Pub Date : 1997-10-22DOI: 10.1109/EURBOT.1997.633621
A. Carbonaro, P. Zingaretti
A system for landmark tracking by a template matching approach is described. Route following based on landmarks may require many models to cover all different situations, so a genetic algorithm learning technique is used to adapt modelling parameters to environmental conditions (lighting, shadows, reflexes, etc.) during the tracking. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence analysis in the 3D position estimation. The experimental results show that the tracking robustness is improved when the adaptive template matching is used for landmark tracking.
{"title":"Landmark matching in a varying environment","authors":"A. Carbonaro, P. Zingaretti","doi":"10.1109/EURBOT.1997.633621","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633621","url":null,"abstract":"A system for landmark tracking by a template matching approach is described. Route following based on landmarks may require many models to cover all different situations, so a genetic algorithm learning technique is used to adapt modelling parameters to environmental conditions (lighting, shadows, reflexes, etc.) during the tracking. In addition, the mobile robot self-localisation is obtained by a stereo approach that uses the centres of matching in the two images to solve in a simple way the correspondence analysis in the 3D position estimation. The experimental results show that the tracking robustness is improved when the adaptive template matching is used for landmark tracking.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115119329","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633551
M. Piaggio, R. Zaccaria
The roadmap approach to robot path planning is one of the earliest methods. Since then, many different algorithms for building roadmaps have been proposed and widely implemented in mobile robots but their use has always been limited to planning in static, totally known environments. In this paper we combine the use of dynamic analogical representations of the environment with an efficient roadmap extraction method, to guide the robot navigation and to classify and learn the different navigation situation it encounters. The paper presents the general reference architecture for the robotic system and then focuses on the algorithms for the construction of the roadmap, the classification of the regions of space and their use in robot navigation. Experimental results are also discussed.
{"title":"Learning navigation situations using roadmaps","authors":"M. Piaggio, R. Zaccaria","doi":"10.1109/EURBOT.1997.633551","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633551","url":null,"abstract":"The roadmap approach to robot path planning is one of the earliest methods. Since then, many different algorithms for building roadmaps have been proposed and widely implemented in mobile robots but their use has always been limited to planning in static, totally known environments. In this paper we combine the use of dynamic analogical representations of the environment with an efficient roadmap extraction method, to guide the robot navigation and to classify and learn the different navigation situation it encounters. The paper presents the general reference architecture for the robotic system and then focuses on the algorithms for the construction of the roadmap, the classification of the regions of space and their use in robot navigation. Experimental results are also discussed.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116206577","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633576
F. Voorbraak
We study the problem of making decisions under partial ignorance, or partially quantified uncertainty. This problem arises in many applications in robotics and AI, and it has not yet got the attention it deserves. The traditional decision rules of decision under risk and under strict uncertainty (or complete ignorance) can naturally be extended to the more general case of decision under partial ignorance. We propose partial probability theory (PPT) for representing partial ignorance, and we discuss the extension to PPT of expected utility maximization. We argue that decision analysis should not be exclusively focused on optimizing but pay more serious attention to finding satisfactory actions, and to reasoning with assumptions. The extended minimax regret decision rule appears to be an important rule for satisficing.
{"title":"Deciding under partial ignorance","authors":"F. Voorbraak","doi":"10.1109/EURBOT.1997.633576","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633576","url":null,"abstract":"We study the problem of making decisions under partial ignorance, or partially quantified uncertainty. This problem arises in many applications in robotics and AI, and it has not yet got the attention it deserves. The traditional decision rules of decision under risk and under strict uncertainty (or complete ignorance) can naturally be extended to the more general case of decision under partial ignorance. We propose partial probability theory (PPT) for representing partial ignorance, and we discuss the extension to PPT of expected utility maximization. We argue that decision analysis should not be exclusively focused on optimizing but pay more serious attention to finding satisfactory actions, and to reasoning with assumptions. The extended minimax regret decision rule appears to be an important rule for satisficing.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127619318","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633583
G. Borghi, E. Pagello, M. Vianello
We consider the problem of state recognizability in robotics environments modeled by partially observable Markov decision processes. To make the model of robot-environment interaction more reliable, in the usual state transition table, we add to the state transition probabilities an additional continuous metric via the mean and the variance of some significant sensor measurements suitable to be kept under a continuous form, such as odometric measurements. These information allow one to greatly enhance the state recognizability. Our approach is general, and can be applied to any robotics application that requires compensation of the uncertainties due to sensor errors and to the randomness of robot action effects on its environment. We have devised some possible applications to modeling the interaction between a manipulator and its world, but in this paper, only a specific application to the navigation problem for a mobile robot is illustrated to show the feasibility of our approach.
{"title":"Enhancing recognizability of robotics environments","authors":"G. Borghi, E. Pagello, M. Vianello","doi":"10.1109/EURBOT.1997.633583","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633583","url":null,"abstract":"We consider the problem of state recognizability in robotics environments modeled by partially observable Markov decision processes. To make the model of robot-environment interaction more reliable, in the usual state transition table, we add to the state transition probabilities an additional continuous metric via the mean and the variance of some significant sensor measurements suitable to be kept under a continuous form, such as odometric measurements. These information allow one to greatly enhance the state recognizability. Our approach is general, and can be applied to any robotics application that requires compensation of the uncertainties due to sensor errors and to the randomness of robot action effects on its environment. We have devised some possible applications to modeling the interaction between a manipulator and its world, but in this paper, only a specific application to the navigation problem for a mobile robot is illustrated to show the feasibility of our approach.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127711728","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633565
F. Kirchner
We present work on a six-legged walking machine that uses a hierarchical version of Q-learning (HQL) to learn both the elementary swing and stance movements of individual legs as well as the overall coordination scheme to perform forward movements. The architecture consists of a hierarchy of local controllers implemented in layers. The lowest layer consists of control modules performing elementary actions, like moving a leg up, down, left or right to achieve the elementary swing and stance motions for individual legs. The next level consists of controllers that learn to perform more complex tasks like forward movement by using the previously learned, lower level modules. On the third the highest layer in the architecture presented here the previously learned complex movements are themselves reused to achieve goals in the environment using external sensory input. The work is related to similar, although simulation-based, work by Lin (1993) on hierarchical reinforcement learning and Singh (1994) on compositional Q-learning. We report on the HQL architecture as well as on its implementation on the walking machine SIR ARTHUR. Results from experiments carried out on the real robot are reported to show the applicability of the HQL approach to real world robot problems.
{"title":"Q-learning of complex behaviours on a six-legged walking machine","authors":"F. Kirchner","doi":"10.1109/EURBOT.1997.633565","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633565","url":null,"abstract":"We present work on a six-legged walking machine that uses a hierarchical version of Q-learning (HQL) to learn both the elementary swing and stance movements of individual legs as well as the overall coordination scheme to perform forward movements. The architecture consists of a hierarchy of local controllers implemented in layers. The lowest layer consists of control modules performing elementary actions, like moving a leg up, down, left or right to achieve the elementary swing and stance motions for individual legs. The next level consists of controllers that learn to perform more complex tasks like forward movement by using the previously learned, lower level modules. On the third the highest layer in the architecture presented here the previously learned complex movements are themselves reused to achieve goals in the environment using external sensory input. The work is related to similar, although simulation-based, work by Lin (1993) on hierarchical reinforcement learning and Singh (1994) on compositional Q-learning. We report on the HQL architecture as well as on its implementation on the walking machine SIR ARTHUR. Results from experiments carried out on the real robot are reported to show the applicability of the HQL approach to real world robot problems.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120977203","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633560
R. Pfeifer, C. Scheier
The work is based on that of Brooks (1986), who argued that intelligence requires a body and therefore suggested that robots be used to study principles of intelligence. We show in more detail why some of the problems in intelligent behavior like category learning are simplified if the embodiment is exploited appropriately. We will also demonstrate that embodied systems can learn in an unstructured and "unlabelled" environment. Moreover, the seemingly intractable problems of behaving and learning in the real world become manageable. We will substantiate our argument with an information theoretic analysis. The work presented in this paper is theoretically motivated. It has been derived from a number of design principles of autonomous agents. They will be briefly outlined to provide the general context in which this research is situated.
{"title":"Implications of embodiment for robot learning","authors":"R. Pfeifer, C. Scheier","doi":"10.1109/EURBOT.1997.633560","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633560","url":null,"abstract":"The work is based on that of Brooks (1986), who argued that intelligence requires a body and therefore suggested that robots be used to study principles of intelligence. We show in more detail why some of the problems in intelligent behavior like category learning are simplified if the embodiment is exploited appropriately. We will also demonstrate that embodied systems can learn in an unstructured and \"unlabelled\" environment. Moreover, the seemingly intractable problems of behaving and learning in the real world become manageable. We will substantiate our argument with an information theoretic analysis. The work presented in this paper is theoretically motivated. It has been derived from a number of design principles of autonomous agents. They will be briefly outlined to provide the general context in which this research is situated.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"306 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115666636","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633579
P. Bison, G. Chemello, C. Sossai, G. Trainito
We present a formal method, based on the logic of possibility, to fuse uncertain sensory information and to produce an estimate of the position of a mobile robot. The robot navigates in an office environment, using a topological map, with the assistance of a "slave" robot acting as a portable local landmark. Each relevant place in the map is characterized by a set of logical formulae axiomatizing both "crisp" knowledge and uncertain information from the sensors. At each time instant during navigation, the necessity degree of each place is calculated using a purely syntactical method based on sequent calculus.
{"title":"A possibilistic approach to sensor fusion in mobile robotics","authors":"P. Bison, G. Chemello, C. Sossai, G. Trainito","doi":"10.1109/EURBOT.1997.633579","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633579","url":null,"abstract":"We present a formal method, based on the logic of possibility, to fuse uncertain sensory information and to produce an estimate of the position of a mobile robot. The robot navigates in an office environment, using a topological map, with the assistance of a \"slave\" robot acting as a portable local landmark. Each relevant place in the map is characterized by a set of logical formulae axiomatizing both \"crisp\" knowledge and uncertain information from the sensors. At each time instant during navigation, the necessity degree of each place is calculated using a purely syntactical method based on sequent calculus.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123443974","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633607
M. A. Martínez, J. González, J.L. Martinez
This paper deals with the design and development of a system for controlling a ring of sixteen sonar transducers working at two different frequencies, generated by a DSP, for the mobile robot RAM-2. Data gathering speed is increased by the simultaneous firing of all sensors since the ultrasonic sensors that work at the same frequency are separated by 45/spl deg/. The software and hardware implementation of the proposed perception system are presented. The results from the calibration process and the integration in the mobile robot RAM-2 are also studied.
{"title":"The DSP multi-frequency sonar configuration of the RAM-2 mobile robot","authors":"M. A. Martínez, J. González, J.L. Martinez","doi":"10.1109/EURBOT.1997.633607","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633607","url":null,"abstract":"This paper deals with the design and development of a system for controlling a ring of sixteen sonar transducers working at two different frequencies, generated by a DSP, for the mobile robot RAM-2. Data gathering speed is increased by the simultaneous firing of all sensors since the ultrasonic sensors that work at the same frequency are separated by 45/spl deg/. The software and hardware implementation of the proposed perception system are presented. The results from the calibration process and the integration in the mobile robot RAM-2 are also studied.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124362278","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633609
K.-W. Jorg, M. Berg, M. Muller
Conventional time-of-flight sonar sensing is widely used within the autonomous mobile robot research community. One of its most severe problems is known as crosstalk. This paper presents the experimental results of a new approach which allows the robot to operate a set of sonar sensors simultaneously with no frequent misreading caused by crosstalk or external ultrasound sources. This is achieved by carefully designing the emitted bursts, i.e. by using appropriate pseudo-random sequences together with the pulse compression technique well known from radar applications.
{"title":"Towards sophisticated mobile robot sonar sensing using pseudo-random sequences","authors":"K.-W. Jorg, M. Berg, M. Muller","doi":"10.1109/EURBOT.1997.633609","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633609","url":null,"abstract":"Conventional time-of-flight sonar sensing is widely used within the autonomous mobile robot research community. One of its most severe problems is known as crosstalk. This paper presents the experimental results of a new approach which allows the robot to operate a set of sonar sensors simultaneously with no frequent misreading caused by crosstalk or external ultrasound sources. This is achieved by carefully designing the emitted bursts, i.e. by using appropriate pseudo-random sequences together with the pulse compression technique well known from radar applications.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114302152","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 : 1997-10-22DOI: 10.1109/EURBOT.1997.633581
S. Baranov
To design a control unit for a mobile robot, the finite state machine (FSM) describing the behavior of such a robot should be constructed. As a rule, it is difficult to construct an optimal FSM to represent a complex behavior of the mobile robot containing several subbehaviors. We present the formal method for synthesis a control for mobile robots, including the following procedures: representation of each subbehavior as an algorithmic state machine (ASM), combining several private ASMs into one aggregated ASM, constructing a finite state machine, implementing aggregated ASM, and synthesis of FSM's logic circuit.
{"title":"Synthesis of control units for mobile robots","authors":"S. Baranov","doi":"10.1109/EURBOT.1997.633581","DOIUrl":"https://doi.org/10.1109/EURBOT.1997.633581","url":null,"abstract":"To design a control unit for a mobile robot, the finite state machine (FSM) describing the behavior of such a robot should be constructed. As a rule, it is difficult to construct an optimal FSM to represent a complex behavior of the mobile robot containing several subbehaviors. We present the formal method for synthesis a control for mobile robots, including the following procedures: representation of each subbehavior as an algorithmic state machine (ASM), combining several private ASMs into one aggregated ASM, constructing a finite state machine, implementing aggregated ASM, and synthesis of FSM's logic circuit.","PeriodicalId":129683,"journal":{"name":"Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133395140","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：