 | | RE: Antenna Bumpers/Insects —Gary Kacmarcik (Exchange)
| | | | insects can indeed move backwards, although perhaps not in the way you're imagining. --- more info than you probably care to know about roaches --- most hexapod robots hard-code a "tripod gait" on their robots, where the first (prothoracic) and last (...) (26 years ago, 4-Dec-98, to lugnet.robotics)
| | | | | | | | | | Re: Antenna Bumpers/Insects —stephen p spackman
| | | | | Hey, I vote that gait discussions are definitely *on* topic - a lot of my thought about LEGO robotics in the past has related to mobility! But on a different tangent - what would be needed to run a neural net on an RCX? What kind of processing model (...) (26 years ago, 5-Dec-98, to lugnet.robotics)
| | | | | | | | | | | | RE: Antenna Bumpers/Insects —Carl G. Schaefer, Jr.
| | | | | <SNIP> (...) Because of the limited on-board computational resources, IMHO you would have to use offline simulation to train the neural network and then embed the trained net, provided of course, that the resulting weight and bias matrices and the (...) (26 years ago, 5-Dec-98, to lugnet.robotics)
| | | | | | |
