Month: March 2019

CAD v4

/sigh

So I redesigned the robot again. and I failed… /sigh

Here’s a quick picture of the CAD model:

You’ll note that I’ve removed the room for the back sensors. It makes the robot smaller, and moves the wheels further towards the back, so the robot lean distinctly forwards (so it doesn’t move like a chicken). This also removes room for the back sensors… but I’m not using them in the code anyway.

A Few pictures of the build:

Okay I thought it turned out looking SUPER CUTE (and reliable). Here’s a full-blown pic of the front view:

Continue reading “CAD v4”

Picking Out Patterns pt.2

Hello!

I’ve got the robot running off of timestamps! I’ll separate this out into steps:

1. run the simulated neural network

Here’s the code and resulting output-display:

W = log(abs(randn(15)));
>> [spk NetParams V] = SimLIFNet(W,'simTime',50,'tstep',1e-2,...
'offsetCurrents',1.1*ones(length(W),1));

2. detect intersections

Continue reading “Picking Out Patterns pt.2”

Picking Out Patterns (pt. 1)

Hello!

The neural-network simulation I’m working with does output an array of spike times for each neuron. Rereading through the reference paper, though, that’s useful only if you can correlate it to a particular input; each input (pattern of stimulation based on sensor values) is correlated to a particular pattern of spiking, which is then translated into the action-command for the robot.

Since I can’t (or haven’t yet figured out how to) ‘stimulate’ the neuronal network I’m working with, I thought it might be a good idea to just choose a random pattern and see if I could write code to pick it out.

Here’s the situation I’ve decided on: neurons in the simulation (I’m now using 12) will spike, and I’ll get an output of all their respective spike times. Then I intervene and pick the three with the most spiking. Tell me at what time all three are spiking together.

Continue reading “Picking Out Patterns (pt. 1)”