For the last two weeks our team worked together to integrate the various subsystems. Attached is a video which demonstrates that our robot can autonomously complete the majority of the work, including navigation to basket and shelf, identifying the pointed object with the laser tag, and successful physical retrieval of the item. In comparison to the last status report, the robot has much more consistent behavior, and most runs are nearly successful. Some solutions include adding an IMU sensor to the robot, so that the robot can orient itself after travelling some distance, to account for drift in the wheels. We experimented on finer tunings of the edge detection code, where the camera only looks at a specific area where the object is located at. This greatly helps in reducing background noise. We also implemented the last step of returning to the basket and dropping the item. Our team also ran some preliminary tests, as well as worked on the slides for the final presentation this last week. During this process we ran into the claw having inconsistent closing behavior, but after tweaking with the heights of the two sides, the performance is much better. Since the claw inconsistencies mostly come from the claw being worn down too much after multiple runs, we also ordered a new claw in case the claw malfunctions before the final demo.
We believe our team is on schedule, and the final delivery of the project is almost finished. Next week our group would mostly focus on the project report, final video, as well as last tweaking of parameters to achieve better consistency.