AUTOBRAINS TECHNOLOGIES LTD. (20250061326). METHOD FOR REDUCING COMPUTATIONAL COST FOR AUTONOMOUS DRIVING SYSTEM
METHOD FOR REDUCING COMPUTATIONAL COST FOR AUTONOMOUS DRIVING SYSTEM
Organization Name
Inventor(s)
Julius Engelsoy of Tel Aviv-Yafo (IL)
Igal Raichelgauz of Tel Aviv (IL)
Armin Biess of Ness Ziona (IL)
Isaac Misri of Tel Aviv-Yafo (IL)
Joey Hendry of Tel Aviv-Yafo (IL)
METHOD FOR REDUCING COMPUTATIONAL COST FOR AUTONOMOUS DRIVING SYSTEM
This abstract first appeared for US patent application 20250061326 titled 'METHOD FOR REDUCING COMPUTATIONAL COST FOR AUTONOMOUS DRIVING SYSTEM
Original Abstract Submitted
a method for reducing the computational cost for an autonomous driving system is disclosed. the method may include the following steps: a) acquiring data related to a task for operating a vehicle; b) training a deep learning model using the data acquired, wherein the deep learning model includes an encoder and a policy head for the task; c) reducing a complexity of the data acquired in step a) by passing the data to the encoder to produce a compressed latent representation of the data; and d) determining a driving operation by the policy head using the compressed latent representation of the data.
