Blog
Buoy Testing
Jul 15, 2013
Comments are off
Today we tried out some new methods of bumping the LED buoys. Reusing our manipulator task actuator we were able to reliably cycle through the colors.
Continue Reading →
Manipulation Task
Jul 11, 2013
Comments are off
Today we were able to successfully turn the steering wheel of the manipulation task. With one week until the competition, we are getting excited to see all the other teams in San Diego.
Continue Reading →
Camera Calibration
Jul 09, 2013
Comments are off
Today, we calibrated our cameras with our new calibration grid. After the new calibration, we noticed significant improvement in object depth estimation.
Continue Reading →
SubjuGator 2013 Preview
Jun 30, 2013
Comments are off
Check out our introduction video for the 16th AUVSI/ONR Robosub competition.
Continue Reading →
New tether
Jun 20, 2013
Comments are off
Today we received a 1000′ gel filled, shielded Ethernet cable. After measuring out 250′ and crimping both sides we now have a new tether! Our last tether was starting to fail and was increasing our packet loss percentage.
Continue Reading →
Pool Testing June 8, 2013
Jun 08, 2013
Comments are off
Today we spent most of our time refining our vision algorithms. SubjuGator can consistently find pipes on the pool floor. The sub was also able to recognize the “pizza box”. Next step, install the pneumatic claw!
Continue Reading →
Pool Testing June 1, 2013
Jun 05, 2013
Comments are off
Today we worked on our controller and particle filter again. We used buoys to test our vision system. The video below shows the sub looking for a buoy shaped object that is also red. When the sub locates and bumps the buoy, it surfaces and proceeds toward its next objective: a shooting target from last year’s competition.
Continue Reading →
Pool testing April 27, 2013
Apr 29, 2013
Comments are off
Saturday testing went well. We continued to improve on the particle filter by attempting several of last year’s challenges. Our attempts of the buoy bumping and pipe to shooter were consistently successful.
Continue Reading →
Particle-filter based vision
Apr 12, 2013
Comments are off
This year, we’re trying to approach vision a different way. In the past, we’ve done image segmentation by using various thresholding algorithms and then classified the resulting contours based on size and shape. Our experimental software instead makes numerous guesses of the pose of the object being searched for, and then ranks them by how likely they are to be true, given the images received from the camera (Particle Filtering). The output quickly converges to the true 3D pose of th
Continue Reading →
Machine Intelligence Laboratory | University of Florida