Autonomous vehicles present a significant data collection and management challenge. Just one autonomous vehicle (AV) can produce up to 30 GB/hour of data, meaning that even a team with a single car will produce large amounts of data, and this presents even more of a challenge at scale. For AV researchers, this data is an opportunity to use historical data to improve their methods and algorithms, particularly for specific events that tend to cause problems for AVs. Thus having an easy way to query sensor data from such specific situations would be an invaluable resource. However, while platforms such as ROS exist for managing sensor data, it is difficult to come by good tools for querying specific sensor data over a large dataset. Furthermore, without careful thought the majority of useful query workloads would be painfully slow. Our database system will address these challenges.
If you would like to contact us about our work, please scroll down to the people section and click on one of the group leads' people pages, where you can reach out to them directly.