514 Hits in 4.6 sec

Forthcoming papers

1998 Artificial Intelligence  
, that takes a significant step toward enabling this future.  ...  The '4-D approach' integrating expection-based methods from systems dynamics and control engineering with methods from AI has allowed to create vehicles with unprecedented capabilities in the technical  ...  is provably correct with respect to the stable model semantics.  ... 
doi:10.1016/s0004-3702(98)90015-7 fatcat:wovog2kmgvcr7clo2c6gyj5qrm

Semantically-based priors and nuanced knowledge core for Big Data, Social AI, and language understanding

Daniel Olsher
2014 Neural Networks  
Noise-resistant and nuanced, COGBASE makes 10 million pieces of commonsense data and a host of novel reasoning algorithms available via a family of semantically-driven prior probability distributions.  ...  document gists and topic models, and link commonsense knowledge to domain models and social, spatial, cultural, and psychological data.  ...  COMMONSENSE reasoning mode This mode is used most frequently with COGBASE.  ... 
doi:10.1016/j.neunet.2014.05.022 pmid:25022322 fatcat:jdhvomvbyzaqxapt6ffjrepc4e

The St. Thomas Common Sense Symposium: Designing Architectures for Human-Level Intelligence

Marvin Minsky, Push Singh, Aaron Sloman
2004 The AI Magazine  
Instead, each developed some special technique that could deal with some class of problem well, but does poorly at almost everything else.  ...  are convinced, however, that no one such method will ever turn out to be "best," and that instead, the powerful AI systems of the future will use a diverse array of resources that, together, will deal with  ...  Involves social reasoning and cooperative problem solving. several reflective levels beyond the reactive and deliberative levels.  ... 
doi:10.1609/aimag.v25i2.1764 dblp:journals/aim/MinskySS04 fatcat:nk6nwrvkbfhsxpsx6i2bpft4tq

An event calculus production rule system for reasoning in dynamic and uncertain domains

2016 Theory and Practice of Logic Programming  
The framework implements the declarative semantics of the underlying logic theories in a forward-chaining rule-based reasoning system, coupling the high expressiveness of its formalisms with the efficiency  ...  A hybrid framework that combines logic-based with probabilistic reasoning has been developed, that aims to accommodate activity recognition and monitoring tasks in smart spaces.  ...  Finally, an explanation of the parsing methodology is given, as an attempt to better clarify how complexity results discussed in section 3.2 are related with the Event Calculus programs.  ... 
doi:10.1017/s1471068416000065 fatcat:thoiu6lbnvftlfyvjwlviq46xq

Logic-Based Technologies for Intelligent Systems: State of the Art and Perspectives

Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini
2020 Information  
Together with the disruptive development of modern sub-symbolic approaches to artificial intelligence (AI), symbolic approaches to classical AI are re-gaining momentum, as more and more researchers exploit  ...  Specific technologies exist for dealing with the environment abstraction of cognitive architectures, mostly in the coordination area.  ...  , possibly building high-level aggregations aimed at synthesizing an argumentative process, to be possibly emulated.  ... 
doi:10.3390/info11030167 fatcat:e3wed54dyzabldrnml7khx37te

Modelling Models of Robot Navigation Using Formal Spatial Ontology [chapter]

John Bateman, Scott Farrar
2005 Lecture Notes in Computer Science  
This approach finds its motivation in cognitive robotics and draws on research from cognitive science and psychology in an attempt to solve problems via high-level reasoning.  ...  Spatial knowledge can then be used that is derived, or abducted, from the sensory level for purposes of navigation, rather than simply having the agent rely on a reactive/sensory level.  ...  We can therefore place approaches to robot navigation along a continuum ranging across: (i) no use of an ontological foundation, where an account has to provide its own knowledge modelling and reasoning  ... 
doi:10.1007/978-3-540-32255-9_21 fatcat:xejypgqnongibaxmuln7zyrzhm

Learning Spatial Models for Navigation [chapter]

Susan L. Epstein, Anoop Aroor, Matthew Evanusa, Elizabeth I. Sklar, Simon Parsons
2015 Lecture Notes in Computer Science  
The approach reported here offers an alternative: navigation with a spatial model and commonsense qualitative spatial reasoning.  ...  In extensive empirical testing, qualitative spatial reasoning principles that reference this model support increasingly effective navigation in a variety of built spaces.  ...  Layered robot architectures typically partition control based on functionality (e.g., with layers for reactive feedback control, planning, and low-level action selection [12] ).  ... 
doi:10.1007/978-3-319-23374-1_19 fatcat:adaq2uz33nfcleb3tmariaz2b4

WHY: Natural Explanations from a Robot Navigator [article]

Raj Korpan, Susan L. Epstein, Anoop Aroor, Gil Dekel
2017 arXiv   pre-print
Language generation here is based upon the robot's commonsense, its qualitative reasoning, and its learned spatial model.  ...  When a robot travels with a human companion, the robot should be able to explain its navigation behavior in natural language.  ...  Along with commonsense qualitative reasoning, affordances are used to select the robot's next action.  ... 
arXiv:1709.09741v1 fatcat:jx6zu3tvjjdwbb5fnzszpxw4m4

Building Agents to Serve Customers

Mihai Barbuceanu, Mark S. Fox, Lei Hong, Yannick Lallement, Zhongdong Zhang
2004 The AI Magazine  
Our customer-service agents use natural language to interact with customers, enabling customers to state their intentions directly instead of searching for the places on the Web site that may address their  ...  Our agents converse with customers, guaranteeing that needed information is acquired from customers and that relevant information is provided to them in order for both parties to make the right decision  ...  by the Interaction Planner, and the domain reasoning level supported by the Business Reasoning module.  ... 
doi:10.1609/aimag.v25i3.1776 dblp:journals/aim/BarbuceanuFHLZ04 fatcat:2lmfria7izdwzl4vzypkjrrlb4

Context-aware decision support in knowledge-intensive collaborative e-Work

Obinna Anya, Hissam Tawfik, Atulya Nagar, Saad Amin
2010 Procedia Computer Science  
specific work context.  ...  We demonstrate how a system based on our proposed model can be applied to support the reactive, collaborative and proactive modes of decision support in collaborative e-work.  ...  reasoning towards a problem solving situation or a decision making process.  ... 
doi:10.1016/j.procs.2010.04.256 fatcat:es57fm2pevc37o6bmspmjmygrm

AAAI 2007 Spring Symposium Series Reports

Thomas Barkowsky, Peter Bruza, Zachary Dodds, Oren Etzioni, George Ferguson, Piotr J. Gmytrasiewicz, Bernhard Hommel, Benjamin Kuipers, Rob Miller, Leora Morgenstern, Simon Parsons, Holger Schultheis (+2 others)
2007 The AI Magazine  
As with previ- commonsense reasoning.  ...  automata and reactive systems.  ... 
doi:10.1609/aimag.v28i3.2058 dblp:journals/aim/BarkowskyBDEFGHKMMPSTY07 fatcat:4vdkaoja6rdfbp4rx5bxbvausa

Immobile Robots AI in the New Millennium

Brian C. Williams, P. Pandurang Nayak
1996 The AI Magazine  
Finally, thanks to Yvonne Clearwater for help with the graphics. Notes 1.  ...  Like David Livingstone, LIVINGSTONE the program is concerned with exploration and the health of explorers.  ...  For high-level reasoning systems that coordinate adaptive processes, the most suitable specification of the adaptive processes are often qualitative.  ... 
doi:10.1609/aimag.v17i3.1229 dblp:journals/aim/WilliamsN96 fatcat:srk53jzxe5dafkpj3m54tto3qi

Scales and Hedges in a Logic with Analogous Semantics [article]

Hedda R. Schmidtke, Sara Coelho
2022 arXiv   pre-print
With the Activation Bit Vector Machine (ABVM), it has a simple and classical logical reasoning mechanism with an inherent imagery process based on the Vector Symbolic Architecture (VSA) model of distributed  ...  Logics with analogous semantics, such as Fuzzy Logic, have a number of explanatory and application advantages, the most well-known being the ability to help experts develop control systems.  ...  This allows us to bring CLA reasoning down to a neuronal bit-level reasoning procedure, where we can also connect it to high-level theories of neuronal computation.  ... 
arXiv:2201.08677v1 fatcat:6m2e7touffd4dg3co4iz3bsvqa

Logic-based subsumption architecture

Eyal Amir, Pedrito Maynard-Zhang
2004 Artificial Intelligence  
It also allows high-level tasks and is tolerant to different changes and elaborations of its knowledge in runtime. Finally, it allows us to give more commonsense knowledge to robots.  ...  We also give formal semantics to our approach.  ...  However, with proper tuning and given recent advances in automated reasoning, this kind of system seems to support high-level reasoning that is still reactive, offering a major advantage to robotic systems  ... 
doi:10.1016/j.artint.2003.07.001 fatcat:h3z7bayngfg7hc3wxbfsei5snq

Learning like a baby: a survey of artificial intelligence approaches

Frank Guerin
2011 Knowledge engineering review (Print)  
One of the major stumbling blocks for Artificial Intelligence remains the commonsense knowledge problem.  ...  The challenge here is to find a learning program which can continuously build on what it knows, to reach increasingly sophisticated levels of knowledge.  ...  This has lead a trend towards avoiding the coding of high level human knowledge, and instead approaching AI research from the bottom up; i.e., by initially building robots which can deal with low level  ... 
doi:10.1017/s0269888911000038 fatcat:bqm6rcwpxbe43awohq6yj5j3ey
« Previous Showing results 1 — 15 out of 514 results