Documentation
We are here to support you in your learning journey and as you start building real-world impact with robotics, AI, and clean-tech systems and earn your industry-recognized credentials. If we can help you in any way, please contact us.
Install controller packages, set up a custom teleop package and drive the robot with a Bluetooth gamepad.
teleop
Launch the camera node, verify image streams, record images and video, preview the feed, calibrate transforms and perform diagnostics.
camera
Build and flash the Teensy firmware, monitor the serial output, start the micro‑ROS agent, and control the robot via keyboard.
teensy
teleop
Reference instructions for assembling the Common Robotics Platform hardware.
hardware
Organize teleop images, configure Label Studio and copy annotations for machine learning.
annotation
Launch the RPLIDAR driver, verify scan data and perform diagnostics and calibration.
lidar
Launch the Nav2 stack, check planner topics, send a navigation goal and monitor planning performance.
navigation
Build and run the object detection node, then verify that detections are being published.
object-detection
Prepare your robot by connecting to the Raspberry Pi, configuring host and network settings, setting the ROS namespace and flashing the microcontroller firmware.
quickstart
setup
Discover the robot’s IP, update the common_platform repo, configure host and network settings and set the ROS namespace.
setup
Startup, shutdown, reboot, emergency shutdown and routine maintenance for the robot.
operations
Start the Fast DDS discovery server and configure the micro‑ROS agent for centralized discovery.
networking
Launch RViz 2 and configure displays to visualize LiDAR, camera and map data.
rviz
Run AMCL-based localization on a saved map and monitor the estimated pose and status.
localization
Prepare the Cartographer launch file, start the robot state publisher, run Cartographer SLAM and occupancy grid mapping, verify topics, tune parameters, monitor constraints and save the resulting map.
SLAM
mapping
Install and configure a development VM with Ubuntu, ROS 2 and coding tools.
vm
Prepare your dataset, train a YOLOv11n model on custom labels and export the model for deployment.
yolo
finetuning
Set up the Hailo development environment, calibrate your dataset, create configuration files, compile your model into a HEF, and deploy it on the Raspberry Pi AI Kit.
hailo
yolo