The GLAIR Cognitive Architecture and Prospects for Consciousness Stuart C. Shapiro Department of Computer Science & Engineering and Center.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California
Advertisements

Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Mental Simulation and Learning in the I CARUS Architecture.
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Modeling Social Cognition in a Unified Cognitive Architecture.
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona A Cognitive Architecture for Integrated.
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA A Unified Cognitive Architecture for Embodied Agents Thanks.
Pat Langley Institute for the Study of Learning and Expertise Palo Alto, California A Cognitive Architecture for Complex Learning.
Semantics (Representing Meaning)
SPECIFYING MODALITIES IN THE MGLAIR ARCHITECTURE Stuart C. Shapiro and Jonathan P. Bona Department of Computer Science and Engineering And Center for Cognitive.
S.C. Shapiro Knowledge Representation and Reasoning Stuart C. Shapiro Professor, CSE Director, SNePS Research Group Member, Center for Cognitive.
Research in Knowledge Representation and Reasoning Stuart C. Shapiro Department of Computer Science & Engineering Center for MultiSource Information.
I1-[OntoSpace] Ontologies for Spatial Communication John Bateman, Kerstin Fischer, Reinhard Moratz Scott Farrar, Thora Tenbrink.
The GLAIR Architecture for Cognitive Robotics Stuart C. Shapiro Department of Computer Science & Engineering and Center for Cognitive Science.
The GLAIR Cognitive Architecture Stuart C. Shapiro and Jonathan P. Bona Department of Computer Science & Engineering Center for Cognitive Science.
The GLAIR Architecture for Cognitive Robots Stuart C. Shapiro Department of Computer Science & Engineering and Center for Cognitive Science.
Knowledge Representation for Self-Aware Computer Systems Stuart C. Shapiro Department of Computer Science and Engineering, and Center for Cognitive.
S.C. Shapiro Development of a Cognitive Agent Stuart C. Shapiro Department of Computer Science and Engineering and Center for Cognitive Science.
S.C. Shapiro Endowing Agents with a Personal Sense of Time Haythem O. Ismail & Stuart C. Shapiro Department of Computer Science and Engineering.
S.C. Shapiro Knowledge Representation for Natural Language Competence Stuart C. Shapiro Department of Computer Science and Engineering and.
Cassie as a Self-Aware SNePS/GLAIR Agent Stuart C. Shapiro Department of Computer Science and Engineering, and Center for Cognitive Science.
Research in Knowledge Representation, Reasoning, and Acting Stuart C. Shapiro Professor, CSE Affiliated Professor, Linguistics, Philosophy.
S.C. Shapiro Knowledge Representation and Reasoning Stuart C. Shapiro Professor, CSE Director, SNePS Research Group Member, Center for Cognitive.
S.C. Shapiro An Intelligent Interface to a GIS Stuart C. Shapiro Professor, CSE Director, SNePS Research Group Member, Center for Cognitive.
Semantics of a Propositional Network Stuart C. Shapiro Department of Computer Science & Engineering Center for MultiSource Information Fusion.
S.C. Shapiro Symbol-Anchoring in Cassie Stuart C. Shapiro and Haythem O. Ismail Department of Computer Science and Engineering and Center for.
Chapter Seven The Network Approach: Mind as a Web.
Knowledge Acquisition by an Intelligent Acting Agent Michael Kandefer and Stuart Shapiro Department of Computer Science and Engineering, Center for Cognitive.
S.C. Shapiro Knowledge Representation and Reasoning Stuart C. Shapiro Professor, CSE Director, SNePS Research Group Member, Center for Cognitive.
S.C. Shapiro Symbol Anchoring in a Grounded Layered Architecture with Integrated Reasoning Stuart C. Shapiro Department of Computer Science.
SNePS 3 for Ontologies Stuart C. Shapiro Department of Computer Science and Engineering, and Center for Cognitive Science University at Buffalo,
S.C. Shapiro The SNePS Approach to Cognitive Robotics Stuart C. Shapiro Department of Computer Science and Engineering and Center for Cognitive.
Research in Knowledge Representation, Reasoning, and Acting Stuart C. Shapiro Professor, CSE Director, Center for Cognitive Science Director,
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering CSCE 580 Artificial Intelligence Ch.2 [P]: Agent Architectures and Hierarchical.
AI: Trends and Directions Stuart C. Shapiro Professor, CSE Affiliated Professor, Linguistics, Philosophy Director, SNePS Research Group ACM.
A Logic of Arbitrary and Indefinite Objects Stuart C. Shapiro Department of Computer Science and Engineering, and Center for Cognitive Science.
Research in Knowledge Representation, Reasoning, and Acting Stuart C. Shapiro Professor, CSE Affiliated Professor, Linguistics, Philosophy.
Intelligent Agents: an Overview. 2 Definitions Rational behavior: to achieve a goal minimizing the cost and maximizing the satisfaction. Rational agent:
S.C. Shapiro An Introduction to SNePS 3 Stuart C. Shapiro Department of Computer Science and Engineering and Center for Cognitive Science State.
Scene Based Reasoning Cognitive Architecture Frank Bergmann, Brian Fenton,
Ontologies Reasoning Components Agents Simulations Belief Update, Planning and the Fluent Calculus Jacques Robin.
Chapter 15: Agents Service-Oriented Computing: Semantics, Processes, Agents – Munindar P. Singh and Michael N. Huhns, Wiley, 2005.
An Architecture for Empathic Agents. Abstract Architecture Planning + Coping Deliberated Actions Agent in the World Body Speech Facial expressions Effectors.
Inference Graphs: A Roadmap Daniel R. Schlegel and Stuart C. Department of Computer Science and Engineering L A – Logic of Arbitrary.
Panel Discussion I: Brainstorm on Language, Embodiment and the Critical minass of Intelligence Moderator: Alexei Samsonovich Panelists: Kenneth De Jong,
NATURAL LANGUAGE UNDERSTANDING FOR SOFT INFORMATION FUSION Stuart C. Shapiro and Daniel R. Schlegel Department of Computer Science and Engineering Center.
Pattern-directed inference systems
1 Knowledge Representation CS 171/CS How to represent reality? Use an ontology (a formal representation of reality) General/abstract domain Specific.
A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture Arno Hartholt (ICT), Thomas Russ (ISI),
The SNePS Research Group Semantic Network Processing System The long-term goal of The SNePS Research Group is the design and construction of a natural-language-using.
1 Viewing Vision-Language Integration as a Double-Grounding case Katerina Pastra Department of Computer Science, Natural Language Processing Group, University.
KNOWLEDGE BASED SYSTEMS
Chapter 9. PlayMate System (1/2) in Cognitive Systems, Henrik Iskov Chritensen et al. Course: Robots Learning from Humans Kwak, Hanock Biointelligence.
Chapter 10. The Explorer System in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans On, Kyoung-Woon Biointelligence Laboratory.
Chapter 8. Situated Dialogue Processing for Human-Robot Interaction Greert-Jan M. Kruijff, Pierre Lison, Trevor Benjamin, Henril Jacobsson, Hendrik Zender,
Feng Zhiyong Tianjin University Fall  An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that.
Spring, 2005 CSE391 – Lecture 1 1 Introduction to Artificial Intelligence Martha Palmer CSE391 Spring, 2005.
Cognitive Architectures and General Intelligent Systems Pay Langley 2006 Presentation : Suwang Jang.
Artificial Intelligence Knowledge Representation.
Definition and Technologies Knowledge Representation.
Artificial Intelligence Logical Agents Chapter 7.
Service-Oriented Computing: Semantics, Processes, Agents
Ontology From Wikipedia, the free encyclopedia
Building an mglair Agent a tutorial
Service-Oriented Computing: Semantics, Processes, Agents
MGLAIR Modal Grounded Layered Architecture with Integrated Reasoning
Logic for Artificial Intelligence
MGLAIR Modal Grounded Layered Architecture with Integrated Reasoning
Service-Oriented Computing: Semantics, Processes, Agents
Presented by Yuqian Jiang 2/27/2019
Presentation transcript:

The GLAIR Cognitive Architecture and Prospects for Consciousness Stuart C. Shapiro Department of Computer Science & Engineering and Center for Cognitive Science State University of New York at Buffalo

Outline  Overview Integration of Acting and Reasoning Symbol Grounding Time CSE 719S. C. Shapiro 2

Cognitive Architecture “A cognitive architecture specifies the underlying infrastructure for an intelligent system[, including] those aspects of a cognitive agent that are constant over time and across different application domains.” [P. Langley, J. E. Laird, S. Rogers, Cognitive architectures: Research issues and challenges, Cognitive Systems Research 10 (2009) ] CSE 719S. C. Shapiro 3

Grounded Layered Architecture with Integrated Reasoning Major Concern: –Knowledge Representation and Reasoning Driving Motivation: –Natural Language Understanding & Generation Additional Concern: –Agents that act Question: –Where do beliefs come from? Partial Answer: –Agent’s being embodied –Agent’s being situated in the world CSE 719 S. C. Shapiro 4

CSE 719 S. C. Shapiro 5 KL PMLa PMLb PMLc SAL Mind Body Independent of lower-body implementation Hearing Vision Motion Speech WORLDWORLD I/P s o c k e t s GLAIR Architecture Dependent on lower-body implementation Proprioception

Sensori-Actuator Layer Sensor and effector controllers CSE 719S. C. Shapiro 6

Perceptuo-Motor Layer PMLa PMLb PMLc CSE 719S. C. Shapiro 7

PMLc Abstracts sensors & effectors Body’s behavioral repertoire CSE 719S. C. Shapiro 8

PMLb Translation & Communication –Between PMLa & PMLc Highest layer that knows body implementation CSE 719S. C. Shapiro 9

PMLa Grounds KL symbols –Perceptual structures –Implementation of primitive actions Registers for Embodiment & Situatedness –Deictic Registers –Modality Registers CSE 719S. C. Shapiro 10

The Knowledge Layer Implemented in SNePS Agent’s Beliefs Representations of conceived of entities Semantic Memory Episodic Memory Quantified & conditional beliefs Plans for non-primitive acts Plans to achieve goals Beliefs re. preconditions & effects of acts Policies: Conditions for performing acts Self-knowledge Meta-knowledge CSE 719 S. C. Shapiro 11

Outline Overview  Integration of Acting and Reasoning Symbol Grounding Time CSE 719S. C. Shapiro 12

SNePS A KRR system Every non-atomic expression is simultaneously –An expression of SNePS logic –An assertional frame –A propositional graph Every SNePS expression is a term –Denoting a mental entity CSE 719S. C. Shapiro 13

Ontology of Mental Entities Entity –Proposition Agent can believe it or its negation Includes quantified & conditional beliefs –Act Agent can perform it –Policy Condition-act rule agent can adopt –Thing Other entities: individuals, categories, properties, etc. CSE 719S. C. Shapiro 14

Policies Reasoning Acting Forward Reasoning whendo(φ, α) wheneverdo(φ, α) Backward Reasoning ifdo(φ, α) CSE 719S. C. Shapiro 15

Types of Acts I External Acts affect the environment supplied by agent designer Mental Acts affect the knowledge layer believe, disbelieve adopt, unadopt Control Acts sequence, selection, loop, etc. CSE 719 S. C. Shapiro 16

Types of Acts II Primitive Acts Implemented in PMLa Composite Acts Structured by control acts Defined Acts Defined by ActPlan(α, p) belief CSE 719S. C. Shapiro 17

Acting Reasoning Control Acts snif({if(φ 1, α 1 ), …, if(φ n, α n ), [else(δ)]}) sniterate({if(φ 1, α 1 ), …, if(φ n, α n ), [else(δ)]}) withsome(x, φ(x), α(x), [δ]) withall(x, φ(x), α(x), [δ]) CSE 719S. C. Shapiro 18

Goal Talk GoalPlan(φ, p) achieve(φ) CSE 719S. C. Shapiro 19

S. C. Shapiro Behavior Cycle English (Statement, Question, Command) (Current) Set of Beliefs (Updated) Set of Beliefs Actions(New Belief) English sentence expressing new belief answering question reporting actions Answer NL Analysis NL Generation Reasoning Clarification Dialogue Looking in World Reasoning CSE

Outline Overview Integration of Acting and Reasoning  Symbol Grounding Time CSE 719S. C. Shapiro 21

S. C. Shapiro FEVAHR/Cassie in the Lab CSE

S. C. Shapiro Entities, Terms, Symbols, Objects Agent’s mental entity: a person named Stu SNePS term: b4 Object in world: 23 BICA 2009

S. C. Shapiro Alignment Mind (KL) Body (PML/SAL) World KL term PML structure Object/PhenomenonAction CSE 71924

World Objects to Feature Tuples <Height, Width, Texture,.. > WorldPML/SAL 25 S. C. Shapiro CSE 719

Feature Tuples to KL Terms <Height, Width, Texture,.. > PML/SALKL ProperName(b4, Stu) Alignment CSE S. C. Shapiro

Incomplete PML-Descriptions <Height, nil,.. > PML/SALKL Height(b4, b12) CSE S. C. Shapiro

Unifying PML-Descriptions PML/SAL KL b20 b30 b31 b6 Isa Prop 28 CSE 719S. C. Shapiro

Deictic Registers For being situated in the world PML registers hold KL terms I term denoting agent YOU term denoting dialogue partner NOW term denoting current time CSE 719S. C. Shapiro 29

Modality Registers For privileged first-person knowledge of what agent is doing Register for each modality holds KL term denoting act modality is engaged in CSE 719S. C. Shapiro 30

S. C. Shapiro Acting 1 CSE

S. C. Shapiro Acting 2 I found a red robot. I am looking at a red robot. Follow a red robot. CSE

S. C. Shapiro Acting 3 I went to a red robot. I am near a red robot. I am following a red robot. I found a red robot. I am looking at a red robot. Follow a red robot. CSE

S. C. Shapiro Use of Indexicals 1 Come here. I found you. I am looking at you. CSE

S. C. Shapiro Come here. I came to you, Stu. I am near you. Use of Indexicals 2 I found you. I am looking at you. CSE

S. C. Shapiro Who am I? Your name is ‘Stu’ and you are a person. Who have you talked to? I am talking to you. Talk to Bill. I am talking to you, Bill. Come here. Use of Indexicals 3 CSE

S. C. Shapiro Come here. I found you. I am looking at you. Use of Indexicals 4 CSE 71937

S. C. Shapiro Come here. I came to you. I am near you. I found you. I am looking at you. Use of Indexicals 5 CSE

S. C. Shapiro Who am I? I talked to Stu and I am talking to you. Your name is ‘Bill’ and you are a person. Who are you? I am the FEVAHR and my name is ‘Cassie’. Who have you talked to? Use of Indexicals 6 CSE

PML/SAL KL b20 b30 b6 Isa Prop 40 CSE 719S. C. Shapiro m2 Find a green robot. (find ) cassie m75 m76 robbie VISION Language-Mind-World-Mind WORLD

Outline Overview Integration of Acting and Reasoning Symbol Grounding  Time CSE 719S. C. Shapiro 41

B6 Representation of Time find lex action object B1 ! agent act event time NOW !! beforeafterbeforeafter ????????????? I CSE S. C. Shapiro

Building Episodic Memory CSE 719 S. C. Shapiro 43 KL PML e1 I a1 b1b1 ! t1e2 a2 ! t2 ! NOW COUNT n hom 0 q ! before after event time act agent duration ACT

Performing a Punctual Act t1 t3! beforeafter NOW CSE S. C. Shapiro t2! beforeafter ! time event

Performing a Durative Act t1 NOW t3 ! supint subint CSE S. C. Shapiro NOW ! beforeafter t2 ! time event

Aligning NOW using MTF NOW Semi-lattice of times, all of which contain *NOW, any of which could be meant by “now” Finite---only conceptualized times of conceptualized states Maximal Temporal Frame based on *NOW KL PML CSE S. C. Shapiro

Moving NOW with MTF NOW KL PML Moves when Cassie acts, newly observes a state, or is informed of a new state. Always includes times of states in modality registers. CSE S. C. Shapiro

CSE 719S. C. Shapiro 48 Collaborators Past and present members of SNeRG: The SNePS Research Group