McGillFormulaElectric/MFE-Driverless-V1

AI Summary: Implement LiDAR data processing to clean raw data from a Velodyne Puck. This involves fraction accumulation and velocity compensation to improve data quality and usability for the McGill Formula Electric driverless car project. Good software design patterns are required.

AI Summary: Configure the Jetson Nano development board with necessary software development tools and visualization packages for testing the McGill Formula Electric driverless car software. Documentation of this setup is also required for future development of a Jetson dev container.

AI Summary: Extract depth data from a YOLO object detection pipeline by overlaying bounding boxes onto a depth map generated using the librealsense SDK. The depth value for each detected object will be determined, potentially using the median depth within the bounding box, and this method should be documented.

AI Summary: Integrate the Intel Realsense SDK into the McGill Formula Electric Driverless ROS 2 workspace, ensuring compatibility with `librealsense` and employing appropriate design patterns for future scalability. This involves configuring the ROS 2 workspace to work seamlessly with the Realsense camera for both real-world and simulated driving scenarios.