Integrating Pixhawk and Realsense Camera for Rover Autonomy

This study presents the design and implementation of a low-cost autonomous go-kart that uses a Pixhawk-4 flight controller and ArduPilot to enable waypoint-based navigation and speed control without human intervention. It also demonstrates how integrating an Intel RealSense depth camera improves safety through MAVLink-based obstacle avoidance, particularly in environments with obstacles.

This project demonstrates the design and implementation of an autonomous go-kart using a Pixhawk-4 flight controller for navigation and speed control. This system uses Pulse Width Modulation signals to control a brushless motor via an electronic speed controller, allowing waypoint navigation-based autopilot without the need for human intervention. A secondary configuration integrates an Intel RealSense depth camera with a companion laptop running a Python script for obstacle detection, enhancing safety through MAVLink (Micro Air Vehicle Link) [5], based avoidance commands. Key results demonstrate successful waypoint navigation with accuracy in open and unobstructed environments, whereas the RealSense addition reduces collision risk in paths with obstacles. This project utilizes aerospace-grade autonomy using ArduPilot with ground vehicle applications, emphasizing a relatively low-cost application of autonomous systems.

Explore More!

Allez Go: AI Fencing Referee

Technology in fencing is generally an underdeveloped field and automated referees present potentially significant benefits to the sport. Automated referees will offer a more consistent call compared to a group of human referees with slightly different interpretations of the fencing rules.