Progress
This week, we made good progress towards implementing mapping and gesture recognition using ML methods like SVM.
Robot Mapping
This week, we (partially) implemented the 2D mapping algorithm. There are two phases to the algorithm: edge-following and scanning the rest of the room. The edge-following works fine, but we are still experimenting with the second phase. We need to continue tuning and potentially come up with a new algorithm. Since mapping is a significant part of the project and we don’t want any bottlenecking, we must complete the algorithm by the beginning of the week after the break.
Gesture Recognition
We deployed our data gathering pipelines to collect data for teleop and point data. We also trained both multiclass and one versus all (OVR) SVMs for each task and tried them with our main camera script. Our best teleop model gave around 0.94 accuracy with SVM params C = 10, gamma = “scale”, and polynomial kernel. It was interesting to see the cases that our models beat the heuristics, especially when the user is standing on the of the screen or not directly facing the camera.
Deliverables next week
Next week, we will continue working on gesture recognition with more features and explore 2D point tracking with models. We will also explore the possibility of tracking with multiple cameras. We also will start exploring methods to locate the robot from the image in order to start working on our 2D to 3D mapping synchronization.
Schedule
On Schedule.