Re: Shanahan: Robotics and Common Sense

From: Cove Stuart (smc198@ecs.soton.ac.uk)
Date: Tue May 29 2001 - 14:32:38 BST


Cove Stuart on Sloss Finn

RE: Shanahan: Robotics and Common Sense

>Sloss:
>By utilising the formal logic described in this paper, any new objects that
>are encountered are instantly incorporated into the robot's description
>of the world, therefore it can cope with new objects or being immersed
>into a strange new environment. Initially the robot will think it can
>move anywhere because the initial map is empty, but as it bumps into
>objects it will correct its choices as to where to move next, eventually
>being able to avoid collisions. In terms of AI this feature is of great
>importance for robots that are required to interact with our everyday
>world. Obviously the scale of this project is much smaller, but the same
>ideals still hold. Given the necessary sensors and actuators a robot
>could be made to interact for example: A kitchen robot could be told to
>make a coffee, in the case of a standard robot, if the coffee cup is not
>in its predefined location, the robot could fail at the task. Using the
>logic framework described in Shanahan's paper, the robot would be able
>to aquire the new location of the cup and successfully interact.

Cove:

This does appear to be a solution to some of the locality problems
presented by the frame problem. I wonder if a scaled-up version of the
logic, used in a more TT3 type robot, could get any closer to human
abilities at determining information about the surrounding environment.
Obviously humans don't bump into things before realising they are in
the way, and this would be useless to any robot working in a china
shop. From what I understand, any new locality the robot is faced
with, must have its map constructed from scratch, clearly humans use
semantic knowledge about previous surroundings to construct a model of
the new situation more efficiently, this method may not be able cope
with real time human performance, and the semantic understanding
suggests that although every attempt has been made to solve the frame
problem, symbol grounding in a broad sense is not.



This archive was generated by hypermail 2.1.4 : Tue Sep 24 2002 - 18:37:31 BST