Last seen: 2024-05-03 7:15 pm
I haven’t measured this robot’s top speed, but it’s probably in the 0.19 to 0.22 meters/second range, but that does not influence the time it takes to...
Well, my swarm robot has low power 6V gear motors and Pico MCUs that can run between 1.8V and 5.5V. Since these robots are intended to run in a ‘cont...
I don't know, I've got a ways to go yet. The IR sensors on my swarm bot were designed for a much larger arena and to send messages, not this short di...
Yeah, I’m using the same fitness function and neural network that I posted earlier. Move as fast as you can in a straight direction and avoid obstac...
I’m pleased (relieved?!) to report that after 50 generations my little swarm robot evolved into a decent wall follower. It turns counter clockwise an...
LOL Ask away! Tom
@robotbuilder To try this experiment with one of my robots I needed to make a few changes: change out the battery for a constant source of p...
@robotbuilder Looks like you're making progress! Your solution reminds me of the Braitenberg vehicles. He described something similar with excita...
Interesting point. I’ve been reading about Robotic experiments in evolution and learning and your comment reminded me of one where they wanted to ...
It sounds like you have a misconception about how the sigmoid function is used. You won’t find it mentioned in Goldberg’s text. It is used as an act...
Reading that book was a walk down memory lane for me. I graduated from the University of Oregon in the mid 80’s and Pascal was the programming languag...
After reading that paper by Elman I’ve wondered about how the recurrent connections worked in this experiment. Their robot never got stuck in a corne...
Ha, good one I've always used the + as forward and - as backward. Actually the output of the neural network is -0.5 to +0.5, so I use the sign for...