High-definition (HD) maps are detailed digital models of the world, including elements like road geometry, signs, and traffic signals. While they've been widely used for autonomous driving, they’re costly to create and maintain. This has led to the growing demand for “mapless driving.” In this episode of DRIVE Labs, we’ll explore NVIDIA innovations that enhance mapless driving by removing information bottlenecks, improving task accuracy, and accelerating model training and inference times. Timestamps 00:00:25 - Growing demand for mapless driving and removing the dependency on HD maps 00:00:40 - RoadNet predicts road geometry in real time 00:01:03 - Improving mapless driving by removing information bottlenecks 00:01:45 - Further improvements by tight module integration 00:02:22 Provide direct path to end-to-end AV stack Resources: Paper: arxiv.org/abs/2403.16439 arxiv.org/abs/2407.06683 GitHub: github.com/alfredgu001324/MapUncertaintyPrediction Watch ...