Imagery in cognitive architecture: Representation and control at multiple levels of abstraction

@article{Wintermute2012ImageryIC,
  title={Imagery in cognitive architecture: Representation and control at multiple levels of abstraction},
  author={Samuel Wintermute},
  journal={Cognitive Systems Research},
  year={2012},
  volume={19},
  pages={1-29}
}
Prospection in Cognition: The Case for Joint Episodic-Procedural Memory in Cognitive Robotics
TLDR
It is argued that such a representation framework has several advantages for cognitive robotics, and by virtue of its associative nature, joint episodic-procedural memory allows the internal simulation to be conditioned by current context, semantic memory, and the agent's value system.
Multiple Representations in Cognitive Architectures
TLDR
It is argued that a SMM must incorporate (a) multiple representational formats and (b) meta-cognitive processes that operate on them and current approaches to extend cognitive architectures with visual-spatial representations are described.
Dreaming of electric sheep? Exploring the functions of dream-like mechanisms in the development of mental imagery simulations
TLDR
An experimental set-up based on a simple simulated robot is developed to test whether such dream-like mechanisms can be used to instruct research into the development of simulations and mental imagery-like abilities and initial results in favour of the hypothesis are presented.
Modeling visuospatial reasoning
  • S. K. Reed
  • Computer Science
    Spatial Cogn. Comput.
  • 2019
ABSTRACT I apply my proposed modification of Soar/Spatial/Visual System and Kosslyn’s (1983) computational operations on images to problems within a 2 × 2 taxonomy that classifies research according
ReaCog, a Minimal Cognitive Controller Based on Recruitment of Reactive Systems
TLDR
This work proposes an artificial neural network, termed reaCog, that is able to deal with a specific domain of behavior (six-legged-walking) and shows how a minor expansion of this system enables the system to plan ahead and deploy existing behavioral elements in novel contexts in order to solve current problems.
Human Reasoning Module
A Review of 40 Years of Cognitive Architecture Research: Focus on Perception, Attention, Learning and Applications
TLDR
A broad overview of the last 40 years of research on cognitive architectures, which confirms that the hybrid approach to cognitive modeling already dominates the field and will likely continue to do so in the future.
Progress in building a cognitive vision system
TLDR
The research hypothesis of this work is that the movements of the robot's cameras are only those that are necessary to build a sufficiently accurate world model for the robot’s current goals, so this approach trades model accuracy for speed.
40 years of cognitive architectures: core cognitive abilities and practical applications
TLDR
This survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.
...
1
2
3
...

References

SHOWING 1-10 OF 79 REFERENCES
Abstraction, Imagery, and Control in Cognitive Architecture
TLDR
This theory addresses two challenges in architecture design that arise due to the diversity and complexity of spatial tasks that an intelligent agent must address, and use of imagery to address these challenges differs from other approaches in AI.
Extending Cognitive Architectures with Spatial and Visual Imagery Mechanisms
TLDR
The evaluation reveals that in tasks where reasoning includes many spatial or visual properties, the combination of amodal and perceptual representations provides an agent with additional functional capability and improves its problem-solving quality.
Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents
TLDR
This paper considers the problem of reinforcement learning in spatial tasks, and shows that this integration with an imagery system broadens the class of perceptual abstraction methods that can be used while preserving the underlying problem.
Computational Imagery
TLDR
A knowledge representation scheme for computational imagery is proposed that incorporates three representations: a long-term memory, descriptive representatlon and two working-memory representations, corresponding to the distinct visual and spatial components of mental imagery.
Extending Cognitive Architectures with Mental Imagery
TLDR
This paper describes the architecture supporting behavior in an environment where perceptual-based thought is inherent to problem solving and shows that imagery provides the agent with additional functional capabilities improving its ability to solve rich spatial and visual problems.
Exploring the Functional Advantages of Spatial and Visual Cognition From an Architectural Perspective
TLDR
A general cognitive architecture that tightly integrates symbolic, spatial, and visual representations is presented, allowing cognition to move freely between these modes, using mental imagery.
Multimodal Cognitive Architecture: Making Perception More Central to Intelligent Behavior
TLDR
The proposal explains the rich multimodal internal experience of embodied agents, and the implementation of a bi-modal version in which a diagrammatic representation component is added to the cognitive state.
Mental imagery: In search of a theory
  • Z. Pylyshyn
  • Psychology, Philosophy
    Behavioral and Brain Sciences
  • 2002
TLDR
It is claimed that when such questions as whether images are depictive or spatial are formulated more clearly, the evidence does not provide support for the picture-theory over a symbol-structure theory of mental imagery, and whether recent neuroscience evidence clarifies the debate over the nature of mental images is considered.
CaMeRa: A Computational Model of Multiple Representations
TLDR
This research aims to clarify the use of multiple representations in problem solving, focusing on their role in visual reasoning, by constructing and testing a model that employs a “Mind’s Eye” representation for pictorial information and uses the diagrammatic and verbal representations to complement one another, thus exploiting the unique advantages of each.
Using concrete, perceptually based representations to avoid the frame problem*
TLDR
It is shown that an alternative approach, performing projections on a concrete, property-based representation, and rederiving the abstract level from it, can greatly alleviate the frame problem in certain types of spatial domains, while maintaining the advantages of planning at an abstract level.
...
1
2
3
4
5
...