Progress
We finished the first version of our MVP! We integrated all our systems together for teleop control and docking to the charging point. It was great to see all the components come together. The gesture recognition is still shaky and the home docking system needs to use our mapping system, but we will work on that next.
Software
We experimented with different cameras and are working on pipelines for data collection to train ML models to recognize gestures from keypoints. In addition, the sockets we used for our webserver are unstable, so we did work to make sure that crashes were greatly reduced.
Hardware
It was good to see the hardware components coming together. We were able to control Roomba via headless RPi which was our MVP. Additionally, we began building the mapping algorithm for the robot. It would require a decent amount of testing and fixing, but we hope to finish it by spring break. 2D mapping is essential for the robot’s additional tasks, so we have to make sure the algorithm works correctly before starting to use the generated map.
Deliverables next week
Still a few fixes to finish our MVP and we want to start using a 2D mapping system from the Roomba.