公开(公告)号：US20200074230A1

公开(公告)日：2020-03-05

申请号：US16560046

申请日：2019-09-04

Applicant: Luminar Technologies, Inc.

Inventor： Benjamin Englard ,  Miguel Alexander Peake

IPC: G06K9/62

Abstract: Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications. The sensor parameter optimizer may determine, based on operation of the autonomous vehicle, an optimal parameter setting of the parameter setting where the optimal parameter setting may be applied to a real-world sensor associated with real-world autonomous driving applications.

公开(公告)号：US11521009B2

公开(公告)日：2022-12-06

申请号：US16559945

申请日：2019-09-04

Applicant: Luminar Technologies, Inc.

Inventor： Miguel Alexander Peake ,  Benjamin Englard

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/00 ,  G08G1/0962 ,  G06N5/04 ,  G06F13/28 ,  G06T7/246 ,  G06T7/50 ,  G05D1/00 ,  G05D1/02 ,  G01S7/48 ,  G01C21/28 ,  G06V20/56 ,  G06N20/00 ,  G06F9/451 ,  G06T11/60

Abstract: Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications. The sensor parameter optimizer may determine, based on operation of the autonomous vehicle, an optimal parameter setting of the parameter setting where the optimal parameter setting may be applied to a real-world sensor associated with real-world autonomous driving applications.

公开(公告)号：US20200074266A1

公开(公告)日：2020-03-05

申请号：US16559945

申请日：2019-09-04

Applicant: Luminar Technologies, Inc.

Inventor： Miguel Alexander Peake ,  Benjamin Englard

IPC: G06N3/00 ,  G06N20/00 ,  G06N5/04 ,  G06F13/28 ,  G06K9/62 ,  G06T7/246 ,  G06K9/00 ,  G06T7/50 ,  G05D1/00 ,  G05D1/02 ,  G01S7/48 ,  G01C21/28

Abstract: Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications. The sensor parameter optimizer may determine, based on operation of the autonomous vehicle, an optimal parameter setting of the parameter setting where the optimal parameter setting may be applied to a real-world sensor associated with real-world autonomous driving applications.

公开(公告)号：US20200074233A1

公开(公告)日：2020-03-05

申请号：US16560018

申请日：2019-09-04

Applicant: Luminar Technologies, Inc.

Inventor： Benjamin Englard ,  Miguel Alexander Peake

IPC: G06K9/62 ,  G06N3/00 ,  G06T11/60 ,  G08G1/0962

Abstract: Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications. The sensor parameter optimizer may determine, based on operation of the autonomous vehicle, an optimal parameter setting of the parameter setting where the optimal parameter setting may be applied to a real-world sensor associated with real-world autonomous driving applications.