We are able to conduct green ball detection end-to-end pipeline using ESP 32 Cam The closed-loop communication figure: We are now able to transfer detected data (X,Y) position of the center of the green ball) to Esp32 feather board ESP 32 Camera (as an Access Point) broadcast video it saw ...
We finished the two-way wifi communication between two esp32. Based on our experiment two days ago, in order to easily and quickly debug our PID paramters. We need to find a good way to tune those parameters and receive the information from the blimp for debugging purposes. In the following v...
The reason we failed tonight: (1) Space decoration: it took us 40 mins to setup everything (new floor lamp, super long power strip, table, blimp, chair and so on) It sitll not a good setup. For example, the power strip is at the center of the field, which is easily stumbled. Th...
The FORAY team is presently working on the integration of tasks for the individual blimp. This includes ball detection (presently using color detection for the prototype), ball capture (using the basket and a LIDAR+camera system), goal detection (presently using April Tag detection and shape detecti...
We figured out a new way of doing image detection. In this way, we should be able to use the computational power of laptop to detect objects using trained machine learning algorithm. Here is the overall flowchart: We tested the RF communication part in the lab: It works exceedingly bette...
Simulation playground decoration progress： We attached April tag with the square hoop and hang them at the ceiling. Since there is a strong wind coming out of the wind tunnel on the simulation room, we used a plate to block the wind tunnel. (Effect see demo 1:) Demo 1: Strong wind disturbance...
Simulation room decoration: We hang the net at the ceiling We tested the floor lamp in the simulated space We implemented the April Tag recognition there. Video is from yesterday:
Demo: Blimp recognize and move toward an April tag [x] Camera is capable of identifying the April tags below the goal [x] Blimp is capable of moving toward an identified goal [x] Test the range and performance of this capability [ ] Blimp can conduct rotation and vertical motion using the Ap...
For the last few days, we have been working on two problems: the ball possession problem and the ML-based ball detection algorithm. Ball Possession At first, we attempted to detect the possession of the ball in the basket using IR sensors. However, both the sensors we had gave a very small range...
Blimp can seek, recognize, move toward and capture a green ball using color detection （the new blimp setup：with camera on the nose of the blimp) (demo) Modify and improve our current design (lightweight gondola, control board and camera at the new position) Test the algorithm on the new bl...