CABot 1
- CABot 1 is the version of the project finished in July 2007.
- The agent is in a very simple crystal space game.
- The agent itself does almost all of its processing in fLIF
neurons.
- It can execute a few commands given by the user, sees the room (1
pyramid or stalactite), and uses a spreading activation net for
plans and goals, which are set by the user.
- To run the agent you'll need the
simple2 crystal space game that we developed.
- You will also need the CABot1 agent.
- There are a range of ways to
run CABot.
- We are in the process of producing a Technical Report of
CABot 1.
- It is by no means perfect, but shows a range of sophisticated
behaviours.
- The parser is pretty solid on the 21 sentences it is designed
for. Nets vary, but a random net usually gets around 98% of
parses correct as gauged by semantic frames.
- Vision is more rudimentary, but largely succeeds in
recognizing stalactites and pyramids.
