ALVINN Wasn't built in a day

and neither was I

Published on November 2, 2006 By PJ_ In Misc

...since determining the steering direction from the input image merely involves a forward sweep through the network, the system is able to process 10 images per second, and drive at up to 55 mph. This is over five times as fast as any non-connectionist system as driven using comparable hardware (Crisman, 1990; Kluge, 1990).
from Defense and Civilian Applications of the ALVINN Robot Driving System

As I was reading this paper for class, I though to myself, "What good is a car that can drive itself if it can only go 10 miles per hour?" It seemed like a reasonable question. There's certainly not much of a market for automatic cars that can only go 10 miles an hour. But of course I realized immediately that ALVINN wouldn't have been developed if those other, slower systems hadn't been developed first. This kind of thinking, I believe, is a real problem for me sometimes. I see things as failures that I should see as incremental successes. A car that can't drive more than 10mph, instead of a car that can actually follow a road without human intervention. I wonder how many successes I've had in my life that I've dismissed because they were only partial successes, and not fully what I wanted. And how can I recognize when I'm making that same mistake again?

Comments

No one has commented on this article. Be the first!

Welcome Guest! Please take the time to register with us.
There are many great features available to you once you register, including:

Richer content, access to many features that are disabled for guests like commenting on the forums.
Access to a great community, with a massive database of many, many areas of interest.
Access to contests & subscription offers like exclusive emails.
It's simple, and FREE!