It is time to locate Connectionist representation theory in the new wave of robotics research. The utility of representations developed in Artificial Neural Networks during learning has been demonstrated in Cognitive Science research since the 1980s. The research reported here puts learned representations to work in a decentered control task, the disembodied arm problem, in which a mobile robot operates an arm fixed to a table to pick up objects. There is no physical linkage between the arm and the robot and so the robot's point of view must be decentered. This is done by developing a modular Artificial Neural Net system in three stages: (i) a Classifier net is trained with laser scan data; (ii) an Arm net is trained for picking up objects; (iii) an Inter net is trained to communicate and coordinate the sensing and acting. The completed system is shown to create new nonsymbolic transformationally invariant representations in order to perform the effective generalisation of decentered viewpoints.
|
2141
|
A robust layered control system for a mobile robot
– Brooks
- 1986
|
|
2138
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
967
|
Intelligence without representation
– Brooks
- 1991
|
|
653
|
Intelligence without reason
– Brooks
- 1991
|
|
417
|
A logical calculus of the ideas immanent in nervous activity
– McCulloch, Pitts
- 1943
|
|
394
|
Connectionism and cognitive architecture: A critical analysis
– Fodor, Pylyshyn
- 1988
|
|
308
|
Recursive distributed representations
– Pollack
- 1990
|
|
294
|
Vehicles: Experiments in synthetic psychology
– Braitenberg
- 1984
|
|
210
|
The Organization of Learning
– GALLISTEL
- 1990
|
|
117
|
The origins of intelligence in children
– Piaget
- 1952
|
|
113
|
Syntactic transformations on distributed representations
– Chalmers
- 1990
|
|
112
|
The origins of intelligence
– Piaget
- 1952
|
|
110
|
Beyond modularity: A developmental perspective on cognitive science
– Karmiloff-Smith
- 1992
|
|
85
|
Compositionality: A connectionist variation on a classical theme
– Gelder
- 1990
|
|
77
|
The child’s conception of space
– Piaget, Inhelder
- 1948
|
|
60
|
Learning recursive distributed representations for holistic computation
– Chrisman
- 1991
|
|
53
|
Connectionism and the problem of systematicity: Why Smolensky’s solution doesn’t work
– Fodor, McLaughlin
- 1990
|
|
44
|
Minimalist mobile robotics: A colony-style architecture for an artificial creature
– Connell
- 1990
|
|
33
|
Exploring the symbolic/subsymbolic continuum: A case study of RAAM
– Blank, Meeden, et al.
- 1992
|
|
30
|
Psychology: The briefer course
– James
- 1892
|
|
26
|
Landmark learning in bees: experiments and models
– Cartwright, Collett
- 1983
|
|
25
|
Rethinking Grounding
– Ziemke
- 1999
|
|
24
|
Connectionist representation techniques
– Sharkey
- 1991
|
|
24
|
The constituent structure of connectionist mental states: a reply to Fodor and Pylyshyn
– Smolensky
- 1987
|
|
23
|
An internal report for connectionists
– Sharkey, Jackson
- 1994
|
|
16
|
The Neural Mind and the Robot
– Sharkey, Heemskerk
- 1997
|
|
16
|
A modular design for connectionist parsing
– Sharkey, Sharkey
- 1992
|
|
15
|
Three Horns of the Representational Trilemma
– Sharkey, Jackson
- 1994
|
|
14
|
On being systematically connectionist
– Gelder, Niklasson
- 1994
|
|
13
|
Do insects have cognitive maps
– WEHNER, MENZEL
- 1990
|
|
12
|
Reactive robotic systems
– Arkin
- 1995
|
|
10
|
Visual spatial memory in a hoverfly
– Collett, Land
- 1975
|
|
9
|
Where am I
– Dennett
- 1978
|
|
7
|
Liberalization of basic S-R concepts: Extensions to conflict behavior, motivation, and social learning.(In S. Koch (Ed.), Psychology: A study of a science
– Miller
- 1959
|
|
6
|
Systematicity and Generalisation in Connectionist Compositional Representations, (forthcoming) In Neural Networks and a new 'AI
– Niklasson
- 1992
|
|
6
|
The Mechanisms of Perception
– Piaget
- 1969
|
|
6
|
Situated Cognition: Empirical Issue, Paradigm Shift or Conceptual Confusion
– Slezak
- 1999
|
|
4
|
In defense of Piaget's theory: A reply to 10 common criticisms
– Machado
- 1996
|
|
3
|
Neural network architectures for the forward kinematics problem in robotics
– Nguyen, Patel, et al.
- 1990
|
|
3
|
Subsuming behaviors in neural network controllers
– Sharkey, Heemskerk, et al.
- 1996
|
|
3
|
Training Artificial Neural Networks for Robot Control
– Sharkey, Heemskerk, et al.
- 1996
|
|
3
|
Emergent cognition
– Sharkey, Sharkey
- 1994
|
|
2
|
A hierarchical model of voluntary movement and its application to robotics
– Kawato, Uno, et al.
- 1987
|
|
2
|
A one-eyed self learning robot manipulator
– Krose, Smagt, et al.
- 1993
|
|
2
|
A neural network based inverse kinematics solution in robotics
– Li, Zeng
- 1993
|
|
2
|
The miracle mind model
– Niklasson, Sharkey
- 1992
|
|
1
|
Multi-layer back-propagation network for learning the forward and inverse kinematics equations
– Arteaga-Bravo
- 1990
|
|
1
|
Subsymbolic inference: Inferring verb meaning
– Baldwin
- 1992
|
|
1
|
Theoretical psychology
– Bergman
- 1953
|
|
1
|
Piaget's theory: a psychological critique
– Brown, Desforges
- 1979
|
|
