Artificial Cognitive Systems: David Vernon

Artificial Cognitive Systems
David Vernon
www.vernon.eu
Artificial Cognitive Systems 1 David Vernon

Artificial Cognitive Systems www.vernon.eu
2 David Vernon
www.vernon.eu/wiki/Artificial_Cognitive_Systems
Supporting Texts
David Vernon, Artificial Cognitive Systems, MIT Press, 2014.

Goals of the Course
• Comprehensive cross-section of the main elements of artificial cognitive systems
• Highlight links with artificial intelligence, developmental psychology, and cognitive

neuroscience
• Discuss how to build systems that can act on their own to achieve goals: perceiving their
environment, anticipating the need to act, learning from experience, and adapting to
changing circumstances

Learning Objectives
After completing this course, you should be able to
– Identify the key attributes of a cognitive system
– Explain the main characteristics of cognitivist, emergent, and hybrid cognitive science
– Compare cognitive architectures using several criteria
– Explain how a specific hybrid cognitive architecture works and show how it can be used to
allow a robot to reason about its environment and achieve goals set by a user
– Explain the implications of computational functionalism and its relationship to the embodied
cognition thesis
– Distinguish between learning and development and explain how these processes are facilitated
by different forms of memory and knowledge

Social
Cognition
Memory &
Prospection
Development
& Learning
Knowledge & Cognitive

Representation Architectures
Paradigms
of Cognitive
Science
The Nature of
Autonomy Cognition
Embodiment

(Almost) No Equations or Algorithms!

Describe with equations

The Nature of
Cognition

Motivation for Studying
Cognitive Systems

Industrial Robots

Cognitive Robots
c.f. Maria Petrou’s Ironing challenge; see http://www.commsp.ee.ic.ac.uk/~mcpetrou/iron.html

Motivation
• Controlled environment
We know what to expect,

and can program the robot
to do what we want
• Complex environment
We don’t know what to expect,

and the robot has to be
flexible and adaptable
Uncertainty, incomplete knowledge, change
c.f. Maria Petrou’s Ironing challenge; see http://www.commsp.ee.ic.ac.uk/~mcpetrou/iron.html

https://www.theguardian.com/us-news/2018/oct/08/robot-farm-iron-ox-california
Assisting in Psychotherapy with ASD Children
(Simple Perspective Taking in Interaction Tasks)

Funded by The European Commission, Project IST-004370, RobotCub,
under Strategic Objective 2.3.2.4: Cognitive Systems
Head: 6 DoF
Arm 7 DoF
Hand 9 DoF
Waist 3 DoF
Leg 6 DoF

OpenEASE CeBIT 2016
http://www.open-ease.org/
Introduction to Cognitive Robotics 34 34 David Vernon
David Vernon
LEA
Robot Care Systems
Motivation
Two complementary reasons for wanting a cognitive system
1. Cognition allows the robot to
• Work independently in challenging environments
• Adapt to changes
• Anticipate events in preparing its actions

Motivation
Two complementary reasons for wanting a cognitive system
2. Cognition facilitates interaction with people
Works two ways:
1. It facilitates interaction by the human
2. It provides the robot with the ability to infer the goals and intentions of the human
(and thereby interact with the human in a safe and helpful manner)

Industrial Priorities for Cognitive Robotics
Survey of industrial developers to determine what they and

their customers require from a cognitive robot
Cast as a series of eleven functional abilities
D. Vernon and M. Vincze, "Industrial Priorities for Cognitive Robotics", Proceedings of the European
Society for Cognitive Systems Meeting, EUCognition 2016, Vienna, 8-9 December 2016.

Safe, reliable, and
transparent operation
?

High-level instruction and
context-aware task
execution
?

Knowledge Acquisition
and Generalization
?

Adaptive Planning
?

Personalized interaction ?

Self-Assessment
?

Learning from
Demonstration
https://sketchucation.com/foru https://www.istockphoto.com/d
ms/viewtopic.php?f=15&t=585 e/fotos/man-
87 vacuuming?sort=mostpopular&
mediatype=photography&phras
e=man%20vacuuming

Evaluating the
Safety of Actions ?

Development and
Self-Optimization ?

Knowledge Transfer
??

Communicating
Intentions and
Collaborative Action
?

Industry 4.0 requires automation solutions to be
highly cognitive and highly autonomous
It requires enhanced collaboration between humans and machines,
including next generation robots that work hand-in-hand and safely with
humans [Deloitte 2014]
https://www.accenture.com/us-en/digital-industry-index

https://ieeexplore.ieee.org/document/8931075
http://vernon.eu/publications/19_Vernon_RAM.pdf

Reading
D. Vernon, Artificial Cognitive Systems, MIT Press, 2014; Chapter 1.
D. Vernon and M. Vincze, "Industrial Priorities for Cognitive Robotics", Proceedings of the
European Society for Cognitive Systems Meeting, EUCognition 2016, Vienna, 8-9
December, R. Chrisley. V. C. Müller, Y. Sandamirskaya. M. Vincze (eds.), CEUR-WS Vol-
1855, ISSN 1613-0073, pp. 42-43. 2016.

Artificial Cognitive Systems: David Vernon

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Artificial Cognitive Systems: David Vernon

Uploaded by

Copyright:

Available Formats

Artificial Cognitive Systems

Artificial Cognitive Systems 1 David Vernon

David Vernon, Artificial Cognitive Systems, MIT Press, 2014.

Artificial Cognitive Systems 4 David Vernon

• Comprehensive cross-section of the main elements of artificial cognitive systems

• Highlight links with artificial intelligence, developmental psychology, and cognitive

Artificial Cognitive Systems 12 David Vernon

After completing this course, you should be able to

– Identify the key attributes of a cognitive system

– Compare cognitive architectures using several criteria

Artificial Cognitive Systems 18 David Vernon

Knowledge & Cognitive

Artificial Cognitive Systems 19 David Vernon

Artificial Cognitive Systems 20 David Vernon

Artificial Cognitive Systems 21 David Vernon

Artificial Cognitive Systems 22 David Vernon

Artificial Cognitive Systems 23 David Vernon

Artificial Cognitive Systems 24 David Vernon

c.f. Maria Petrou’s Ironing challenge; see http://www.commsp.ee.ic.ac.uk/~mcpetrou/iron.html

We know what to expect,

We don’t know what to expect,

Uncertainty, incomplete knowledge, change

c.f. Maria Petrou’s Ironing challenge; see http://www.commsp.ee.ic.ac.uk/~mcpetrou/iron.html

Artificial Cognitive Systems 29 David Vernon

Artificial Cognitive Systems 32 David Vernon

Two complementary reasons for wanting a cognitive system

1. Cognition allows the robot to

• Work independently in challenging environments

• Anticipate events in preparing its actions

Artificial Cognitive Systems 36 David Vernon

Two complementary reasons for wanting a cognitive system

2. Cognition facilitates interaction with people

Works two ways:

1. It facilitates interaction by the human

Artificial Cognitive Systems 37 David Vernon

Survey of industrial developers to determine what they and

Cast as a series of eleven functional abilities

Artificial Cognitive Systems 38 David Vernon

Artificial Cognitive Systems 39 David Vernon

Artificial Cognitive Systems 40 David Vernon

Artificial Cognitive Systems 41 David Vernon

Artificial Cognitive Systems 42 David Vernon

Artificial Cognitive Systems 43 David Vernon

Artificial Cognitive Systems 44 David Vernon

Artificial Cognitive Systems 45 David Vernon

Artificial Cognitive Systems 46 David Vernon

Artificial Cognitive Systems 47 David Vernon

Artificial Cognitive Systems 48 David Vernon

Artificial Cognitive Systems 49 David Vernon

It requires enhanced collaboration between humans and machines,

Artificial Cognitive Systems 50 David Vernon

Artificial Cognitive Systems 51 David Vernon

Artificial Cognitive Systems 52 David Vernon

You might also like