Architectures for functional imagination

Authors:
Hugo Gravato Marques;Owen Holland
Affiliations:
Department of Computer Science, University of Essex, Colchester CO4 3SQ, UK;Department of Computer Science, University of Essex, Colchester CO4 3SQ, UK
Venue:
Neurocomputing
Year:
2009

Citing 8
Cited 2

Integrated architecture for learning, planning, and reacting based on approximating dynamic programming

Proceedings of the seventh international conference (1990) on Machine learning
Intelligence without representation

Artificial Intelligence
Artificial Neuroconsciousness an Update

IWANN '96 Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation
Imagination and Situated Cognition

Imagination and Situated Cognition
Activation of Cortical and Cerebellar Motor Areas during Executed and Imagined Hand Movements: An fMRI Study

Journal of Cognitive Neuroscience
Perception through visuomotor anticipation in a mobile robot

Neural Networks
Internal simulation of perception: a minimal neuro-robotic model

Neurocomputing
Use your illusion: sensorimotor self-simulation allows complex agents to plan with incomplete self-knowledge

SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior

Neural Pathways of Embodied Simulation

Anticipatory Behavior in Adaptive Learning Systems
Dreaming of electric sheep? Exploring the functions of dream-like mechanisms in the development of mental imagery simulations

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

Imagination can be defined broadly as the manipulation of information that is not directly available to an agent's sensors. However, the topic of imagination raises representational, physiological, and phenomenological issues that cannot be tackled easily without using the body as a reference point. Within this framework, we define functional imagination as the mechanism that allows an embodied agent to simulate its own actions and their sensory consequences internally, and to extract behavioural benefits from doing so. In this paper, we present five necessary and sufficient requirements for the implementation of functional imagination, as well as a minimal architecture that meets all these criteria. We also present a taxonomy for categorising possible architectures according to their main attributes. Finally, we describe experiments with some simple architectures designed using these principles and implemented on simulated and real robots, including an extremely complex anthropomimetic humanoid.