Filters








120,073 Hits in 5.9 sec

Using Machine Learning for Decreasing State Uncertainty in Planning

Senka Krivic, Michael Cashmore, Daniele Magazzeni, Sandor Szedmak, Justus Piater
2020 The Journal of Artificial Intelligence Research  
We present a novel approach for decreasing state uncertainty in planning prior to solving the planning problem.  ...  We demonstrate that an agent is able to solve problems with uncertainties in the state with less planning effort compared to standard planning techniques.  ...  Sensing Action Selection in Contingent Planning There are a number of approaches to planning with incomplete information and sensing actions.  ... 
doi:10.1613/jair.1.11567 fatcat:zcj7fxx63naibdhvwkcv3lsl6a

Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning [article]

Haonan Chen, Hao Tan, Alan Kuntz, Mohit Bansal, Ron Alterovitz
2020 arXiv   pre-print
However, natural language instructions are often missing information that would be obvious to a human based on environmental context and common sense, and hence does not need to be explicitly stated.  ...  Our results show the feasibility of a robot learning commonsense knowledge automatically from web-based textual corpora, and the power of learned commonsense reasoning models in enabling a robot to autonomously  ...  We refer to the LM trained and tested with the former approach as frame-based LM and the latter one as sentence-based LM.  ... 
arXiv:1904.12907v2 fatcat:gs4g2ijdnrds7afl6dggvbtwlu

Controlling Semi-automatic Systems with FLUX [chapter]

Michael Thielscher
2003 Lecture Notes in Computer Science  
FLUX is a recent, constraint logic programming-based method for designing reasoning agents that can sense, act, and plan under incomplete information [3] .  ...  An agent program in this language consists of a background theory, which endows the agent with the necessary knowledge of its actions, along with a high-level acting and planning strategy.  ...  FLUX is a recent, constraint logic programming-based method for designing reasoning agents that can sense, act, and plan under incomplete information [3] .  ... 
doi:10.1007/978-3-540-24599-5_49 fatcat:p7rnummv2faetlvmmz65byheue

Least Commitment on Variable Binding in Presence of Incomplete Knowledge [chapter]

R. Barruffi, E. Lamma, P. Mello, M. Milano
2000 Lecture Notes in Computer Science  
For this purpose, we have extended a Partial Order Planner performing least commitment on variable binding. This extension can cope with incomplete knowledge.  ...  A constraint based approach for this issue has been previously proposed by Yang and Chan 21]. In this setting, the planning problem is mapped onto a Constraint Satisfaction Problem.  ...  Acknowledgments Authors' work has been partially supported by Hewlett Packard Laboratories of Bristol-UK (Internet Business Management Department) and CNR, (Project 40%).  ... 
doi:10.1007/10720246_13 fatcat:xbjn4d2kufc75liitnceutkxf4

Planning perception and action for cognitive mobile manipulators

Andre Gaschler, Svetlana Nogina, Ronald P. A. Petrick, Alois Knoll, Juha Röning, David Casasent
2014 Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques  
Our approach is based on contingent planning and run-time sensing, integrated in our "knowledge of volumes" planning framework, called KVP.  ...  We present a general approach to perception and manipulation planning for cognitive mobile manipulators.  ...  supporting deterministic planning with incomplete information and sensing.  ... 
doi:10.1117/12.2038967 fatcat:huiyegnejnh2zof4mivvjau56i

Forthcoming Papers

2005 Artificial Intelligence  
How should one interpret informal evidential statements? Should, and do, iterated belief revisions commute?  ...  to this problem: how should one specify uncertain evidence?  ...  Oglietti, Understanding planning with incomplete information and sensing PKS is the framework for planning with incomplete information and sensing recently introduced by Bacchus and Petrick [Proc.  ... 
doi:10.1016/j.artint.2004.12.001 fatcat:msj5iuiqgzhtlmsunydxvwafvm

Page 7415 of Mathematical Reviews Vol. , Issue 2001J [page]

2001 Mathematical Reviews  
Summary: “In the presence of incomplete information about the world we need to distinguish between the state of the world and the state of an agent’s knowledge about the world.  ...  This paper extends inconsistency-tolerant inference meth- ods from the flat case to the prioritized case and investigates other methods, specific to prioritized knowledge bases, for coping with inconsistency  ... 

Planning with Sensing Actions and Incomplete Information Using Logic Programming [chapter]

Tran Cao Son, Phan Huy Tu, Chitta Baral
2003 Lecture Notes in Computer Science  
We present a logic programming based conditional planner that is capable of generating both conditional plans and conformant plans in the presence of sensing actions and incomplete information.  ...  We prove the correctness of our implementation and show that our planner is complete with respect to the 0approximation of sensing actions and the class of conditional plans considered in this paper.  ...  The work is partially supported by NSF grants EIA-0130887 and EIA-0220590.  ... 
doi:10.1007/978-3-540-24609-1_23 fatcat:dcxb7qid4jhh3j2essfpwhwfmu

Beyond Reward: The Problem of Knowledge and Data [chapter]

Richard S. Sutton
2012 Lecture Notes in Computer Science  
Intelligence can be defined, informally, as knowing a lot and being able to use that knowledge flexibly to achieve one's goals. In this sense it is clear that knowledge is central to intelligence.  ...  the knowledge base becomes large and diverse.  ...  Acknowledgements This work was done with many colleagues, including particularly Anna Koop  ... 
doi:10.1007/978-3-642-31951-8_2 fatcat:q4sjjqspmncvhlpwciup4tjwny

Narrative based Postdictive Reasoning for Cognitive Robotics [article]

Manfred Eppe, Mehul Bhatt
2013 arXiv   pre-print
Making sense of incomplete and conflicting narrative knowledge in the presence of abnormalities, unobservable processes, and other real world considerations is a challenge and crucial requirement for cognitive  ...  In the backdrop of an autonomous wheelchair robot control task, we report on application-driven work to realise postdiction triggered abnormality detection and re-planning for real-time robot control:  ...  This requires a formalism like HPX , which supports sensing along with postdiction.  ... 
arXiv:1306.0665v1 fatcat:6gxk3zaf6jaylajcmx7uzqptde

Planning while Executing: A Constraint-Based Approach [chapter]

R. Barruffi, M. Milano, P. Torroni
2000 Lecture Notes in Computer Science  
According to the deferred planning strategy proposed in 14 , a plan schema is produced o -line by a generative constraint based planner and re ned at execution time by retrieving up-todate information  ...  We propose a planning architecture where the planner and the executor interact with each other in order to face dynamic changes of the application domain.  ...  Thus, it is not convenient, if possible at all, to store all this information in advance and keep it up-to-date. We developed a planner able to deal with dynamic and incomplete knowledge.  ... 
doi:10.1007/3-540-39963-1_24 fatcat:64uflj3nufgznk3mkkqpak5azm

Planning and Failure Detection [chapter]

Michael Brenner, Christian Plagemann, Bernhard Nebel, Wolfram Burgard, Nick Hawes
2010 Cognitive Systems Monographs  
Agents can then plan how to extend their knowledge.  ...  Our approach is based on the idea of active knowledge-gathering: instead of planning for possible contingencies, agents try to learn more about the state of the world directly.  ... 
doi:10.1007/978-3-642-11694-0_6 fatcat:l33656kcmjf2bmn4jfdqhv6mjm

Multi-Modal Active Perception for Information Gathering in Science Missions [article]

Akash Arora, P. Michael Furlong, Robert Fitch, Salah Sukkarieh, Terrence Fong
2017 arXiv   pre-print
We then formulate path planning and sensor scheduling as an information gain maximization problem, and propose a sampling-based solution based on Monte Carlo tree search to plan informative sensing actions  ...  The computational complexity of our framework does not grow with the number of observations taken and allows long horizon planning in an anytime manner, making it highly applicable to field robotics.  ...  ACKNOWLEDGEMENTS The authors would like to thank Richard Elphic at NASA Ames Research Center for his help in understanding the Neutron Spectrometer System data.  ... 
arXiv:1712.09716v1 fatcat:622gwsio2rexvcsveedpohuuhq

Functionally Accurate, Cooperative Distributed Systems

Victor R. Lesser, Daniel D. Corkill
1981 IEEE Transactions on Systems, Man and Cybernetics  
Much of the inspiration for the FA/C approach comes from the mechanisms used in knowledge-based artificial intelligence (AI) systems for resolving uncertainty caused by noisy input data and the use of  ...  The appropriateness of the FA/C approach is explored in three application domains: distributed interpretation, distributed network traffic-light control, and distributed planning.  ...  We would also like to acknowledge discussions with the other members of the University of Massachusetts Cooperative Distributed Problem-Solving Research Group: Jasmina Pavlin, Scott Reed, and Ram Mukunda  ... 
doi:10.1109/tsmc.1981.4308581 fatcat:hmsgkoexfjcuxpwkg2nscriwfu

Functionally Accurate, Cooperative Distributed Systems [chapter]

VICTOR R. LESSER, DANIEL D. CORKILL
1988 Readings in Distributed Artificial Intelligence  
Much of the inspiration for the FA/C approach comes from the mechanisms used in knowledge-based artificial intelligence (AI) systems for resolving uncertainty caused by noisy input data and the use of  ...  The appropriateness of the FA/C approach is explored in three application domains: distributed interpretation, distributed network traffic-light control, and distributed planning.  ...  We would also like to acknowledge discussions with the other members of the University of Massachusetts Cooperative Distributed Problem-Solving Research Group: Jasmina Pavlin, Scott Reed, and Ram Mukunda  ... 
doi:10.1016/b978-0-934613-63-7.50034-6 fatcat:vymhphlmffeijbgzpvgnvfnuee
« Previous Showing results 1 — 15 out of 120,073 results