Pub Date : 1996-10-09DOI: 10.1109/EURBOT.1996.551891
C. Owen, U. Nehmzow
This paper describes route-learning experiments with an autonomous mobile robot in which map building is achieved through a process of unsupervised clustering of sensory data. The resulting topological mapping of the robot's perceptual space is used for subsequent navigation tasks such as route following. After the autonomous mapbuilding process is completed, the acquired generalised perceptions are associated with motor actions, enabling the robot to follow routes autonomously. The navigation system has been tested extensively on a Nomad 200 mobile robot, it is reliable and copes with noise and variation inherent in the environment. One important aspect of the map building and route following system described here is that relevance or irrelevance of perceptual features is determined autonomously by the robot, not through predefinition by the designer. Secondly, the presented route learning system enables the robot to use the map for association of perception with action, rather than localisation alone.
{"title":"Route learning in mobile robots through self-organisation","authors":"C. Owen, U. Nehmzow","doi":"10.1109/EURBOT.1996.551891","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551891","url":null,"abstract":"This paper describes route-learning experiments with an autonomous mobile robot in which map building is achieved through a process of unsupervised clustering of sensory data. The resulting topological mapping of the robot's perceptual space is used for subsequent navigation tasks such as route following. After the autonomous mapbuilding process is completed, the acquired generalised perceptions are associated with motor actions, enabling the robot to follow routes autonomously. The navigation system has been tested extensively on a Nomad 200 mobile robot, it is reliable and copes with noise and variation inherent in the environment. One important aspect of the map building and route following system described here is that relevance or irrelevance of perceptual features is determined autonomously by the robot, not through predefinition by the designer. Secondly, the presented route learning system enables the robot to use the map for association of perception with action, rather than localisation alone.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115320873","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551878
Jianwei Zhang, F. Wille, A. Knoll
We use fuzzy logic rules to directly map sensor data to robot control outputs by classifying a set of typical subtasks, such as "path tracking", "local collision avoidance", "contour tracking", "situation evaluation", etc. With the help of existing heuristics, the decision-making process for each subtask can be modelled and represented with "IF-THEN" rules. The underlying concepts of mapping with fuzzy logic rules are briefly explained by considering the proximity sensors, the control of speed and steering angle of a mobile robot. The development of these fuzzy rules is explained, typical rules for dealing with various motion situations are listed. The modularly developed fuzzy rule bases can be integrated to realise task-level programming and the exploration task. Experiments with the mobile robot validate this concept.
{"title":"Fuzzy logic rules for mapping sensor data to robot control","authors":"Jianwei Zhang, F. Wille, A. Knoll","doi":"10.1109/EURBOT.1996.551878","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551878","url":null,"abstract":"We use fuzzy logic rules to directly map sensor data to robot control outputs by classifying a set of typical subtasks, such as \"path tracking\", \"local collision avoidance\", \"contour tracking\", \"situation evaluation\", etc. With the help of existing heuristics, the decision-making process for each subtask can be modelled and represented with \"IF-THEN\" rules. The underlying concepts of mapping with fuzzy logic rules are briefly explained by considering the proximity sensors, the control of speed and steering angle of a mobile robot. The development of these fuzzy rules is explained, typical rules for dealing with various motion situations are listed. The modularly developed fuzzy rule bases can be integrated to realise task-level programming and the exploration task. Experiments with the mobile robot validate this concept.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130090108","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551883
Joachim Hertzberg, Frank Kirchner
We describe a method for an autonomous mobile robot to navigate through a system of sewerage pipes. Landmarks signalling positions in the pipe system have to be detected and classified, where classification is allowed do be unreliable. Self localization is interpreted as a partially observable Markov decision problem and solved accordingly. The method is implemented and used on a prototype robot platform operating in a dry sewage pipe test network.
{"title":"Landmark-based autonomous navigation in sewerage pipes","authors":"Joachim Hertzberg, Frank Kirchner","doi":"10.1109/EURBOT.1996.551883","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551883","url":null,"abstract":"We describe a method for an autonomous mobile robot to navigate through a system of sewerage pipes. Landmarks signalling positions in the pipe system have to be detected and classified, where classification is allowed do be unreliable. Self localization is interpreted as a partially observable Markov decision problem and solved accordingly. The method is implemented and used on a prototype robot platform operating in a dry sewage pipe test network.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125511022","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551881
A. Ramirez-Serrano, M. Boumédine
In this study a fuzzy logic navigation controller has been designed in order to deal with the uncertainty and ambiguity of the information the system (mobile robot) receives. The technique has been applied to MOBIRO, an experimental mobile robot using a set of seven ultrasonic sensors to perceive its surroundings. The fuzzy control designed maps the input space (information coming from ultrasonic sensors) to a safe collision avoidance trajectory (output Space). This is accomplished by an inference process based on rules (list of IF-THEN statements) taken from a common sense knowledge base. The technique generates satisfactory real time movements of the autonomous vehicle to reach its goal safely. Simulation and experimental results show that the method can be satisfactory used by mobile robots moving on unknown static terrains.
{"title":"Ultrasonic sensing and fuzzy logic control for navigation in unknown static environments","authors":"A. Ramirez-Serrano, M. Boumédine","doi":"10.1109/EURBOT.1996.551881","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551881","url":null,"abstract":"In this study a fuzzy logic navigation controller has been designed in order to deal with the uncertainty and ambiguity of the information the system (mobile robot) receives. The technique has been applied to MOBIRO, an experimental mobile robot using a set of seven ultrasonic sensors to perceive its surroundings. The fuzzy control designed maps the input space (information coming from ultrasonic sensors) to a safe collision avoidance trajectory (output Space). This is accomplished by an inference process based on rules (list of IF-THEN statements) taken from a common sense knowledge base. The technique generates satisfactory real time movements of the autonomous vehicle to reach its goal safely. Simulation and experimental results show that the method can be satisfactory used by mobile robots moving on unknown static terrains.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122002384","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551896
C. Balkenius, L. Kopp
This paper describes how tracking and target selection are used in two behavior systems of the XT-1 vision architecture for mobile robots. The first system is concerned with active tracking of moving targets and the second is used for visually controlled spatial navigation. We overview the XT-1 architecture and describe the role of expectation-based template matching for both target tracking and navigation. The subsystems for low-level processing, attentional processing, single feature processing, spatial relations, and place/object-recognition are described and we present a number of behaviors that can make use of the different visual processing stages. The architecture, which is inspired by biology, has been successfully implemented in a number of robots which are also briefly described.
{"title":"Visual tracking and target selection for mobile robots","authors":"C. Balkenius, L. Kopp","doi":"10.1109/EURBOT.1996.551896","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551896","url":null,"abstract":"This paper describes how tracking and target selection are used in two behavior systems of the XT-1 vision architecture for mobile robots. The first system is concerned with active tracking of moving targets and the second is used for visually controlled spatial navigation. We overview the XT-1 architecture and describe the role of expectation-based template matching for both target tracking and navigation. The subsystems for low-level processing, attentional processing, single feature processing, spatial relations, and place/object-recognition are described and we present a number of behaviors that can make use of the different visual processing stages. The architecture, which is inspired by biology, has been successfully implemented in a number of robots which are also briefly described.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129778430","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551895
G. Adorni, G. Destri, M. Mordonini, F. Zanichelli
We present an application of vision-based object recognition capabilities to the self-positioning-problem of an autonomous robot. Alphanumeric signs are placed in the robot environment as position markers and perceived through an on-board CCD camera on a pan-tilt head. Sign recognition is performed by a neural network based system, driven by some a-priori knowledge about the characteristics of the objects used as markers (signs). When given a map of the location of markers, the robot is able to estimate its position from the information extracted through perceived images. Marker distances and angular displacements allow the computation of a position uncertainty region for the mobile robot. Even using common, human readable markers, localization is performed with an average position accuracy within a few centimeters.
{"title":"Robot self-localization by means of vision","authors":"G. Adorni, G. Destri, M. Mordonini, F. Zanichelli","doi":"10.1109/EURBOT.1996.551895","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551895","url":null,"abstract":"We present an application of vision-based object recognition capabilities to the self-positioning-problem of an autonomous robot. Alphanumeric signs are placed in the robot environment as position markers and perceived through an on-board CCD camera on a pan-tilt head. Sign recognition is performed by a neural network based system, driven by some a-priori knowledge about the characteristics of the objects used as markers (signs). When given a map of the location of markers, the robot is able to estimate its position from the information extracted through perceived images. Marker distances and angular displacements allow the computation of a position uncertainty region for the mobile robot. Even using common, human readable markers, localization is performed with an average position accuracy within a few centimeters.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128868552","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551892
Schmucker U, Schneider A, Ihme T
New results on the development of an adaptive six-legged hexagonal walking robot and its control system are presented. The major part of the paper considers control of foot force distribution and control of body motion based on the information about force foot reactions and the information about the main force vector acting on the robot's body. Inserting and drilling operations based on the force control are considered.
{"title":"Six-legged robot for service operations","authors":"Schmucker U, Schneider A, Ihme T","doi":"10.1109/EURBOT.1996.551892","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551892","url":null,"abstract":"New results on the development of an adaptive six-legged hexagonal walking robot and its control system are presented. The major part of the paper considers control of foot force distribution and control of body motion based on the information about force foot reactions and the information about the main force vector acting on the robot's body. Inserting and drilling operations based on the force control are considered.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124468000","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551887
T. Ziemke
In this paper a higher-order recurrent connectionist architecture is used for learning adaptive behaviour in an autonomous robot. This architecture consists of two sub-networks in a master-slave relationship: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the sensory input weights in order to allow a flexible, context-dependent mapping from percepts to actions. The capabilities of this architecture are demonstrated in a number of action selection experiments with a simulated Khepera robot, and it is argued that the general approach of generically dividing the overall control task between sequentially cascaded context and function learning offers a powerful mechanism for autonomous long- and short-term adaptation of behaviour.
{"title":"Towards adaptive perception in autonomous robots using second-order recurrent networks","authors":"T. Ziemke","doi":"10.1109/EURBOT.1996.551887","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551887","url":null,"abstract":"In this paper a higher-order recurrent connectionist architecture is used for learning adaptive behaviour in an autonomous robot. This architecture consists of two sub-networks in a master-slave relationship: a function network for the coupling between sensory inputs and motor outputs, and a context network, which dynamically adapts the sensory input weights in order to allow a flexible, context-dependent mapping from percepts to actions. The capabilities of this architecture are demonstrated in a number of action selection experiments with a simulated Khepera robot, and it is argued that the general approach of generically dividing the overall control task between sequentially cascaded context and function learning offers a powerful mechanism for autonomous long- and short-term adaptation of behaviour.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124351058","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551879
K.-W. Jorg, M. Berg
Crosstalk is one of the most severe problems in conventional mobile robot sonar sensing. This paper addresses the crosstalk-problem and presents first and promising results of a new approach which enables a mobile robot to fire its sonar sensors simultaneously while totally eliminating any misreading caused by crosstalk or external ultrasound sources. This is achieved by carefully designing the emitted burst, i.e. by using appropriate pseudo-random sequences together with a matched filter technique. Experimental results are presented.
{"title":"First results in eliminating crosstalk and noise by applying pseudo-random sequences to mobile robot sonar sensing","authors":"K.-W. Jorg, M. Berg","doi":"10.1109/EURBOT.1996.551879","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551879","url":null,"abstract":"Crosstalk is one of the most severe problems in conventional mobile robot sonar sensing. This paper addresses the crosstalk-problem and presents first and promising results of a new approach which enables a mobile robot to fire its sonar sensors simultaneously while totally eliminating any misreading caused by crosstalk or external ultrasound sources. This is achieved by carefully designing the emitted burst, i.e. by using appropriate pseudo-random sequences together with a matched filter technique. Experimental results are presented.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128004606","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551876
P. Štěpán, L. Preucil
Making-use of multiple sensors is crucial for improvement of mobile robot navigation performance. The contribution introduces a problem of integrating noisy range-data by data fusion on signal/pixel level. This is performed for multiple sensors and different sensor positions into a common description of the environment. The paper deals with grid models, which are used as a low-level representations of sonar range measurements as well as for data fusion process. A short overview of used methods for the grid representation is shown and different fusion methods for various sonar models are discussed. Special attention is paid to the influence of sonar modeling on robustness of data integration process. The paper deals with methods for improvement of fusion robustness. Novelty of the presented approach stands in a sonar model which is designed as dependent on measured distance. The other improvement is an optimal feature selection for doorway recognition. The designed methods are illustrated by examples and test runs on experimental mobile platform with sonar sensory system.
{"title":"Statistical approach to range-data fusion and interpretation","authors":"P. Štěpán, L. Preucil","doi":"10.1109/EURBOT.1996.551876","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551876","url":null,"abstract":"Making-use of multiple sensors is crucial for improvement of mobile robot navigation performance. The contribution introduces a problem of integrating noisy range-data by data fusion on signal/pixel level. This is performed for multiple sensors and different sensor positions into a common description of the environment. The paper deals with grid models, which are used as a low-level representations of sonar range measurements as well as for data fusion process. A short overview of used methods for the grid representation is shown and different fusion methods for various sonar models are discussed. Special attention is paid to the influence of sonar modeling on robustness of data integration process. The paper deals with methods for improvement of fusion robustness. Novelty of the presented approach stands in a sonar model which is designed as dependent on measured distance. The other improvement is an optimal feature selection for doorway recognition. The designed methods are illustrated by examples and test runs on experimental mobile platform with sonar sensory system.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132802637","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：