Mae’s Status Report for 12/10/22

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 rid of angle calculation and the second inference if the bottle is already centered initially. We also fixed bugs in the pipeline, such as sometimes we would be stuck in angle calculation or stuck in a loop where the robot would keep adjusting the angle. One major issue has been our Realsense depth readings, as the readings are very inaccurate and often give us 0.0m distances. Due to this, we have not been able to accurately track obstacles and avoid them. We have tried changing the settings of the Realsense, but did not have luck. Tomorrow, we will do our best to test our second test case, but I am greatly concerned about whether we will be able to achieve this metric before the demo on Monday.