This invention describes a system for an autonomous vehicle to drive itself to a user-specified destination. It uses sensors to map its surroundings, identifying areas it can drive through and areas it cannot. As the vehicle moves, it continuously updates this map and adjusts its route to safely reach the target location, specifically by using a machine learning model to create and update a grid-based map of drivable and non-drivable spaces.
Why it matters: Filed only two years ago, the core challenges of real-world autonomous navigation, including robust sensor fusion and safety-critical software, remain largely unchanged. No specific technological leap has occurred to make this particular approach significantly easier or more viable since 2024.
AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.
Reinvent this with AI