Robot Research

The beginning of the thesis that I'm reading:

The major problem of robotics research today is that there is a barrier to entry into
robotics research. Robot system software is complex and a researcher that wishes to
concentrate on one particular problem often needs to learn about details, dependencies
and intricacies of the complete system. This is because a robot system needs several
different modules that need to communicate and execute in parallel.

Today there is not much controlled comparisons of algorithms and solutions for a
given task, which is the standard scientific method of other sciences. There is also very
little sharing between groups and projects, requiring code to be written from scratch
over and over again.

Yup, that's pretty much what I'm picking up from my research. Everybody's grabbed a corner and they're all pulling in different directions, with very little communication about it. To be expected, I'm sure, in a free market situation, but it's frustrating to see. It's particularly irritating when they're all groups working for DARPA.

We totally are not going to be the first ones with really effective military/police-use robots. I mean, c'mon! One of the fairly recent research projects funded by DARPA to assess the viability of various types of robots is a prime example. One of the models they tried? Essentially, a giant rolling beachball. The problem with it, translated out of scientific-ese? It blew away. The most successful model? Was built around a commercially-purchased toy car. Kicker? The parts that they added on didn't really work, but the car did.

Gah!