Pub Date : 1992-07-08DOI: 10.1109/AIHAS.1992.636879
S. Venkatesh, D. Kieronska
The problem of deriving spatial relationships between objects in general requires high lever' abstract representation, and it would pose diflculties evenjb human observer. Based on a formalism for spatial layouts proposed earlier, we present methods for deducing spatial relations between objects by an active, sighted agent in a krrge-scale environment. The deduction of spatial relations ir: based on simple visual clues, and thus this technique is more feasible than schemes that rely on complex object recognition.
{"title":"Spatial Reasoning by Active Observation","authors":"S. Venkatesh, D. Kieronska","doi":"10.1109/AIHAS.1992.636879","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636879","url":null,"abstract":"The problem of deriving spatial relationships between objects in general requires high lever' abstract representation, and it would pose diflculties evenjb human observer. Based on a formalism for spatial layouts proposed earlier, we present methods for deducing spatial relations between objects by an active, sighted agent in a krrge-scale environment. The deduction of spatial relations ir: based on simple visual clues, and thus this technique is more feasible than schemes that rely on complex object recognition.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123319615","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636898
R. Girle
The original ELIZA was a puzzling success. There is a case for seeing EUZA in a new light, CIS the first, and highly successful, move towards treating certain kinds of activity as automatic and reactive. There is a strong analogy between the way in which ELI24 reacts and the way in which robotic automata react. The major thesis of this paper is that there is at least one important and systematic direction in which this way of seeing EDZA can be developed. The development concerns precisely the area in which ELIZA was most successful, dialogue. A multi-automata approach to dialogue is explored in terms of the most recent work in dialogue logic and dialogue game theory. The paper contrasts the work of the linguistic discourse analysts and the dialogicians. A typical dialogue logic is presented with extensions for task oriented dialogue with emphasis on joint activity.
{"title":"Eliza and the Automata","authors":"R. Girle","doi":"10.1109/AIHAS.1992.636898","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636898","url":null,"abstract":"The original ELIZA was a puzzling success. There is a case for seeing EUZA in a new light, CIS the first, and highly successful, move towards treating certain kinds of activity as automatic and reactive. There is a strong analogy between the way in which ELI24 reacts and the way in which robotic automata react. The major thesis of this paper is that there is at least one important and systematic direction in which this way of seeing EDZA can be developed. The development concerns precisely the area in which ELIZA was most successful, dialogue. A multi-automata approach to dialogue is explored in terms of the most recent work in dialogue logic and dialogue game theory. The paper contrasts the work of the linguistic discourse analysts and the dialogicians. A typical dialogue logic is presented with extensions for task oriented dialogue with emphasis on joint activity.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133255151","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636878
P. Husbands, I. Harvey
This paper sets out and justifies a methodology for the development of the control systems, or ‘cognitive architectures)) of autonomous mobile robots. It will be argued that the design b y hand of such control systems becomes prohibitively dificult as complexity increases. The alternative approach of artificial evolution is presented. It is argued that the most useful basic building blocks for an evolved cognitive archite(*t ? ure are adaptive noise tolerant neural networks raiher than programs. These networks may be recurrent, and should operate in real time. Evolution should be incremental, using an extended and modified version of genetic algorithms. Time constraints mean that architecture evaluations must be largely done an simulation. Results from a simulation are presented. The pitfalls of simulations compared with reality is discussed, together with the importance of incorporating noise.
{"title":"Evolution Versus Design: Controlling Autonomous Robots","authors":"P. Husbands, I. Harvey","doi":"10.1109/AIHAS.1992.636878","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636878","url":null,"abstract":"This paper sets out and justifies a methodology for the development of the control systems, or ‘cognitive architectures)) of autonomous mobile robots. It will be argued that the design b y hand of such control systems becomes prohibitively dificult as complexity increases. The alternative approach of artificial evolution is presented. It is argued that the most useful basic building blocks for an evolved cognitive archite(*t ? ure are adaptive noise tolerant neural networks raiher than programs. These networks may be recurrent, and should operate in real time. Evolution should be incremental, using an extended and modified version of genetic algorithms. Time constraints mean that architecture evaluations must be largely done an simulation. Results from a simulation are presented. The pitfalls of simulations compared with reality is discussed, together with the importance of incorporating noise.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"26 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126050654","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636865
J. Rozenblit
ing blocks that are eventually evolving into a comprehensive methodology for autonomous systems design [lo]. In this article, we briefly summarize the definition of an intelligent autonomous system and requirements for achieving high autonomy. Then, model-based techniques which unify autonomous system design are preThis article discusses a high level design methodology and its support of high autonomy systems synthesis. Requirements for high autonomy as well as the design framework are briefly summarized. Then, model-based techniques which unify autonomous system design are presented. sented.
{"title":"Achieving Autonomy through Design","authors":"J. Rozenblit","doi":"10.1109/AIHAS.1992.636865","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636865","url":null,"abstract":"ing blocks that are eventually evolving into a comprehensive methodology for autonomous systems design [lo]. In this article, we briefly summarize the definition of an intelligent autonomous system and requirements for achieving high autonomy. Then, model-based techniques which unify autonomous system design are preThis article discusses a high level design methodology and its support of high autonomy systems synthesis. Requirements for high autonomy as well as the design framework are briefly summarized. Then, model-based techniques which unify autonomous system design are presented. sented.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122953552","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636867
K. Yum, T. Richards
{"title":"Simulating Teaching by Reasoning About Instructional Objectives","authors":"K. Yum, T. Richards","doi":"10.1109/AIHAS.1992.636867","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636867","url":null,"abstract":"","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117297939","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636894
M. Nelson
This paper describes a new type of control architecture that adaptively navigates a simulated mobile robot. A robust control system requires multiple strategies for formulating actions so that if one fails then another can be used. A consequence of the design of this architecture is a redundancy of c40ntrol strategies. It is this redundancy that facilitates a unique mechanism for achieving robust control through the adaptive utilisation of the various strategies in response to the environment. The mechanisms for adapting behaviour are described and their effects illustrated by robot simulations.
{"title":"An Architecture for Adaptive Navigational Control","authors":"M. Nelson","doi":"10.1109/AIHAS.1992.636894","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636894","url":null,"abstract":"This paper describes a new type of control architecture that adaptively navigates a simulated mobile robot. A robust control system requires multiple strategies for formulating actions so that if one fails then another can be used. A consequence of the design of this architecture is a redundancy of c40ntrol strategies. It is this redundancy that facilitates a unique mechanism for achieving robust control through the adaptive utilisation of the various strategies in response to the environment. The mechanisms for adapting behaviour are described and their effects illustrated by robot simulations.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132637548","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636857
W. Sverdlik, R. Reynolds, E. Zannoni
In the paper, a hybrid learning algorithm for discovering concepts with multiple disjuncts in an exponentially growing hypothesis space is presented. The approach, HYBAL, extends the work of Hirsh 141 and Reynolds [9] to produce an autonomous system that learns to partition a large search space incrementally into successively smaller search spaces using a divide and conquer strategy. This approach is used to solve the Boolean problem for a F20 multiplexor. The system needed to examine less than 0.5% of the entire search space, in order to achieve a solution.
{"title":"Hybal: A Self Tutoring Algorithm for Concept Learning in Highly Autonomous Systems","authors":"W. Sverdlik, R. Reynolds, E. Zannoni","doi":"10.1109/AIHAS.1992.636857","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636857","url":null,"abstract":"In the paper, a hybrid learning algorithm for discovering concepts with multiple disjuncts in an exponentially growing hypothesis space is presented. The approach, HYBAL, extends the work of Hirsh 141 and Reynolds [9] to produce an autonomous system that learns to partition a large search space incrementally into successively smaller search spaces using a divide and conquer strategy. This approach is used to solve the Boolean problem for a F20 multiplexor. The system needed to examine less than 0.5% of the entire search space, in order to achieve a solution.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"210 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132075840","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636896
M. Rillo
This paper is a preliminary report on EXTEPS, a domain independent temporal projection system. The main goal of EXTEPS is anticipating a future action set which is supposed to be the behavior that best f i ts the agentS intentions. This set of future actions and the intentions of the agents are both described by means of the same language used in the PETRUS control system. PETRUS is a procedural control system based on Petri nets and production rules. The central idea in EXTEPS is to focus the attention on the set of internal and external events which can change the state of the world. These relevant events could affect the antecedent parts of rules and the predicate associated to the transition of the nets.
{"title":"Expectation-Based Temporal Projection System","authors":"M. Rillo","doi":"10.1109/AIHAS.1992.636896","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636896","url":null,"abstract":"This paper is a preliminary report on EXTEPS, a domain independent temporal projection system. The main goal of EXTEPS is anticipating a future action set which is supposed to be the behavior that best f i ts the agentS intentions. This set of future actions and the intentions of the agents are both described by means of the same language used in the PETRUS control system. PETRUS is a procedural control system based on Petri nets and production rules. The central idea in EXTEPS is to focus the attention on the set of internal and external events which can change the state of the world. These relevant events could affect the antecedent parts of rules and the predicate associated to the transition of the nets.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121453056","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636895
S. Nadjm-Tehrani, P. Osterling
The reactive paradigm of planning addresses the problem of determining actions by agents in changing environments. A common property of all such works is that decision making as highly dependent on results from a perception unit, and the reacting agent is intended to behave in real time. In this paper we present a formalism to support recognition of significant situations in a dynamic environment based on sequences of observations, whale meeting well-defined temporal constraints. We propose a logic which allows formal specifications of quantitative temporal constraints and explicit representation of deictic references. We have used the logic for specifications where values of parameters vary over continuous time. The specifications refer -to distances within different time scales including continuous ones.
{"title":"Characterization of Environment Conditions with Metric Temporal Feature Logic","authors":"S. Nadjm-Tehrani, P. Osterling","doi":"10.1109/AIHAS.1992.636895","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636895","url":null,"abstract":"The reactive paradigm of planning addresses the problem of determining actions by agents in changing environments. A common property of all such works is that decision making as highly dependent on results from a perception unit, and the reacting agent is intended to behave in real time. In this paper we present a formalism to support recognition of significant situations in a dynamic environment based on sequences of observations, whale meeting well-defined temporal constraints. We propose a logic which allows formal specifications of quantitative temporal constraints and explicit representation of deictic references. We have used the logic for specifications where values of parameters vary over continuous time. The specifications refer -to distances within different time scales including continuous ones.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116798521","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 : 1992-07-08DOI: 10.1109/AIHAS.1992.636888
V. Clément, M. Thonnant
This paper deals with the supervision of perception tasks, as a component of an autonomous system. First, the role of this component in an autonomous system is presented. Then a model of supervision of perception tasks is proposed: needed control mechanims as well as knowledge modelling are detailed. In the next section, we propose a software tool named OCAPI that uses artificial intelligence techniques. It has been designed as an expert system shell, and handles knowledge about image processing procedures including their goals and their proper usage. The knowledge base is highly structured to improve the efficiency of the system. The OCAPI system automates planning (selection of a sequence of programs) and control of ezecution (parameters initialization and adjustment, and results evaluation). An application for the supervision of a stereovisual process for obstacle detection in road scenes is descmbed.
{"title":"Supervision of Perception Tasks for Autonomous Systems: the Ocapi Approach","authors":"V. Clément, M. Thonnant","doi":"10.1109/AIHAS.1992.636888","DOIUrl":"https://doi.org/10.1109/AIHAS.1992.636888","url":null,"abstract":"This paper deals with the supervision of perception tasks, as a component of an autonomous system. First, the role of this component in an autonomous system is presented. Then a model of supervision of perception tasks is proposed: needed control mechanims as well as knowledge modelling are detailed. In the next section, we propose a software tool named OCAPI that uses artificial intelligence techniques. It has been designed as an expert system shell, and handles knowledge about image processing procedures including their goals and their proper usage. The knowledge base is highly structured to improve the efficiency of the system. The OCAPI system automates planning (selection of a sequence of programs) and control of ezecution (parameters initialization and adjustment, and results evaluation). An application for the supervision of a stereovisual process for obstacle detection in road scenes is descmbed.","PeriodicalId":442147,"journal":{"name":"Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125650773","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：