Search papers, labs, and topics across Lattice.
This paper introduces SkyDrive, a novel framework that leverages drone-based traffic monitoring to enhance the adaptability of autonomous driving systems in new urban environments. By collecting 137 hours of aerial footage, the authors extracted 650,000 driving samples, demonstrating that limited aerial supervision can significantly reduce performance degradation in zero-shot scenarios across different cities. The results indicate that aerial monitoring provides a scalable and efficient alternative to traditional vehicle-based data collection for training trajectory planners and motion predictors.
Aerial traffic monitoring can drastically improve the adaptability of autonomous vehicles to new cities with minimal data collection efforts.
Autonomous driving has made remarkable progress through imitation learning with massive human demonstration data. However, a trained planner often degrades severely when applied to a new environment zero-shot, because of domain shifts in traffic regulations, road layout and driving behaviors. Therefore, adapting a trajectory planner to a new city typically requires resource-demanding local data collection with a vehicle sensor suite. In this work, we show that driving behavior can be learned from a scalable and efficient alternative. We introduce \emph{SkyDrive}, a framework that utilizes drone-based traffic monitoring to provide efficient supervision for autonomous driving agents in a new environment. While vehicle-based data collection logs the ego and its surroundings, an aerial platform naturally observes many road users simultaneously over an extended field of view. As a result, every vehicle can be a data source with grounded driving behavior, effectively scaling up the amount of supervision. Based on 137 hours of aerial traffic monitoring footage, we extract 650K driving samples and construct a benchmark for trajectory planners and motion predictors. Zero-shot experiments with multiple models reveal significant cross-city domain gaps, but many of them can be alleviated by limited supervision from the sky, e.g., 30 minutes of monitoring per location. Our findings show that aerial traffic monitoring is an efficient and scalable data source for adapting autonomous driving systems in new cities. Data and code will be made publicly available.
