RoboDoctor: A Local AI Debugging Companion for Robotics
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Debugging robotics software has a particular kind of pain. You don't just have one terminal. You might have a ROS2 launch running in one terminal, a controller in another, a sensor node somewhere else, RViz open on the side, and a Python script running in another window. Then something breaks. You get a…
RoboDoctor is an artificial intelligence tool designed to assist with debugging robotics software. It is an open-source project available on GitHub that aims to simplify the process of troubleshooting complex issues in robotics development. RoboDoctor sits on the desktop and monitors multiple terminal sessions related to robotics projects.
When an error occurs in any of these sessions, RoboDoctor captures the context automatically and presents the problem to the user through a small robot companion on the desktop. The AI reasoning layer behind RoboDoctor is Gemma 3 4B, which is run locally using Ollama. This allows the tool to analyze diagnostic evidence without sending sensitive information to remote servers.
RoboDoctor treats each terminal session as an independent entity, preventing confusion between errors in different sessions. It monitors command output, exit codes, and ROS2 environments to accurately associate errors with their respective sessions. The desktop companion provides an intuitive interface for developers to navigate to the problematic terminal session and start an investigation.
By keeping the AI reasoning locally and using open-source components, RoboDoctor offers a practical solution for robotics debugging that respects privacy, connectivity, and cost concerns.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
