วีดีโอ

It's called VEXcode IQ, you can install is here: www.vexrobotics.com/vexcode/install/iq There's also a browser version but I highly recommend installing the app instead: codeiq.vex.com/

It's an LDS-01 on top of a TurtleBot3: emanual.robotis.com/docs/en/platform/turtlebot3/appendix_lds_01/

All of the 3D plots were made in MATLAB, mostly using the plot3 and quiver3 functions. Full code can be found here: github.com/KaiNakamura/RBE3001

@@kaihnakamura thank you

I just contacted my professor and they told me the walls are custom made from rectangular thin plywood sheets and 3D printed parts. The curved walls are made by laser cutting a zig-zag pattern into the plywood, allowing it to bend. If you're interested in creating your own I could probably contact the lab staff and get the files needed to reproduce them if you're interested. Hope this helps!

me too i also want to go through nav2 package from scratch

Me too! Although it’s meaningless because it’s the first one. Data needs context. 😅

It's hard to say for sure if LIDAR would work well in an outdoor environment for your needs. One thing to keep in mind for the robot I used is that it only makes LIDAR scans parallel to the ground. This worked find for my needs because the only obstacles were the walls. But if the environment were full of obstacles shorter than the LIDAR sensor, then the robot would be unable to detect them. There are 3D LIDAR sensors that allow you to create point clouds in 3D, but these can be quite expensive. Some SLAM robots use a 2D LIDAR scanner in combination with a stereo camera to achieve the same effect. The robot in the video is a TurtleBot3, but I know the TurtleBot4 uses the LIDAR and camera approach. Hope this helps! turtlebot.github.io/turtlebot4-user-manual/overview/features.html

@@kaihnakamura I really appreciate your thoughts and input. I was considering using GPS, but realized I would need RTK to make it accurate enough and that’s a bit more expensive than I was hoping for.

Currently, the robot is using the gmapping ROS package to map the environment which only works for static environments. However, there are other SLAM implementations in ROS that allow for dynamic maps such as slam_toolbox. gmapping: wiki.ros.org/gmapping slam_toolbox: github.com/SteveMacenski/slam_toolbox#lifelong-mapping

Cool, I gotta say this is a very well made video, I’m surprised at how small the Chanel is and I hope to see it grow.

Thank you so much! :)

Three people over the course of a seven week term. Unfortunately, I cannot share the code in its entirety due to academic policy (students next year would just be able to copy it). But I could share code snippets or point toward resources with some of the algorithms I used if you’re interested. Thank you so much for your interest in this project! :)

can u share me as well

@@kaihnakamura Yeah, it would be awesome! If you could share info about the hardest points, not in a code, but maybe as a theory, methodology or something similar. It could help others and i think will be a interesting material for your blog!

There’s no one right way to create a computer vision pipeline, but there are certainly some things that help a whole lot. One of the more difficult steps is getting the color thresholding just right since it can vary a lot with ambient light levels so it’ll inevitably pick up some unwanted pixels. To combat this, I highly recommend using the MATLAB imfindcircles function to clean up unwanted pixels. In my experience it works far better than other alternatives like erosion. Best of luck with your project!

The arm we used is the OpenMANIPULATOR-X. More details about it can be found in our full report here: kainakamura.com/project/rbe3001

We used MATLAB to control the arm, you can look at the source code here: github.com/KaiNakamura/RBE3001

The Dynamixel servos are more advanced than normal servos. They each have their own processor and can receive a command to move their joint to a specific position, which they then do without additional help from the main computer

Good catch! No this was not intentional, the x and y axes should be switched in each frame.

@@kaihnakamura Got it. Anyway, really good video. With your permission, I'd like to use this video for when I'll teach RBE 3001 in C term.

@@kid-a Absolutely, feel free to use this video!

Yes! I've got some more details and a full report on my website at kainakamura.com/project/rbe3001

Thanks @@kaihnakamura

probably trigonometry, linear algebra and Python programming