{"title":"Design of micro- and nano-robots","authors":"A. Codourey, R. Buechi, W. Zesch, R. Siegwart","doi":"10.1109/FPA.1994.636119","DOIUrl":"https://doi.org/10.1109/FPA.1994.636119","url":null,"abstract":"Nanotechnology is a key issue in today's and tomorrow's development of advanced products. Soon, new tools will be needed to automatically handle and assemble micro sized objects with nanometer resolution, or simply to give humans being the capability of operating in those tiny dimensions. The development of micro and nano robots appears in that sense as one of the most promising issues in the near future. The paper describes two new robot designs, where the focus has been put firstly in high accuracy and secondly to the reduction of the overall dimensions. The first robot uses piezo actuators to achieve very precise displacements and the second one is a fully autonomous miniature mobile robot based on watch type gears.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115112577","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":"Acting to sense: the lowest levels of a subsumption architecture","authors":"M. Pebody","doi":"10.1109/FPA.1994.636127","DOIUrl":"https://doi.org/10.1109/FPA.1994.636127","url":null,"abstract":"A truly distributed implementation of the subsumption architecture is presented that is used on a network of transputers to control an industrial laser scanning inspection system. The lowest levels of a bottom-up development are presented that deal with the control of sophisticated active sensory systems. Discussion continues dealing with aspects of learning control and subsystem interaction illustrated by reference to the active sensory subsystems of the inspection system.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"586 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116069179","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":"Insight: a virtual laboratory for looking into an autonomous agent","authors":"S. Strippgen, T. Christaller","doi":"10.1109/FPA.1994.636129","DOIUrl":"https://doi.org/10.1109/FPA.1994.636129","url":null,"abstract":"This paper introduces a simulation environment which is supposed to facilitate the study of behavior-based concepts by providing the user with a look at the dynamics inside the agent. Additionally we argue for more advanced environments in which agents may be able to show more interesting behavior.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130629047","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":"Advantage updating on a mobile robot","authors":"G. Bartha","doi":"10.1109/FPA.1994.636135","DOIUrl":"https://doi.org/10.1109/FPA.1994.636135","url":null,"abstract":"The paper describes the first experiments with advantage updating on a mobile robot. Advantage updating is an algorithm for reinforcement learning that has been recently developed and only simulation studies have been done previously. The task for the mobile robot was to move forward for a period of a few seconds if possible and to avoid obstacles otherwise using sonar, tactile, and motor position sensors. The performance of advantage updating was compared to the related Q-learning algorithm. While both algorithms were able to solve a one-dimensional form of the problem with only 2 states and 2 actions, advantage updating outperformed Q-learning for the two-dimensional problem with 4 actions. This was due to advantage updating's explicit account of time and the use of a variable time step for updating.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122241064","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":"RCS: a reference model architecture for intelligent control","authors":"J. Albus, W. Rippey","doi":"10.1109/FPA.1994.636106","DOIUrl":"https://doi.org/10.1109/FPA.1994.636106","url":null,"abstract":"The Real-time Control System (RCS) is a reference model architecture for intelligent real time control systems. It partitions the control problem into four basic elements: task decomposition, world modeling, sensory processing, and value judgment. It clusters these elements into computational nodes that have responsibility for specific subsystems and arranges these nodes in hierarchical layers such that each layer has characteristic functionality and timing. The RCS architecture has a systematic regularity, and recursive structure that suggests a canonical form. Systems based on the RCS architecture have been implemented more or less for a wide variety of applications that include loading and unloading of parts and tools in machine tools, controlling machining workstations, performing robotic deburring and chamfering, and controlling space station telerobots, multiple autonomous undersea vehicles, unmanned land vehicles, coal mining automation systems. postal service mail handling systems, and submarine operational automation systems. Software developers accustomed to using RCS for building control systems have found it provides a structured design approach that makes it possible to reuse a great deal of software.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132223351","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":"Control architectures for autonomous mobile robots","authors":"R. Chatila","doi":"10.1109/FPA.1994.636109","DOIUrl":"https://doi.org/10.1109/FPA.1994.636109","url":null,"abstract":"The paper discusses issues related to the design of the control architecture of an autonomous robot capable of performing tasks efficiently and intelligently, i.e., in a manner adapted to its environment, to its own state and to the execution status of its task. We examine and criticize some of the arguments of the proponents of the \"behavior based\" approach to the design of control architectures. Based on our own developments and experimentations on indoor and outdoor mobile robot navigation, we show hour it is necessary to produce representations at several levels of abstraction, that are manipulated by adequate processes. We also show that deliberation is also necessary for the robot to anticipate events, take efficient decisions, and react adequately to asynchronous events.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131328044","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}
H. Cruse, C. Bartling, G. Cymbalyuk, J. Dean, M. Dreifert
{"title":"A neural net controller for a six-legged walking system","authors":"H. Cruse, C. Bartling, G. Cymbalyuk, J. Dean, M. Dreifert","doi":"10.1109/FPA.1994.636082","DOIUrl":"https://doi.org/10.1109/FPA.1994.636082","url":null,"abstract":"A system that controls the leg movement of an animal or a robot walking over irregular ground has to react adaptively to unpredictable features of the environment. We present here a model for the control of the leg movement of a 6-legged walking system. The model is based on biological data obtained from the stick insect. The model extends a previous algorithmic model by substituting simple networks of artificial neurons for the algorithms previously used to control leg state and interleg coordination. Each system controlling an individual leg consists of three subnets. A hierarchically superior net rhythmically suppresses the output of one or the other of the two subordinal nets. These are responsible for controlling the return stroke (swing net) and the power stroke (stance net) movement, respectively. The swing module can produce appropriate return stroke movements for a broad range of initial and final positions, can cope with mechanical disturbances of the leg movement and is able to react to an obstacle which hinders the normal performance of the swing movement. The complete model is able to walk at different speeds over irregular surfaces. The control system rapidly reestablishes a stable gait when the movement of the legs is disturbed.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130704568","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":"Ants, buses and robots-self-organization of transportation systems","authors":"J. Deneubourg, P.-L. Clip, S.S. Camazine","doi":"10.1109/FPA.1994.636078","DOIUrl":"https://doi.org/10.1109/FPA.1994.636078","url":null,"abstract":"This article explores the potential for applying ideas in collective intelligence to transportation systems. A number of biological, human and robot models are discussed. First, we examine the ability of insect societies to form transportation networks by simple positive feedback. Second, we show how the undesirable aggregation tendencies in buses can be solved by self-organization. Finally, we consider a team of automated guided vehicles (AGVs) based on a decentralized supply and demand mechanism. These three examples offer some insights into what self-organization can offer transportation systems, in terms of task allocation, division of labour, etc.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126390979","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":"New fungus eater experiments [autonomous agents]","authors":"T. Wehrle","doi":"10.1109/FPA.1994.636132","DOIUrl":"https://doi.org/10.1109/FPA.1994.636132","url":null,"abstract":"Although there seems to be a high agreement among researchers that the concept of autonomous agents should also be applied in psychology, especially in emotion psychology, most work has not yet exceed the theoretical level. One reason is the lack of adequate tools for applying and exploring this concept. This paper describes, on the basis of an implemented software package, what such a tool could look like. This simulation package has already been used for several applications. As an example we discuss an application that implements the basic concepts of the emotional (or social) fungus eater of Masanao Toda (1962).","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132249513","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 perception and action when moving fast-egomotion perception for rapid robots","authors":"C. Haider","doi":"10.1109/FPA.1994.636124","DOIUrl":"https://doi.org/10.1109/FPA.1994.636124","url":null,"abstract":"Todays robots are slow. Being fast can be advantageous for animals and robots. In order to be fast it is necessary to perceive the distant environment. Distal senses must be spatial sensor fields. The new concept of shells is used to describe the projections of objects on the sensory field. The flow of shells contains information relevant to the orientation while moving.","PeriodicalId":338245,"journal":{"name":"Proceedings of PerAc '94. From Perception to Action","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134372637","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}