The grounding problem is, generally speaking, the problem of how to embed an artificial agent into its environment such that its behaviour, as well as the mechanisms, representations, etc. underlying it, can be intrinsic and meaningful to the agent itself, rather than dependent on an external designer or observer. This paper briefly reviews Searle's and Harnad's analyses of the grounding problem, and then evaluates cognitivist and enactive approaches to overcoming it. It is argued that, although these two categories of approaches differ in their nature and the problems they have to face, both, so far, fall short of solving the grounding problem for similar reasons. Further it is concluded that the reason the problem is still somewhat underestimated lies in the fact that modern situated and embodied AI, despite its emphasis of agent-environment interaction, still fails to fully acknowledge the historically rooted integrated nature of living organisms and their environmental embedding.
|
2141
|
A robust layered control system for a mobile robot
– Brooks
- 1986
|
|
967
|
Intelligence without representation
– Brooks
- 1991
|
|
653
|
Intelligence without reason
– Brooks
- 1991
|
|
501
|
Pengi: an implementation of a theory of activity
– Agre, Chapman
- 1987
|
|
478
|
The symbol grounding problem
– Harnad
- 1990
|
|
394
|
Connectionism and cognitive architecture: A critical analysis
– Fodor, Pylyshyn
- 1988
|
|
331
|
The modularity of mind
– Fodor
- 1983
|
|
286
|
Being there: Putting brain body and world together again
– Clark
- 1997
|
|
239
|
Understanding intelligence
– Pfeifer, Scheier
- 1999
|
|
215
|
Minds, brains and programs
– Searle
- 1980
|
|
198
|
A robot that walks; emergent behaviors from a carefully evolved network
– Brooks
- 1989
|
|
177
|
The embodied mind : Cognitive science and human experience
– Varela, T-E, et al.
- 1991
|
|
155
|
The Tree of Knowledge: The Biological Roots of Human Understanding
– Maturana, Varela
- 1987
|
|
150
|
Computer science as empirical inquiry: symbols and search. The Tenth Turing Lecture. First published in Communications of the Association for Computing Machinery 19
– Newell, Simon
- 1976
|
|
135
|
A dynamical systems perspective on agent-environment interaction
– Beer
- 1995
|
|
122
|
Physical symbol systems
– Newell
- 1980
|
|
104
|
Automatic definition of modular neural networks
– Gruau
- 1995
|
|
86
|
Co-Evolution of Pursuit and Evasion II: Simulation Methods and Results
– Cliff, Miller
- 1996
|
|
75
|
Toward the evolution of dynamical neural networks for minimally cognitive behavior
– Beer
- 1996
|
|
64
|
Mind as Motion: Explorations in the Dynamics of Cognition
– Port, Gelder
- 1995
|
|
56
|
What might cognition be, if not computation
– Gelder
- 1995
|
|
52
|
Methodological solipsism considered as a research strategy in cognitive science
– Fodor
- 1980
|
|
50
|
The brain has a body: Adaptive behavior emerges from interactions of nervous system, body and environment. Trends Neurosci
– Chiel, Beer
- 1997
|
|
44
|
Evolving robot morphology
– Lund, Hallam, et al.
- 1997
|
|
43
|
Using emergent modularity to develop control systems for mobile robots", Adaptive Behavior 5
– Nolfi
- 1997
|
|
42
|
Computer evolution of buildable objects
– Funes, Pollack
- 1997
|
|
33
|
Cognition - Perspectives from autonomous agents
– Pfeifer
- 1995
|
|
32
|
The Acquisition of Lexical Semantics for Spatial Terms: A Connectionist Model of Perceptual Categorization
– Regier
- 1992
|
|
30
|
Evolution of neural control structures: Some experiments on mobile robots. Robotics and Autonomous Systems 16
– Floreano, Mondada
- 1995
|
|
28
|
The Animat Path to AI. In From Animals to Animats
– Wilson
- 1991
|
|
24
|
The integrative action of the nervous system
– Sherrington
- 1906
|
|
23
|
Minds, Machines and Searle
– Harnad
- 1989
|
|
22
|
Elephants don't play chess. Robotics and Autonomous Systems 6
– Brooks
- 1986
|
|
22
|
Grounding meaning in perception
– Cottrell, Bartell, et al.
|
|
18
|
A consideration of the biological and psychological foundations of autonomous robotics
– Sharkey, Ziemke
- 1998
|
|
16
|
Subsymbolic computation and the chinese room
– Chalmers
- 1992
|
|
16
|
The Neural Mind and the Robot
– Sharkey, Heemskerk
- 1997
|
|
15
|
Three Horns of the Representational Trilemma
– Sharkey, Jackson
- 1994
|
|
13
|
Evolving nontrivial behavior in autonomous robots: Adaptation is more powerful than decomposition and integration,” in Evolutionary Robotics: From Intelligent Robots to Artificial
– Nolfi
- 1997
|
|
12
|
Connectionism, symbol grounding, and autonomous agents
– Dorffner, Prem
- 1993
|
|
12
|
Representations: Philosophical Essays on the Foundations of Cognitive Science
– Fodor
- 1981
|
|
12
|
Symbol grounding is an empirical problem: Neural nets are just a candidate component
– Harnad
- 1993
|
|
12
|
Forced movements, tropisms, and animal conduct
– Loeb
- 1918
|
|
12
|
Towards Adaptive Behaviour System Integration using Connectionist Infinite State Automata
– Ziemke
- 1996
|
|
11
|
The representational relation between environmental structures and neural systems: Autonomy and environmental dependency in neural knowledge representation
– Peschl
- 1997
|
|
11
|
Neural networks for coordination and control: The portability of experiential representations. Robotics and Autonomous Systems
– Sharkey
- 1997
|
|
11
|
The dynamical hypothesis
– Gelder
- 1998
|
|
10
|
Toward a Noncomputational Cognitive Neuroscience
– Globus
- 1992
|
|
10
|
Grounding symbolic capacity in robotic capacity
– Harnad
- 1995
|
|
10
|
Towards Adaptive Perception in Autonomous Robots using Second-Order Recurrent Networks
– Ziemke
- 1996
|
|
