This week we worked on the final presentation. We also made minor changes to our software pipeline to improve both speed and accuracy. We came up with a major issue with our Realsense depth readings being inaccurate for larger distances, as well as the sampling of the depth readings not Read more…
This week Serena and I made a lot of small adjustments to the pipeline to increase speed and accuracy of the system. Accuracy improvements include putting angle calculation in multitracking. Speed improvements include driving the bot with higher numbers, changing the openCV tracking algorithm to a faster one, and getting Read more…
This week the team put in a lot of effort to integrate our software and hardware into a working system. I wrote the rest of the logic for the software pipeline, including obstacle avoidance and rotation upon not detecting bottles. Serena and I figured out how to command the Arduino Read more…
This week Serena and I worked extensively to get cuda working with Tamal’s help. We tried many things from flashing Jetpack5 on the Xavier to flashing Jetpack 4.6.1 on the Jetson Nano but could not get a working pytorch with cuda available combined with a working pyrealsense2. Our plan for Read more…
This week I used openCV’s object multitracking with our Realsense livestream to verify that it works. Then, I integrated openCV’s multitracking and distance readings into our pipeline. Our pipeline now consists of inference, then angle calculation to center the robot to the bottle, inference again to capture objects in the Read more…
In my attempt to get inference to perform faster, I realized that I am not actually using cuda because torch.cuda.is_available() returns false. I was unable to install a version of Pytorch on the Xavier through the terminal. After talking to Tamal, I realized that getting cuda on the Jetson Xavier Read more…
This week we were very productive and have been preparing for the interim demos. We worked more on robot construction and have finished the frame and ramp with the intake attached to the front. We still haven’t found the perfect motor yet for the intake, but we are very close Read more…
This week we all got together to build the structure on top of the iRobot, forming a box on top of the iRobot including the intake. Since our battery pack for the Jetson came in, I figured out how to ssh into the Jetson and test without the Jetson needing Read more…
This week we focused on the design report and testing. We tested the bottle detection algorithm on the Realsense and found that it is only classifying bottles that are a short distance away, approximately .3 meters. Mae will work to increase this range to 2 meters next week. We also Read more…
This week we primarily focused on the design report. We changed our use case requirement to the robot being able to pick water bottles up within a 1 meter radius, meaning that it should be able to see bottles from 2 meters away. With our testing right now, the bottle Read more…