Thursday, March 4, 2010

From Geek to Sleek: Integrating Task Learning Tools to Support End Users in Real-World Applications

Written by: Aaron Spaulding, Jim Blythe, Will Haines, Melinda Gervasio

The authors created a integrated task learning system (ITL) that learns a task by watching the user. This is accomplished by using a macro reader to follow the actions, programming by demonstration (PBD), and a good UI so people will use it. The UI was key because people initially saw the ITL as "a bunch of geek stuff." Because people are unwilling to show a program how to do stuff more than once the ITL uses a very strong learning database for background knowledge and understanding.

This is extremely important because it can take care of menial computer tasks for companies and free up another minimum wage job. The program seems like it would be hard to use, similar to computer vision training where it takes a lot of work for a machine to know what it's looking for. Future work would be to expand on what functions are available to the users and refined learning capability for the ITL.

2 comments:

  1. The learning part is definitely going to be key. If it misses a step or assumes the wrong thing, it's usually a pain to try to edit in the correct steps.

    ReplyDelete
  2. It seems difficult, but for some jobs automation is really important. One thing I thought about is this could be better than a straight up programatic automation because security can be enforced by the ITL system and any vulnerabilities can be fixed for all scripts simultaneously.

    ReplyDelete