公开(公告)号：US11734935B2

公开(公告)日：2023-08-22

申请号：US17314462

申请日：2021-05-07

Applicant: Argo AI, LLC

Inventor： Kevin Chen ,  James Hays ,  Ersin Yumer

IPC: G06V20/56 ,  G01S17/90 ,  G05D1/00 ,  G06F30/20 ,  G06V10/80 ,  G09B9/04 ,  G05D1/02 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V20/56 ,  G01S17/90 ,  G05D1/0088 ,  G05D1/0221 ,  G06F30/20 ,  G06V10/774 ,  G06V10/803 ,  G06V10/82 ,  G05D2201/0213

Abstract: Methods and systems are disclosed for correlating synthetic LiDAR data to a real-world domain for use in training an model for use by autonomous vehicle when operating in an environment. To do this, the system will obtain a data set of synthetic LiDAR data, along with images of a real-world environment. The system will transfer the synthetic LiDAR data to a two-dimensional representation, use the two-dimensional representation and the images to train a model that a vehicle can use to operate in a real-world environment.

公开(公告)号：US20210263528A1

公开(公告)日：2021-08-26

申请号：US17314462

申请日：2021-05-07

Applicant: Argo AI, LLC

Inventor： Kevin Chen ,  James Hays ,  Ersin Yumer

IPC: G05D1/02 ,  G06F30/20 ,  G01S17/90 ,  G05D1/00

Abstract: Methods and systems are disclosed for correlating synthetic LiDAR data to a real-world domain for use in training an model for use by autonomous vehicle when operating in an environment. To do this, the system will obtain a data set of synthetic LiDAR data, along with images of a real-world environment. The system will transfer the synthetic LiDAR data to a two-dimensional representation, use the two-dimensional representation and the images to train a model that a vehicle can use to operate in a real-world environment.

公开(公告)号：US20200326717A1

公开(公告)日：2020-10-15

申请号：US16380180

申请日：2019-04-10

Applicant: Argo AI, LLC

Inventor： Kevin Chen ,  James Hays ,  Ersin Yumer

IPC: G05D1/02 ,  G05D1/00 ,  G06F17/50 ,  G01S17/89

Abstract: Methods and systems are disclosed for correlating synthetic LiDAR data to a real-world domain for use in training an autonomous vehicle in how to operate in an environment. To do this, the system will obtain a data set of synthetic LiDAR data, transfer the synthetic LiDAR data to a two-dimensional representation, use the two-dimensional representation to train a model of a real-world environment, and use the trained model of the real-world environment to train an autonomous vehicle.

公开(公告)号：US11436842B2

公开(公告)日：2022-09-06

申请号：US16817704

申请日：2020-03-13

Applicant: Argo AI, LLC

Inventor： Guy Hotson ,  Richard L. Kwant ,  Ersin Yumer

IPC: G06V20/58 ,  G05D1/00 ,  G06T7/90 ,  G06V10/56 ,  G06V10/60

Abstract: Systems and methods are provided for representing a traffic signal device. The method includes receiving a digital image of a traffic signal device that includes one or more traffic signal elements, representing the traffic signal device as a raster image, each traffic signal element of the traffic signal device being represented by a mask corresponding to a location of the traffic signal element on the traffic signal device, representing each mask in a channel in the raster image, providing the raster image as an input to a neural network to classify a state for each of the one or more traffic signal elements, and receiving, from the neural network, a classified raster image, in which the classified raster image includes a plurality of masks, each mask representing a state of one of the one or more traffic signal elements.

公开(公告)号：US20210287023A1

公开(公告)日：2021-09-16

申请号：US16817704

申请日：2020-03-13

Applicant: Argo AI, LLC

Inventor： Guy Hotson ,  Richard L. Kwant ,  Ersin Yumer

IPC: G06K9/00 ,  G06K9/46 ,  G06T7/90 ,  G05D1/00

Abstract: Systems and methods are provided for representing a traffic signal device. The method includes receiving a digital image of a traffic signal device that includes one or more traffic signal elements, representing the traffic signal device as a raster image, each traffic signal element of the traffic signal device being represented by a mask corresponding to a location of the traffic signal element on the traffic signal device, representing each mask in a channel in the raster image, providing the raster image as an input to a neural network to classify a state for each of the one or more traffic signal elements, and receiving, from the neural network, a classified raster image, in which the classified raster image includes a plurality of masks, each mask representing a state of one of the one or more traffic signal elements.

公开(公告)号：US11016496B2

公开(公告)日：2021-05-25

申请号：US16380180

申请日：2019-04-10

Applicant: Argo AI, LLC

Inventor： Kevin Chen ,  James Hays ,  Ersin Yumer

IPC: G05D1/02 ,  G06F30/20 ,  G01S17/90 ,  G06K9/00 ,  G09B9/05 ,  G05D1/00

Abstract: Methods and systems are disclosed for correlating synthetic LiDAR data to a real-world domain for use in training an autonomous vehicle in how to operate in an environment. To do this, the system will obtain a data set of synthetic LiDAR data, transfer the synthetic LiDAR data to a two-dimensional representation, use the two-dimensional representation to train a model of a real-world environment, and use the trained model of the real-world environment to train an autonomous vehicle.