Filters








1 Hit in 2.0 sec

Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data [article]

David Hallac, Suvrat Bhooshan, Michael Chen, Kacem Abida, Rok Sosic, Jure Leskovec
2018 arXiv   pre-print
In this paper, we develop a deep learning-based method, called Drive2Vec, for embedding such sensor data in a low-dimensional yet actionable form.  ...  With automobiles becoming increasingly reliant on sensors to perform various driving tasks, it is important to encode the relevant CAN bus sensor data in a way that captures the general state of the vehicle  ...  Our model takes as input a short segment of sensor data and returns a low-dimensional embedding representing the car's state.  ... 
arXiv:1806.04795v1 fatcat:wpym2uoubbfubkb43r4kfqwq7y