• Navigation
  • Home
  • About
  • FAQ
  • Development
  • Project Status
  • Topic Categories
  • Recent Changes
• Community
  • The Team
  • Donate
  • Get Involved
  • Events
• Toolbox
  • What links here
  • Related changes
  • Upload file
  • Special pages
• Personal tools
  • Log in / create account

Embodiment

From OpenCog

Embodiment is a system based on OpenCog concepts for controlling a real or virtual intelligent agent's body. The Embodiment system uses a Proxy to connect to a virtual world where the agent's body lives (or directly to a robot living in the real world). The proxy provides an interface for collecting perceptions from this world and commanding the agent's body through action plans to be executed within the world.

Contents 1 Architecture related pages 2 Learning Server 3 Components and Modules 4 Code organization 5 Feelings and Predicates 6 Functionalities and features 7 System usage and tests 8 Embodiment Proxies 9 Miscellaneous 9.1 Combo-related pages 9.2 Behavior-related pages 9.3 Occams Razor 9.4 Ben's notes and ideas 9.5 Language Comprehension 9.6 Others

Architecture related pages

• Embodiment Architecture Description
• Design for Embodiment Communications Layer
• Embodiment Spawner Design
• OperationalPetController Design

Learning Server

The Learning Server (LS) provides several mechanisms to make the agent learn sequences of actions.

Components and Modules

• PAI (Perception & Action Interface)
• Rule Engine: Agent's Rule Based System description
• Pedavese parser: A module responsible for processing NL commands
• Predavese handlers: Converting NL to agent commands
• Some descriptions about Space Server
• Pet Physiological Model (original design)

Code organization

• Code Organization notes

Feelings and Predicates

• Some specifications about Feelings
• Details on implementation of Predicates

Functionalities and features

• Desired Functionalities for Embodiment
• Agent's personalities definitions
• Learning Functionalities (both implemented and desired)
• Status of 3D Modeling and Animations for Embodiment

System usage and tests

• Manual System Tests
• Automated System Tests
• Robustness Tests

Embodiment Proxies

• MV-Proxy
  • This is the Proxy for Multiverse (http://www.multiverse.net). You can find the related codebase at lp:~opencog-dev/opencog/embodiment_MV-Proxy. There is a README file in the root's directory with instructions on how to build and execute that Proxy within a standalone Multiverse server.
• Rex-Proxy
  • This is the Proxy for RealXtend (http://www.realxtend.org). You can find the related codebase at lp:~opencog-dev/opencog/embodiment_ReX-Proxy. There is a README in the root's directory with instructions on how to build and execute that Proxy within a standalone RealXtend server.
  • ReX-Proxy: Integration issues
• Comparison of some aspects between Multiverse and RealXtend platforms
• Proxy Messages : Description of the messages exchanged between Embodiment and the Proxy.

Miscellaneous

Combo-related pages

• Embodiment Combo
• Status of combo implementation (it's probably out of date)

Behavior-related pages

• Behavior Similarity Algorithm
• Behavior Descriptions (BDs)
• Dogs Behavior In Combo Language
• Retrieving BDs and Exemplars

Occams Razor

• Distorting Occams Razor For Complex Operators
• OccamsRazorCalibration

Ben's notes and ideas

These are pages written by Ben that may still be useful for further work:

• Naturalistic animations
• Background on virtual pets
• Ben's SpaceServer design (as an improvement to the current RudimentarySpaceServer: not sure this still stands or is desirable.

Language Comprehension

• Pipeline
• Relex and frames adaptation
• Anaphora Resolution
• Object's properties considered
• Reference Resolution
• Command Resolution
• NLGen
• Question answering
• Dialog Controller
• Frames to Atoms conversion

Others

• Mike Ross' document about what RelEx is able to handle: this is not the right place to document RelEx bugs -- see RelEx instead.