROS.1989.637933","url":null,"abstract":"A new algorithm is presented for reconstructing the 3D road shape from camera images for the purpose of navigating auto- nomous land vehicles (ALVs). The approximation that the road sur- face is locally flat enables us to determine a one-to-one correspon- dence between the two road boundaries, which in tum determines the 3D road shape. In order to cope with inaccuracy of image data, a least-square curve fitting technique is proposed with error behaviors taken into account. Examples based on real images are shown, and the role of heuristics is discussed. et al. (15) proposed a parametric fitting approach by preparing several prototypes of the 3D road shape. Kanatani, et al. 181 proposed a differential approach, describing the constraints that ideal roads should satisfy in terms of differential equations and reconstructing the 3D road shape by numerically integrating them. The solution is very robust to noise even in the distant part of the road. The discrete approach of DeMenthon (3) and the differential approach of Kanatani, et al. (8) both suffer the same problem: Computational error grows rapidly in the course of reconstruc- tion due to inaccuracy of the original image data and approxi- mations involved in the scheme. Recently, DeMenthon 141 pro- posed a new scheme based on the assumption that the road is locally Jrat and showed that the solution can be determined point-wise. As a result, one part of the solution is not affected by the error involved in other parts of the solution. At the same time, however, this local determination destroys the global consistency of the solution; locally constructed solutions can be inconsistent with each other. DeMenthon (6) proposed the use of dynamic programming to search for a globally consistent solution, but there is no guarantee that such a solution exists. In this paper, we incorporate the viewpoint of projective","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129591738","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":"Planning Movements for Several Coordinated Vehicles","authors":"Thierry Fraichard, C. Laugier","doi":"10.1109/IROS.1989.637945","DOIUrl":"https://doi.org/10.1109/IROS.1989.637945","url":null,"abstract":"This paper describes a two-level controlling system for a set of non-holonomic vehicles moving in a dynamic universei.e. among static and moving objects-. The higher level is concerned with planning a trajectory for each vehicle whereas the execution of the plan is distributed at the level of each vehicle. This paper focuses on the higher level i.e. the global planner. Our approach consists in first assigning priorities to the vehicles and then in planning motions one vehicle at a time. For that purpose, we make use of a path/velocity decomposition and of techniques to deal with the kinematic constraints of the vehicles. Planning the velocity parameters is then achieved by temporally allocatiiig “conflict regions” to the vehicles. In order to deal with the uncertainty introduced by the changes of the universe, tlic globill p1;iniicr operatos periodidly on a given interval of time.","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127546577","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":"Autonomous Mobile Robots Controlled by Navigation Functions","authors":"D. Koditschek","doi":"10.1109/IROS.1989.637971","DOIUrl":"https://doi.org/10.1109/IROS.1989.637971","url":null,"abstract":"This paper reviews the theory of navigation functions and the attendant use of natural control techniques with emphasis upon applications to mobile autonomous robots. Results to date will be discussrtl in tlir rontrxt of a 1;irgcr prograrn of rcscarrh that sccks cffcc.t,ivr para.inrtri~ations of rrncrrtainty in rolmt. navigaf.ioii prol)lrms. Constrnctivc solutions to particrilar caws of mobile robot navigation problems with complete certainty are provided as well.","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134378769","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":"On The Revised Theory Of Intelligent Machines","authors":"G. Saridis","doi":"10.1109/IROS.1989.637883","DOIUrl":"https://doi.org/10.1109/IROS.1989.637883","url":null,"abstract":"A summary of the work, aimed to reformulate analytically the theory of intelligent machines is presented. The functions of an Intelligent Machines are executed by Intelligent Controls. The Principle of Increasing Precision with Decreasing Intelligence is used to form a hierarchical structure of the control systems. Distributed Intelligence in compatible with such a structure when it is used for teams of intelligent machines or cooperating coordinators within the machine. The three levels of the Intelligent Control, e.g. the Organization, Coordination and Execution Levels are described as originally conceived. New designs as Neural-nets for the organization level and Petri- nets for the coordination level are proposed. Application to Intelligent Robots for space exploration are suggested.","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133233837","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":"Controllability Of Body Motion In Bipedal Locomotion","authors":"Y. Tagawa, T. Yamashita","doi":"10.1109/IROS.1989.637904","DOIUrl":"https://doi.org/10.1109/IROS.1989.637904","url":null,"abstract":"","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122228940","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":"Man-machine Interface Of A Telerobotic System","authors":"E. Kan","doi":"10.1109/IROS.1989.637959","DOIUrl":"https://doi.org/10.1109/IROS.1989.637959","url":null,"abstract":"","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122890640","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 New Anthropomorphic Telerobot Servicer","authors":"B. Jau","doi":"10.1109/IROS.1989.637961","DOIUrl":"https://doi.org/10.1109/IROS.1989.637961","url":null,"abstract":"","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131277696","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":"Trajectory Design and Control of a Wheel-type Mobile Robot Using B-spline Curve","authors":"K. Komoriya, K. Tanie","doi":"10.1109/IROS.1989.637937","DOIUrl":"https://doi.org/10.1109/IROS.1989.637937","url":null,"abstract":"In flexible trajectory control of a mobile robot it is preferable to design a smooth trajectory which passes specified points with specified tangents in a two dimensional plane. A trajectory design method which satisfies the above condition is presented using a Bspline curve. In order to use the designed B-spline curve for a two-wheel-driven-type mobile mechanism the possibility of using curvature data is examined. Possible speed patterns for the minimum travel time along a curve specified by curvature data is demonstrated given hardware constraints. Trajectory control of experimental hardware demonstrates the feasibility of using the the designed B-spline curve to control the trajectory of a wheel-type mobile robot.","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126993028","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 Modeling of Free-Space for a Mobile Robot","authors":"J. Crowley","doi":"10.1109/IROS.1989.637969","DOIUrl":"https://doi.org/10.1109/IROS.1989.637969","url":null,"abstract":"Unfortunately, the sensing devices which are available for mobile robots often fail in a variety of circumstances. This is especially true of the less expensive devices such as ultrasonic and infrared range sensors. Combining data from several sensors and from a pre-stored model of the domain provides a way to enhance the reliability of a perception system. Such combination may be accomplished by integrating range measurements into a geometric model of the local environment.","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774913","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":"Navigation By Learning","authors":"A. Zelinsky","doi":"10.1109/IROS.1989.637926","DOIUrl":"https://doi.org/10.1109/IROS.1989.637926","url":null,"abstract":"Research into mobile robot navigation has concentrated on the problem of finding optimal paths through known environments. For a mobile robot to operate in a partially known or a completely unknown environment the robot must be able to learn the cnvironmcnt. In this paper a mobile robot cnvironment learning algorithm is presented. The robot learns the environment by sensing, while it is executing paths produced by a path planner. A s obstacles are encountered en route to a goal, the model of the environment is updated and a new path to the goal is planned to avoid the obstacles. The paths generated by the algorithm will initially be locally optimal, but as the knowledge of the environment structure increases the optimality of the solution paths will improve. for the optimisation of distance to the goal combined will obstacle clearance information. The algorithm uses uses a quadtree representation to model environments. Initially the robot treats the unknown world as free space, until it learns information to the contrary. The path planner uses the distance transform methodology to generate all the solution paths from the goal back to the start location. This method not only yields a solution path to the goal, but it can also detect whether a goal is reachable. Once a path has been planned to the goal, the robot can execute it in a \"safe\" or \"optimal\" way. This paper will present the results of a computer simulation of the learning algorithm. Introduction The algorithm allows A great deal of the research concerning the problem of finding optimal paths for robot manipulators and autonomous mobile robots has concentrated on situations where the environment in which the robot operates in, is completely known and supplied -0 the path planner partially known or completely unknown environment, these path planning techniques are not directly applicable or extendable. Difficulties arise in deciding how to treat unexplored regions as obstacles, and only proceed into the unexplored regions if the goal lies there [ 41 [ 61 . 11 131 . For a robot navigating in a Research efforts into environment learning with mobile robots have followed a variety of approaches I41 111 . These can be broadly classified into two groupings; adaptive models and rigid models. Adaptive models use the nature and clutter of the environment to drive a representation of the environment. Typically adaptive modeis represent the environment as a network of free space regions [51 [ 7 ] 191 or as a graph of obstacle vertices [4]. environment learning methods require accurate sensor information. Rigid models impose a structure, such as a grid onto the environment without any regard to the nature and clutter of the environment [ 61 81 [ 111 [ 1 2 1 . Adaptive model environment learning methods offer elegant solutions, but in practise are difficult to implement on a real robot. The converse can be said of rigid model environment learning methods. Environment learning by a mobile robot csn be A","PeriodicalId":332317,"journal":{"name":"Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132985211","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}