03 Feb

This week, we are collecting some green ball data using the cellphone camera and esp32 cam. We've collected three different sets of photos with different resolution: (1) Cellphone camera, resolution: 3264 * 2448 (2) esp32-cam, resolution: 1280 * 1024 (3) esp32-cam, resolution: 800 * 600...

03 Feb

The design parameters space: The performance evaluation system and performance:

02 Feb

This week, I've tested the different relationship between voltage -thrust with different motor + propeller combination. The different motor+propeller combination is shown as follows: (1) Propeller forward turning vs. Propeller reverse turning (2) Propeller forward turning vs. Propeller rev...

01 Feb

I reimplemented the Gtech paper for primitive monocular depth estimation. It works relatively well but requires a certain measurement of the object before the estimation. Reference - N. Yao, E. Anaya, Q. Tao, S. Cho, H. Zheng and F. Zhang, "Monocular vision-based human following on miniature robot...

01 Feb

To explore another method for object detection, I have built the pipeline to stream the video feed from the camera to the laptop and run the model on the video stream. Therefore, we now have the functionality to use any ML / neural network model for object detection Github Repo - https://github.co...

01 Feb

I explored the idea of running object detection on the microcontroller itself. I explored the following libraries – Tensorflow Lite ESP WHO Eloquent Conclusion – I found the TensorFlow lite library extremely unstable. There are many bugs in the repo. I was not able to build a single exampl...

01 Feb

Based on the new rule: No use of adhesives for capturing game balls. We now need to design a ball capture mechanism without using adhesives. Some requirement about this capture mechanism: Functionally, it should be able to easily catch and release the ball From design aspect, it should be l...

28 Jan

We are working towards a fully decenatralize lifelong path planner for multi-agent path finding. To that end we have built an Open.ai gym environment which can be found here: https://github.com/pehuenmoure/warehouse_rrl. Our environment environment will be used for training our agents and analyzing...

28 Jan

I've been thinking about the next direction I can put into my DARPA paper. I'm puting some ideas together, the overall framework is that I would like to solve a multi-agent planning problem: Here are some relative concepts that tight into this problem: Multi-agent planning: multiagent plan...

28 Jan

Currently working on the first step of a simulation for Tsang-Kai's SLAM project. A simulation will help verify landmark accuracy among other things beyond what can be demostrated using datasets. Ultimately we would like the simulation to look like the below figure [1] . The simulation setup...