Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
This work provides a crucial, large-scale benchmark for sub-meter retrieval-based localization at city scale, addressing a key challenge for the development and evaluation of self-driving car technology.
This paper introduces Pit30M, a new image and LiDAR dataset with over 30 million frames, designed to evaluate retrieval-based localization for self-driving cars. The dataset is 10 to 100 times larger than previous datasets and includes diverse conditions and accurate localization ground truth. The authors benchmark existing methods and propose a competitive convolutional network-based LiDAR retrieval method.
We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles. Towards this goal, we introduce Pit30M, a new image and LiDAR dataset with over 30 million frames, which is 10 to 100 times larger than those used in previous work. Pit30M is captured under diverse conditions (i.e., season, weather, time of the day, traffic), and provides accurate localization ground truth. We also automatically annotate our dataset with historical weather and astronomical data, as well as with image and LiDAR semantic segmentation as a proxy measure for occlusion. We benchmark multiple existing methods for image and LiDAR retrieval and, in the process, introduce a simple, yet effective convolutional network-based LiDAR retrieval method that is competitive with the state of the art. Our work provides, for the first time, a benchmark for sub-metre retrieval-based localization at city scale. The dataset, its Python SDK, as well as more information about the sensors, calibration, and metadata, are available on the project website: https://pit30m.github.io/