Hybrid control and learning with coresets for autonomous vehicles
Author(s)
Rosman, Guy; Paull, Liam; Rus, Daniela L
DownloadAccepted version (2.193Mb)
Open Access Policy
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
© 2017 IEEE. Modern autonomous systems such as driverless vehicles need to safely operate in a wide range of conditions. A potential solution is to employ a hybrid systems approach, where safety is guaranteed in each individual mode within the system. This offsets complexity and responsibility from the individual controllers onto the complexity of determining discrete mode transitions. In this work we propose an efficient framework based on recursive neural networks and coreset data summarization to learn the transitions between an arbitrary number of controller modes that can have arbitrary complexity. Our approach allows us to efficiently gather annotation data from the large-scale datasets that are required to train such hybrid nonlinear systems to be safe under all operating conditions, favoring underexplored parts of the data. We demonstrate the construction of the embedding, and efficient detection of switching points for autonomous and non-autonomous car data. We further show how our approach enables efficient sampling of training data, to further improve either our embedding or the controllers.
Date issued
2017-09Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryPublisher
IEEE
Citation
Rosman, Guy, Paull, Liam and Rus, Daniela. 2017. "Hybrid control and learning with coresets for autonomous vehicles."
Version: Author's final manuscript