US 11,657,604 B2
Systems and methods for estimating future paths
David Huberman, Jerusalem (IL); Shaked Shammah, Jerusalem (IL); and Ofer Springer, Jerusalem (IL)
Filed by Mobileye Vision Technologies Ltd., Jerusalem (IL)
Filed on May 7, 2021, as Appl. No. 17/314,157.
Application 17/314,157 is a continuation of application No. 15/398,926, filed on Jan. 5, 2017, granted, now 11,023,788.
Claims priority of provisional application 62/373,153, filed on Aug. 10, 2016.
Claims priority of provisional application 62/275,046, filed on Jan. 5, 2016.
Prior Publication US 2021/0365750 A1, Nov. 25, 2021
Int. Cl. G06V 30/194 (2022.01); G06V 20/56 (2022.01); G05D 1/00 (2006.01); G05D 1/02 (2020.01); G06K 9/62 (2022.01)
CPC G06V 30/194 (2022.01) [G05D 1/0088 (2013.01); G05D 1/0219 (2013.01); G05D 1/0238 (2013.01); G06K 9/6281 (2013.01); G06V 20/56 (2022.01); G06V 20/588 (2022.01)] 24 Claims
OG exemplary drawing
11. A computing device, comprising:
memory to store an image that represents a scene of an environment captured from a current location of a vehicle; and
processor circuitry configured to:
apply a neural network model to the image, the neural network model trained to identify multiple future trajectories from an input image,
wherein the neural network model produces two or more predicted future trajectories of the vehicle ahead of the current location of the vehicle when applied to the image; and
utilize the two or more predicted future trajectories of the vehicle to change operation of the vehicle on a roadway within the environment.