From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solving [PDF]
Frontiers in Robotics and AI, 2019 Reinforcement learning is generally accepted to be an appropriate and successful method to learn robot control. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-
Manfred Eppe +2 more
openalex +3 more sources
Minimizing Entropy and Complexity in Creative Production from Emergent Pragmatics to Action Semantics [PDF]
EntropyNew insights into intractable industrial challenges can be revealed by framing them in terms of natural science. One intractable industrial challenge is that creative production can be much more financially expensive and time consuming than standardized ...
Stephen Fox
doaj +2 more sources
Theory and Practice of Action Semantics
BRICS Report Series, 1996 Action Semantics is a framework for the formal description of programming languages. Its main advantage over other frameworks is pragmatic: action-semantic descriptions (ASDs) scale up smoothly to realistic programming languages.
Peter D. Mosses
semanticscholar +5 more sources
An Introduction to Action Semantics
DAIMI Report Series, 1991 <p>Formal semantics is a topic of major importance in the study of programming languages. Its applications include documenting language design, establishing standards for implementations, reasoning about programs, and generating compilers.</p><p> </p><p>These notes introduce <em>action semantics</em>, a ...
Peter D. Mosses
openalex +4 more sources
Learning the semantics of object–action relations by observation [PDF]
The International Journal of Robotics Research, 2011 Recognizing manipulations performed by a human and the transfer and execution of this by a robot is a difficult problem. We address this in the current study by introducing a novel representation of the relations between objects at decisive time points during a manipulation.
Eren Erdal Aksoy +5 more
openalex +7 more sources
Constructive Action Semantics for Core ML
IEE Proceedings - Software, 2004 Usually, the majority of language constructs found in a programming language can also be found in many other languages, because language design is based on reuse. This should be reflected in the way we give semantics to programming languages.
Jørgen Iversen, Peter D. Mosses
openalex +3 more sources
Scene semantics affects allocentric spatial coding for action in naturalistic (virtual) environments [PDF]
Scientific ReportsInteracting with objects in our environment requires determining their locations, often with respect to surrounding objects (i.e., allocentrically). According to the scene grammar framework, these usually small, local objects are movable within a scene ...
Bianca R. Baltaretu +3 more
doaj +2 more sources
An action decoding framework combined with deep neural network for predicting the semantics of human actions in videos from evoked brain activities. [PDF]
Front NeuroinformZhang Y, Tian M, Liu B.
europepmc +2 more sources
Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases [PDF]
European Conference on Computer Vision, 2023 Motion understanding aims to establish a reliable mapping between motion and action semantics, while it is a challenging many-to-many problem. An abstract action semantic (i.e., walk forwards) could be conveyed by perceptually diverse motions (walking ...
Xinpeng Liu +5 more
semanticscholar +1 more source
Using UML Action Semantics for Executable Modeling and Beyond [PDF]
International Conference on Advanced Information Systems Engineering, 2001 Gerson Sunyé +4 more
openalex +2 more sources