Zebracorn Labs
Here at the Zebracorns, we believe in learning and pushing boundaries. In pursuit of that, we have published papers, given talks, and have other tidbits of knowledge lying around. We hope you enjoy these as much as we do.
Zebravision 7.0
During the past few years, we have focused on developing robust sensing and inference systems to accelerate our progress towards a fully autonomous robot. The ability to estimate the robot’s absolute position on the field is critical to achieving this goal. During the 2020 season, we made groundbreaking strides in this vein, developing systems to make our robot more environment-aware. In this paper, we introduce two systems: a neural network-based object detector and a particle filter localization system. We believe that neural networks are the future of computer vision in FRC; to help foster innovation in the FRC community, we release our dataset from this season.
ZebROS 2020
Over the past four years, the Zebracorns have created a modular design philosophy and development model based on the Robot Operating System (ROS). Last year, we focused on polishing the core elements and laying the foundation of our robot code base. During the 2020 season, we were able to leverage the advantages of this system as we continue to build upon our previous work. Many of this year’s improvements centered around reliability of the robot itself, as well as driver-robot interaction. Other improvements are new features that bring us closer to the goal of a fully autonomous robot.
Towards Robust Color Sensing
A very real whitepaper about the sensing of colors utilizing neural networks in FRC
2020 Pre-Season Code Release
During offseason we focused on improving the swerve drive we used last year and the tank drive we designed last year in the case of obstacles. We’ve put them into a public OnShape space so feel free to peruse our files. Note: Most of the designs are either unfinished or won’t necessarily work in their current state.
2020 Pre-Season CAD Release
During offseason we focused on improving the swerve drive we used last year and the tank drive we designed last year in the case of obstacles. We’ve put them into a public OnShape space so feel free to peruse our files. Note: Most of the designs are either unfinished or won’t necessarily work in their current state.
ZebraSwitch - Reliable Robot Ethernet that won't break your BOM
We’ve spent a long time searching for a reliable gigabit Ethernet solution to use on our robots that is affordable and works well for us. This paper will describe our “recipe” for creating such a switch.
ZebROS Nano
At long last, we have scaled down our robot (but not our efforts) in an attempt to bring our work with ROS to more people. This tutorial focuses on our work with the NVIDIA Jetson Nano, a TileRunner Chassis from AndyMark, and Talon SRX Motor Controllers from Cross The Road Electronics to bring our ZebROS work to a larger audience. We think that the NVIDIA Jetson Nano is an excellent system to bring new robots online or bring older robots back to life and teach yourself some new skills around ROS in the process. We've done our best to make sure this Tutorial is easy to follow but we are releasing the document as a living Google document and not a PDF so that we can keep updating this as we get questions and eventually add even more to this tutorial. We're also releasing our complete software image for this so getting started is even easier.
Collaborative Whitepapers Using Overleaf
Overleaf generously agreed to provide us with a premium subscription which allows us to keep and share the source code of our whitepapers. In this paper, we want to express our gratitude for their generosity, explain our process for writing, editing, and publishing whitepapers, and talk about the features of Overleaf that we like the most.
Terabee Sensors for Robot Alignment
During the 2019 season, we received some distance sensors from Terabee which we have been experimenting with throughout the competition season. This whitepaper discusses the alignment algorithms that we developed using the Terabee sensors and how successful they were for the 2019 game.
ZebROS 1.1
In 2018, we wrote a comprehensive whitepaper explaining our groundbreaking work to introduce ROS to FRC. This year, we learned from last year's mistakes and challenges to write better code: code that was effectively organized for automation and took advantage of more of what ROS has to offer. We also made the huge step of transfering some CAN reads and writes to our NVIDIA Jetson TX2, requiring the setup of a second hardware interface. This whitepaper covers the biggest improvements that we made this year.