Homer
Architecture
Philosophy and Methodological Assumptions
Description of the Architecture
Memory-Related Modules
Generic Memory
Episodic Memory
Reflective Processes
Natural Language Modules
Lexipedia
Text Interpreter
Text Generator
Planning Modules
Planner/Reasoner
Dynamic Plan
Plan Interpreter
Agent Properties
Style of Control (Passive Response)
Forward and Backward Chaining
Impasse-Driven Control
Interruptible Processing
Modular Organization
Symbolic World Model
Glass Box Approach
Black Box Approach
Global Representation and Uniform Access to Knowledge
Efficiency of Knowledge Access (Knowlege-Speed Trade-Off)
Heterogeneous Knowledge Representation
Persistent Episodic Knowledge
Meta-knowledge
STRIPS-like Representation
Frame-Like Representations
Reflexive Learning
Behavior
Domain Knowledge
Agent Has a Sense of Time
List of Agent Properties for All Architectures
Capabilities
Minimal Learning
Temporal Planning and Situated Action
Problem Solving
Replanning
Support of Multiple, Simultaneous Goals
Self-Reflection
Navigational Strategies
Natural Language Understanding
Symbolic Perception
Simulated Robotic Tasks
Focused Behavior and Processing
Opportunistic Execution
Common Sense Reasoning
Query Answering and Providing Explanations for Decisions
List of Capabilities for All Architectures
Environmental Considerations
Dynamic Environments
Simulated Environments
Limited Resources
Complete and Incomplete Knowledge
Unpredictability
Multiple Tasks
Supervisors
Other Agents
List of Environmental Considerations for All Architectures
Issues
References
Table of Contents
Current Location: Homer - Top