The Turing Test was originally proposed as a way of evaluating how well a software system represents human intelligence, based on natural language conversations.
It has recently been recognized that a different approach is needed that incorporates the capabilities required for general intelligence.
The Physical Turing Test extends the Turing Test by specifying questions that require the integration of perception, reasoning, and action.
In particular, two tracks are proposed for the Physical Turing Test.
- The Construction Track focuses on building predefined structures (such as a tent or modular furniture) given a combination of verbal instructions and images.
- The Exploration Track focuses on experiments in building, modifying, and interacting with complex structures.
The research program in this proposal is motivated by the following long-term vision related to the Construction Track:
Given a set of verbal instructions, together with a sequence of annotated images, answer questions about the activities that can possibly occur during the performance of the instructions and the various objects that participate in these activity occurrences.
To address this long-term vision, the proposed research program has two primary objectives:
- Design new ontologies. We will refer to these as the PRAxIS Ontologies (for Perception, Reasoning, and Action across Intelligent Systems) in first-order logic that can represent objects in the physical world, the activities in which these objects can possibly participate, and how to recognize these objects and the spatial relationships between them within images.
- Integrate the PRAxIS Ontologies to support reasoning about physical objects, their behaviors (e.g. the ways in which they can change), and their interactions (e.g. manipulation of solid physical objects).
Paper:
- M. Gruninger, B. Aameri, C. Chui, T. Hahmann, Y. Ru The FOUnt Ontologies for Units of Measure and the Physical World, Applied Ontology 16:.
- Aameri, B. and Gruninger, M. Location Ontologies based on Mereotopological Pluralism, Applied Ontology. 15:1-50
- Aameri, B. and Gruninger, M. (2017) Encountering the Physical World, Eighth Conference on Formal Ontology Meets Industry
- Aameri, B. and Gruninger, M. (2017) A new perspective on the mereotopology of RCC8, Conference on Spatial Information Theory (COSIT 2017), L'Aquila, Italy.
The Process Specification Language is a common ontology for process modeling that was standardized in 2005 as ISO 18629.
PSL provides an ontology that is axiomatized using first-order logic. It is a modular ontology consisting of a core theory that outlines the basic objects that exist in the domain(activity, activity-occurrence, timepoint, and object) and a multitude of consistent extensions that define a rich terminology for describing process knowledge.
The Second Edition of ISO 24707 (Common Logic) was published in 2017.
Common Logic is a family of logic languages designed for use in the representation and interchange of knowledge among disparate computer systems. e.g. the specification of expressions that are the input or output to automated reasoning systems such as theorem provers and constraint satisfaction systems.
An upper ontology is a single artefact, describing some collection of concepts, typically of foundational concepts (e.g., time, space).
An upper ontology axiomatizes a single, fixed set of ontological commitments for the semantics of those concepts, which are universally applicable; other ontologies are meant to be a specialization (an extension) of the upper ontology.
ISO 21838 (Top Level Ontologies) specifies the characteristics of an upper ontology, and includes different upper ontologies as parts within the standard.
The work we have done in the verification and modularization of DOLCE has been incorporated into ISO 21838-3 (Top Level Ontologies: DOLCE), and the newly designed TUpper Ontology is being submitted as ISO 21838-4 (Top Level Ontologies: TUpper).
Upper ontologies have traditionally arisen from the approach in which concepts that are common across a set of domains can be axiomatized at a general level. The rationale is that reuse across domains is to be supported through specialization of the general concepts from an upper ontology. Similarly, semantic integration between ontologies is to be achieved through the general concepts they specialize in.
The TUpper
Ontology follows an alternative approach (referred to as the sideways approach) to the conventional upper ontology paradigm. Rather than think of an upper ontology as a monolithic axiomatization centred on a taxonomy, the sideways approach considers an upper ontology to be a modular ontology composed of generic ontologies that cover concepts including those related to time, process, and space. The central claim is that an upper ontology is a reducible ontology that has a reduction whose modules are all generic ontologies (Figures 1 through 5 show the modules within TUpper). Each upper ontology is therefore composed of a set of generic ontologies, and each generic ontology axiomatizes a particular set of generic concepts (e.g., the classes and relations relevant for time, process, and space). New upper ontologies can be designed by the union of different generic ontologies that already exist.
The TUpper Ontology is designed as a top-level ontology that contains modules from the ontologies within existing international standards, and that extends these modules so as to satisfy the criteria for top-level ontologies in ISO/IEC 21838-1.
Papers
- Silva-Munoz, L. and Gruninger, M. Verifying and Mapping the Mereotopology of upper-Level Ontologies, Knowledge Engineering and Ontology Design (KEOD 2016), Porto, Portugal.
- Silva-Munoz, L. and Gruninger, M.Locating Things in Space and Time: Verification of the SUMO Upper-Level Ontology, European Knowledge Acquisition Workshop (EKAW 2016), Bologna, Italy.
COLORE is an open repository of first-order ontologies that serves as a testbed for ontology evaluation and integration techniques, and that can support the design, evaluation, and application of ontologies in first-order logic.
All ontologies are specified using Common Logic (ISO 24707-2017), which is a recently standardized logical language for the specification of first-order ontologies and knowledge bases.
There are currently 2580 first-order ontologies within COLORE (colore.oor.net) which are organized into hierarchies (sets of ontologies with the same signature).
Papers
- Gruninger, M., Hahmann, T., Hashemi, A., Ong, D., and Ozgovde, A. (2012) Modular First-Order Ontologies via Repositories, Applied Ontology 7:169-210.
- Gruninger, M., Chui, C., Katsumi, M. (2017) Upper Ontologies in COLORE. In: Proceedings of the Joint Ontology Workshops 2017 Episode 3: The Tyrolean Autumn of Ontology, Bozen-Bolzano, Italy, September
- Katsumi, M. and Gruninger, M. (2018) Metatheory of Ontology Reuse. Applied Ontology 13:1-30. Katsumi, M. and Gruninger, M. Choosing Ontologies for Reuse. (2017) Applied Ontology, vol. 12 no.1, pp. 1-27.
