The Naive Physics Manifesto

By P. Hayes. 1990

Subfields: Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Knowledge Graphs & Representation

Citations in the corpus

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, background): “However, it is difficult to answer “what is the minimal viable set of knowledge needed to understand about the physical world?” (Hayes, 1978).”
Interaction Networks for Learning about Objects, Relations and Physics (2016, background): “Previous AI work on physical reasoning explored commonsense knowledge, qualitative representa62 tions, and simulation techniques for approximating physical prediction and inference [28, 9, 6].”
The Generative Lexicon (1991, unknown): “7 Some of these roles are reminiscent of descriptors used by various computational researchers, such as Wilks (1975b), Hayes (1979), and Hobbs et al. (1987).”
Envisioning the qualitative effects of robot manipulation actions using simulation-based projections (2017, background): “As mentioned above, understanding everyday physical phenomena, that is representing and reasoning about them, is an endeavor in the ﬁeld of Artiﬁcial Intelligence which dates at least back to the work of Hayes (1979).”
The scope and limits of simulation in automated reasoning (2016, unknown): “” [24,25,10,13]; or it may be an “intuitive” or “naïve” theory such as an impulse theory of motion.”
Commonsense reasoning about containers using radically incomplete information (2017, methodology): “To characterize cavities dynamically, we use histories; that is, functions from time to regions (Hayes, 1979).”
On Ontology, ontologies, Conceptualizations, Modeling Languages, and (Meta)Models (2007, methodology): “Since the first time the term was used in AI by Hayes [4] and since the development of his naïve ph ysics ontology of liquids [5], a large amount of do main ontologies have been developed in a multitude of su bject areas.”
Machine Common Sense Concept Paper (2018, background): “This suggestion led to a variety of efforts to develop logic‐based approaches to commonsense reasoning (e.g., situation calculus [3], naïve physics [4], default reasoning [5], non‐monotonic logics [6], description logics [7], and qualitative reasoning [8]), less formal knowledge‐based approaches…”