oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Bhatt, Mehul, ProfessorORCID iD iconorcid.org/0000-0002-6290-5492
Biography [eng]

 

 
Biography [swe]

 

 
Publications (10 of 80) Show all publications
Lieto, A., Bhatt, M., Oltramari, A. & Vernon, D. (2018). The role of cognitive architectures in general artificial intelligence. Cognitive Systems Research, 48, 1-3
Open this publication in new window or tab >>The role of cognitive architectures in general artificial intelligence
2018 (English)In: Cognitive Systems Research, ISSN 2214-4366, E-ISSN 1389-0417, Vol. 48, p. 1-3Article in journal (Refereed) Published
Abstract [en]

The term "Cognitive Architectures" indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field of Artificial Intelligence (AI). The main role of Cognitive Architectures in AI is that one of enabling the realization of artificial systems able to exhibit intelligent behavior in a general setting through a detailed analogy with the constitutive and developmental functioning and mechanisms underlying human cognition. We provide a brief overview of the status quo and the potential role that Cognitive Architectures may serve in the fields of Computational Cognitive Science and Artificial Intelligence (AI) research.

Place, publisher, year, edition, pages
Elsevier, 2018
Keyword
Cognitive architectures; Artificial intelligence; Autonomous systems; General artificial intelligence
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-64438 (URN)10.1016/j.cogsys.2017.08.003 (DOI)000419552300001 ()
Available from: 2018-01-20 Created: 2018-01-20 Last updated: 2018-01-22Bibliographically approved
Suchan, J., Bhatt, M., Wałęga, P. & Schultz, C. (2018). Visual Explanation by High-Level Abduction: On Answer-Set Programming Driven Reasoning about Moving Objects. In: AAAI 2018: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. Paper presented at Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA, February 2-7, 2018.
Open this publication in new window or tab >>Visual Explanation by High-Level Abduction: On Answer-Set Programming Driven Reasoning about Moving Objects
2018 (English)In: AAAI 2018: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018Conference paper, Published paper (Refereed)
Abstract [en]

We propose a hybrid architecture for systematically computing robust visual explanation(s) encompassing hypothesis formation, belief revision, and default reasoning with video data. The architecture consists of two tightly integrated synergistic components: (1)(functional) answer set programming based abductive reasoning with SPACE-TIME TRACKLETS as native entities; and (2) a visual processing pipeline for detection based object tracking and motion analysis.

We present the formal framework, its general implementation as a (declarative) method in answer set programming, and an example application and evaluation based on two diverse video datasets: the MOTChallenge benchmark developed by the vision community, and a recently developed Movie Dataset

Keyword
artificial intelligence, cognitive vision, knowledge representation and reasoning, computer vision, robotics
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-63758 (URN)
Conference
Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA, February 2-7, 2018
Available from: 2018-01-02 Created: 2018-01-02 Last updated: 2018-01-13Bibliographically approved
Lieto, A., Bhatt, M., Oltramari, A. & Vernon, D. (Eds.). (2017). Artificial Intelligence and Cognition 2016: Proceedings of the 4th International Workshop on Artificial Intelligence and Cognition co-located with the Joint Multi-Conference on Human-Level Artificial Intelligence (HLAI 2016), New York City, NY, USA, July 16-17, 2016. Paper presented at 4th International Workshop on Artificial Intelligence and Cognition (AIC 2016), New York, USA, July 16-17, 2016. Technical University of Aachen, 1895
Open this publication in new window or tab >>Artificial Intelligence and Cognition 2016: Proceedings of the 4th International Workshop on Artificial Intelligence and Cognition co-located with the Joint Multi-Conference on Human-Level Artificial Intelligence (HLAI 2016), New York City, NY, USA, July 16-17, 2016
2017 (English)Conference proceedings (editor) (Other academic)
Place, publisher, year, edition, pages
Technical University of Aachen, 2017
Series
CEUR Workshop Proceedings, E-ISSN 1613-0073 ; 1895
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-63589 (URN)
Conference
4th International Workshop on Artificial Intelligence and Cognition (AIC 2016), New York, USA, July 16-17, 2016
Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-02-20Bibliographically approved
Schultz, C., Bhatt, M. & Borrmann, A. (2017). Bridging qualitative spatial constraints and feature-based parametric modelling: Expressing visibility and movement constraints. Advanced Engineering Informatics, 31, 2-17
Open this publication in new window or tab >>Bridging qualitative spatial constraints and feature-based parametric modelling: Expressing visibility and movement constraints
2017 (English)In: Advanced Engineering Informatics, ISSN 1474-0346, E-ISSN 1873-5320, Vol. 31, p. 2-17Article in journal (Refereed) Published
Abstract [en]

We present a concept for integrating state-of-the-art methods in geometric and qualitative spatial representation and reasoning with feature-based parametric modelling systems. Using a case-study involving a combination of topological, visibility, and movement constraints, we demonstrate the manner in which a parametric model may be constrained by the spatial aspects of conceptual design specifications and higher-level semantic design requirements. We demonstrate the proposed methodology by applying it to architectural floor plan layout design, where a number of spaces with well defined functionalities have to be arranged such that particular functional design constraints are maintained. The case-study is developed by an integration of the declarative spatial reasoning system CLP(QS) (CLP(QS) - a declarative spatial reasoning system. www.spatial-reasoning.com.) with the parametric CAD system FreeCAD.

Place, publisher, year, edition, pages
Elsevier, 2017
Keyword
Feature-based parametric modelling; Geometric constraint solving; Declarative spatial reasoning; Knowledge representation and reasoning
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-63583 (URN)10.1016/j.aei.2015.10.004 (DOI)000392044800002 ()2-s2.0-84948799892 (Scopus ID)
Note

Funding Agencies:

German Research Foundation (DFG) via Spatial Cognition Research Center  SFB/TR 8

German Research Foundation (DFG) under grant for the SketchMapia project  SCHW 1372/7-1 

Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-01-13Bibliographically approved
Bhatt, M., Cutting, J., Levin, D. & Lewis, C. (2017). Cognition, Interaction, Design: Discussions as Part of the Codesign Roundtable 2017. Künstliche Intelligenz, 31(4), 363-371
Open this publication in new window or tab >>Cognition, Interaction, Design: Discussions as Part of the Codesign Roundtable 2017
2017 (English)In: Künstliche Intelligenz, ISSN 0933-1875, E-ISSN 1610-1987, Vol. 31, no 4, p. 363-371Article in journal (Refereed) Published
Abstract [en]

This transcript documents select parts of discus-sions on the confluence of cognition, interaction, design, and human behaviour studies. The interview and related events were held as part of the CoDesign 2017 Roundtable (Bhatt in CoDesign 2017—The Bremen Summer of Cognition and Design/CoDesign Roundtable. University of Bremen, Bremen, 2017) at the University of Bremen (Germany) in June 2017. The Q/A sessions were moderated by Mehul Bhatt (University of Bremen, Germany., and Örebro Uni-versity, Sweden) and Daniel Levin (Vanderbilt University, USA). Daniel Levin served in a dual role: as co-moderator of the discussion, as well as interviewee. The transcript is published as part of a KI Journal special issue on “Seman-tic Interpretation of Multi-Modal Human Behaviour Data” (Bhatt and Kersting in Special Issue on: Semantic Interpre-tation of Multimodal Human Behaviour Data, Artif Intell, 2017).

Place, publisher, year, edition, pages
Springer, 2017
Keyword
Artificial intelligence; Cognitive science; Psychology; Design cognition and computation; Engineering; Human behaviour studies
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-63585 (URN)10.1007/s13218-017-0512-x (DOI)000424411300008 ()
Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-02-22Bibliographically approved
Suchan, J. & Bhatt, M. (2017). Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW): . Paper presented at ICCV 2017 Workshop - Vision in Practice on Autonomous Robots (ViPAR), 16th IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 22-29, 2017 (pp. 742-750). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions
2017 (English)In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 742-750Conference paper, Published paper (Refereed)
Abstract [en]

We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions. The key contribution is an integrative methodology combining low-level visual processing with high-level, human-centred representations of space and motion rooted in artificial intelligence. We demonstrate practical applicability with examples involving object interactions, and indoor movement.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2017
Series
IEEE International Conference on Computer Vision Workshops, ISSN 2473-9936, E-ISSN 2473-9944
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:oru:diva-63590 (URN)10.1109/ICCVW.2017.93 (DOI)000425239600085 ()978-1-5386-1034-3 (ISBN)978-1-5386-1035-0 (ISBN)
Conference
ICCV 2017 Workshop - Vision in Practice on Autonomous Robots (ViPAR), 16th IEEE International Conference on Computer Vision (ICCV), Venice, Italy, October 22-29, 2017
Note

Funding Agency:

Germany Research Foundation (DFG) via the Collabortive Research Center (CRC) EASE - Everyday Activity Science and Engineering

Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-03-12Bibliographically approved
Suchan, J. & Bhatt, M. (2017). Deep semantic abstractions of everyday human activities: On commonsense representations of human interactions. In: Anibal Ollero, Alberto Sanfeliu, Luis Montano, Nuno Lau, Carlos Cardeira (Ed.), Anibal Ollero, Alberto Sanfeliu, Luis Montano, Nuno Lau, Carlos Cardeira (Ed.), ROBOT 2017: Third Iberian Robotics Conference. Vol. 1. Paper presented at Third Iberian Robotics Conference, Seville, Spain, November 22-24, 2017 (pp. 477-488). Springer
Open this publication in new window or tab >>Deep semantic abstractions of everyday human activities: On commonsense representations of human interactions
2017 (English)In: ROBOT 2017: Third Iberian Robotics Conference. Vol. 1 / [ed] Anibal Ollero, Alberto Sanfeliu, Luis Montano, Nuno Lau, Carlos Cardeira, Springer, 2017, p. 477-488Conference paper, Published paper (Refereed)
Abstract [en]

We propose a deep semantic characterisation of space and motion categorically from the viewpoint of grounding embodied human-object interactions. Our key focus is on an ontological model that would be adept to formalisation from the viewpoint of commonsense knowledge representation, relational learning, and qualitative reasoning about space and motion in cognitive robotics settings. We demonstrate key aspects of the space & motion ontology and its formalisation as a representational framework in the backdrop of select examples from a dataset of everyday activities. Furthermore, focussing on human-object interaction data obtained from RGBD sensors, we also illustrate how declarative (spatio-temporal) reasoning in the (constraint) logic programming family may be performed with the developed deep semantic abstractions.

Place, publisher, year, edition, pages
Springer, 2017
Series
Advances in Intelligent Systems and Computing, ISSN 2194-5357, E-ISSN 2194-5365 ; 693
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:oru:diva-63588 (URN)10.1007/978-3-319-70833-1_39 (DOI)978-3-319-70832-4 (ISBN)978-3-319-70833-1 (ISBN)
Conference
Third Iberian Robotics Conference, Seville, Spain, November 22-24, 2017
Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-01-19Bibliographically approved
Kondyli, V., Schultz, C. & Bhatt, M. (2017). Evidence-Based Parametric Design: Computationally Generated Spatial Morphologies Satisfying Behavioural-Based Design Constraints. In: 13th International Conference on Spatial Information Theory (COSIT 2017): . Paper presented at 13th International Conference on Spatial Information Theory (COSIT 2017), L'Aquila, Italy, September 4-8, 2017 (pp. 11:1-11:14). Springer International Publishing AG, 86
Open this publication in new window or tab >>Evidence-Based Parametric Design: Computationally Generated Spatial Morphologies Satisfying Behavioural-Based Design Constraints
2017 (English)In: 13th International Conference on Spatial Information Theory (COSIT 2017), Springer International Publishing AG , 2017, Vol. 86, p. 11:1-11:14Conference paper, Published paper (Refereed)
Abstract [en]

Parametric design is an established method in engineering and architecture facilitating the rapid generation and evaluation of a large number of configurations and shapes of complex physical structures according to constraints specified by the designer. However, the emphasis of parametric design systems, particularly in the context of architectural design of large-scale spaces, is on numerical aspects (e.g., maximising areas, specifying dimensions of walls) and does not address human-centred design criteria, for example, as developed from behavioural evidence-based studies. This paper aims at providing an evidence-based human-centred approach for defining design constraints for parametric modelling systems. We determine design rules that address wayfinding issues through behavioural multi-modal data analysis of a wayfinding case study in two healthcare environments of the Parkland hospital (Dallas). Our rules are related to the environmental factors of visibility and positioning of manifest cues along the navigation route. We implement our rules in FreeCAD, an open-source parametric system.

Place, publisher, year, edition, pages
Springer International Publishing AG, 2017
Series
Leibniz International Proceedings in Informatics, LIPIcs, E-ISSN 1868-8969 ; 86
Keyword
parametric modelling, behavioural studies, Evidence-Based Design, design computing, wayfinding, spatial cognition
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-63587 (URN)10.4230/LIPIcs.COSIT.2017.11 (DOI)2-s2.0-85026824906 (Scopus ID)9783959770439 (ISBN)
Conference
13th International Conference on Spatial Information Theory (COSIT 2017), L'Aquila, Italy, September 4-8, 2017
Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-02-20Bibliographically approved
Walega, P. A., Schultz, C. P. L. & Bhatt, M. (2017). Non-monotonic spatial reasoning with answer set programming modulo theories. Theory and Practice of Logic Programming, 17(2), 205-225
Open this publication in new window or tab >>Non-monotonic spatial reasoning with answer set programming modulo theories
2017 (English)In: Theory and Practice of Logic Programming, ISSN 1471-0684, E-ISSN 1475-3081, Vol. 17, no 2, p. 205-225Article in journal (Refereed) Published
Abstract [en]

The systematic modelling of dynamic spatial systems is a key requirement in a wide range of application areas such as commonsense cognitive robotics, computer-aided architecture design, and dynamic geographic information systems. We present Answer Set Programming Modulo Theories (ASPMT)(QS), a novel approach and fully implemented prototype for non-monotonic spatial reasoning - a crucial requirement within dynamic spatial systems based on ASPMT. ASPMT(QS) consists of a (qualitative) spatial representation module (QS) and a method for turning tight ASPMT instances into Satisfiability Modulo Theories (SMT) instances in order to compute stable models by means of SMT solvers. We formalise and implement concepts of default spatial reasoning and spatial frame axioms. Spatial reasoning is performed by encoding spatial relations as systems of polynomial constraints, and solving via SMT with the theory of real non-linear arithmetic. We empirically evaluate ASPMT(QS) in comparison with other contemporary spatial reasoning systems both within and outside the context of logic programming. ASPMT(QS) is currently the only existing system that is capable of reasoning about indirect spatial effects (i.e., addressing the ramification problem), and integrating geometric and QS information within a non-monotonic spatial reasoning context.

Place, publisher, year, edition, pages
Cambridge University Press, 2017
Keyword
non-monotonic spatial reasoning; answer set programming modulo theories; declarative spatial reasoning; dynamic spatial systems; reasoning about space; actions; and change
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-63586 (URN)10.1017/S1471068416000193 (DOI)000395794300003 ()2-s2.0-84984693491 (Scopus ID)
Note

Funding Agency:

Polish National Science Centre  2011/02/A/HS1/0039

Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-01-13Bibliographically approved
Bhatt, M. & Schultz, C. (2017). People-Centered Visuospatial Cognition: Next-Generation Architectural Design Systems and Their Role in Design Conception, Computing, and Communication. In: Ammon, Sabine; Capdevila-Werning, Remei (Ed.), The Active Image: Architecture and Engineering in the Age of Modeling (pp. 207-232). Springer International Publishing
Open this publication in new window or tab >>People-Centered Visuospatial Cognition: Next-Generation Architectural Design Systems and Their Role in Design Conception, Computing, and Communication
2017 (English)In: The Active Image: Architecture and Engineering in the Age of Modeling / [ed] Ammon, Sabine; Capdevila-Werning, Remei, Springer International Publishing , 2017, p. 207-232Chapter in book (Other academic)
Abstract [en]

When undertaking the task of design, architects imagine and anticipate the visuospatial and navigational experience of building users during the initial design conception phase. The ultimate goal is to ensure that the final physical built-up structure inherently performs with respect to people-centered design criteria encompassing function, behavior, and affordance. We argue that next-generation people-centered design systems, frameworks, assistive tools, educational discourse, and design policies and practices need to be explicitly founded on the cognitive modalities of human perception, attention, action, dynamics, environmental affordance and user experience, and design conception and semantics. We posit that this requires a holistic approach to architectural design cognition, encompassing the application of principles, practices, and methods from the fields of architecture and engineering, cognitive science, spatial cognition and computation, and evidence-based empirical methods in environmental and social psychology.

Place, publisher, year, edition, pages
Springer International Publishing, 2017
Series
Philosophy of Engineering and Technology, ISSN 1879-7202, E-ISSN 1879-7210 ; 28
Keyword
Computer science; Cognitive science; Artificial intelligence; Cognitive systems; Human-computer interaction; Architecture; Design; Social and behavioural sciences; Spatial cognition and computation; Spatial reasoning; Design semantics; People-centered design; Spatial assistance systems; Computer-aided Architecture Design (CAAD)
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-63608 (URN)10.1007/978-3-319-56466-1_9 (DOI)978-3-319-56465-4 (ISBN)978-3-319-56466-1 (ISBN)
Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-01-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-6290-5492

Search in DiVA

Show all publications