Team Status Report for 12/10/22

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 being fast enough–most of the time one reading will be over 1m and the next reading will immediately drop to 0m. This inaccuracy is a huge problem for obstacle avoidance, as it is crucial to know how far away an obstacle is to know when to stop. We have tried many things such as changing the Realsense settings and using different openCV tracking algorithms to no avail. Tomorrow we will do a final run of our first test case and attempt our second test case. We are concerned about the second test case with obstacles, but will do our best to have numbers before the final demo.