公开(公告)号：US11873006B2

公开(公告)日：2024-01-16

申请号：US17026522

申请日：2020-09-21

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Tiffany J. Hwu ,  Rajan Bhattacharyya ,  Michael J. Daily ,  Kyungnam Kim

IPC: B60W60/00 ,  G01C21/00 ,  G06N3/04 ,  B60W10/04 ,  G01C21/34 ,  G06N3/08 ,  B60W30/12

CPC classification number: B60W60/0011 ,  B60W10/04 ,  B60W30/12 ,  B60W60/0027 ,  G01C21/3407 ,  G01C21/3815 ,  G06N3/04 ,  G06N3/08

Abstract: A virtual lane estimation system includes a memory device, a sensor and a computer. The memory device is configured to store a road map that corresponds to a portion of a road ahead of a vehicle. The sensor is configured to observe a plurality of trajectories of a plurality of neighboring vehicles that traverse the portion of the road. The computer is configured to initialize a recursive self-organizing map as a plurality of points arranged as a two-dimensional grid aligned with the road map, train the points in the recursive self-organizing map in response to the trajectories, generate a directed graph that contains one or more virtual lanes through the road map in response to the points trained to the trajectories, and generate a control signal that controls navigation of the vehicle through the portion of the road in response to the virtual lanes in the directed graph.

公开(公告)号：US20240062555A1

公开(公告)日：2024-02-22

申请号：US17820317

申请日：2022-08-17

Applicant: GM Global Technology Operations LLC

Inventor： Jiejun Xu ,  Kenji Yamada ,  Michael J. Daily ,  Alireza Esna Ashari Esfahani ,  Hyukseong Kwon ,  Darren Michael Chan ,  Alan Perry ,  Joshua Lampkins

IPC: G06V20/58 ,  G06V20/62 ,  G06V10/82 ,  G06V30/262 ,  G06N3/04

CPC classification number: G06V20/582 ,  G06V20/63 ,  G06V10/82 ,  G06V30/274 ,  G06N3/0454

Abstract: A road sign interpretation system includes a front-facing camera mounted on or in a vehicle collecting image data of multiple road signs. A first convolutional neural network (CNN) receives the image data from the front-facing camera and yields a set of sign predictions including one or more sign text instances. A second CNN defining a text extractor receives the image data from the front-facing camera and extracts text candidates including the multiple sign text instances. Sign and sign data localization is provided in the second CNN to compute a text order from the multiple sign text instances. A sign text synthesizer module receives individual sign text instances from the first CNN and individual ones of the sign text instances in digitized forms from an optical character recognizer (OCR). A semantic encoding and interpretation module receives the sign text instances and identifies semantics of the multiple road signs.

公开(公告)号：US11724720B2

公开(公告)日：2023-08-15

申请号：US17487809

申请日：2021-09-28

Applicant: GM Global Technology Operations LLC

Inventor： Amit Agarwal ,  Hyukseong Kwon ,  Rajan Bhattacharyya ,  Michael J. Daily ,  Gavin D. Holland

IPC: B60W60/00 ,  B60W50/00

CPC classification number: B60W60/0027 ,  B60W50/0098 ,  B60W2050/006 ,  B60W2554/4042 ,  B60W2554/4043 ,  B60W2554/4044 ,  B60W2556/60 ,  B60W2720/10 ,  B60W2720/12

Abstract: A method using unsupervised velocity prediction and correction for urban driving from sequences of noisy position estimates includes: performing a vehicle velocity prediction for one or more other vehicles in a vicinity of a host automobile vehicle; calculating a first heuristic based on a uniformity test; calculating a second heuristic based on a vehicle speed of the one or more other vehicles; combining the first heuristic and the second heuristic using a weighted sum; determining an uncertainty mask applying the combined first heuristic and the second heuristic and a heuristic threshold; and applying the uncertainty mask to identify a velocity correction for use by the host automobile vehicle.

公开(公告)号：US11654933B2

公开(公告)日：2023-05-23

申请号：US17094255

申请日：2020-11-10

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Tiffany J. Hwu ,  Iman Mohammadrezazadeh ,  Michael J. Daily ,  Rajan Bhattacharyya

IPC: B60W60/00 ,  G06N3/04 ,  B60W30/12

CPC classification number: B60W60/0011 ,  B60W30/12 ,  G06N3/04 ,  B60W2552/10 ,  B60W2555/20 ,  B60W2556/40

Abstract: An ego vehicle includes decider modules and a grader module coupled to a resolver module. The decider modules generate trajectory decisions at a current time, generate a current two-dimensional slice of a flat space around the ego vehicle, generate future two-dimensional slices of the flat space by projecting the current two-dimensional slice of the flat space forward in time, and generate a three-dimensional state space by stacking the current two-dimensional slice and the future two-dimensional slices. The grader module generates rewards for the trajectory decisions based on a recent behavior of an ego vehicle. The resolver module selects a final trajectory decision for the ego vehicle from the trajectory decisions based on the three-dimensional state space and the rewards. The current two-dimensional slice includes a current ego vehicle location and current neighboring vehicle locations. The future two-dimensional slices include future ego vehicle locations and future neighboring vehicle locations.

公开(公告)号：US20220089183A1

公开(公告)日：2022-03-24

申请号：US17026522

申请日：2020-09-21

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Tiffany J. Hwu ,  Rajan Bhattacharyya ,  Michael J. Daily ,  Kyungnam Kim

IPC: B60W60/00 ,  G01C21/00 ,  B60W30/12 ,  B60W10/04 ,  G01C21/34 ,  G06N3/08 ,  G06N3/04

Abstract: A virtual lane estimation system includes a memory device, a sensor and a computer. The memory device is configured to store a road map that corresponds to a portion of a road ahead of a vehicle. The sensor is configured to observe a plurality of trajectories of a plurality of neighboring vehicles that traverse the portion of the road. The computer is configured to initialize a recursive self-organizing map as a plurality of points arranged as a two-dimensional grid aligned with the road map, train the points in the recursive self-organizing map in response to the trajectories, generate a directed graph that contains one or more virtual lanes through the road map in response to the points trained to the trajectories, and generate a control signal that controls navigation of the vehicle through the portion of the road in response to the virtual lanes in the directed graph.

公开(公告)号：US10677686B2

公开(公告)日：2020-06-09

申请号：US15811846

申请日：2017-11-14

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Matthew E. Phillips ,  Nandan Thor ,  Dylan T. Bergstedt ,  Jaehoon Choe ,  Michael J. Daily

IPC: G01M17/007 ,  G05D1/00

Abstract: The present application generally relates to methods and apparatus for evaluating and assigning a performance metric to a driver response to a driving scenario. More specifically, the application teaches a method and apparatus for breaking a scenario into features, assigning each feature a grade and generating an overall grade in response to a weighted combination of the grades.

公开(公告)号：US12033393B2

公开(公告)日：2024-07-09

申请号：US17487835

申请日：2021-09-28

Applicant: GM Global Technology Operations LLC

Inventor： Rodolfo Valiente Romero ,  Hyukseong Kwon ,  Rajan Bhattacharyya ,  Michael J. Daily ,  Gavin D. Holland

IPC: G06V20/58 ,  G01S17/89 ,  G06V10/82 ,  G06V20/64

CPC classification number: G06V20/58 ,  G01S17/89 ,  G06V10/82 ,  G06V20/64

Abstract: A method for performing object detection during autonomous driving includes: performing 3D object detection in a 3D object detection segment; uploading an output of multiple sensors in communication with the 3D object detection segment to multiple point clouds; transferring point cloud data from the multiple point clouds to a Region Proposal Network (RPN); independently performing 2D object detection in a 2D object detector in parallel with the 3D object detection in the 3D object detection segment; and taking a given input image and simultaneously learning box coordinates and class label probabilities in a 2D object detection network operating to treat object detection as a regression problem.

公开(公告)号：US11618479B2

公开(公告)日：2023-04-04

申请号：US17114822

申请日：2020-12-08

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Divya P. Kulkarni ,  Hyukseong Kwon ,  Kenji Yamada ,  Tiffany J. Hwu ,  Kyungnam Kim ,  Rajan Bhattacharyya ,  Michael J. Daily

IPC: B60W60/00 ,  G05D1/02

Abstract: A method of path planning for a host vehicle includes: receiving host vehicle, environmental and obstacle information; calculating one or more projected host vehicle locations; computing a projected obstacle location for each obstacle; and determining a collision potential between each projected host vehicle location and each projected obstacle location. Until a maximum number of steps is reached, and while at least one projected host vehicle location has an associated collision potential below a collision threshold, the method further includes repeating the calculating, computing and determining steps.

公开(公告)号：US20230100741A1

公开(公告)日：2023-03-30

申请号：US17487809

申请日：2021-09-28

Applicant: GM Global Technology Operations LLC

Inventor： AMIT AGARWAL ,  Hyukseong Kwon ,  Rajan Bhattacharyya ,  Michael J. Daily ,  Gavin D. Holland

IPC: B60W60/00 ,  B60W50/00

Abstract: A method using unsupervised velocity prediction and correction for urban driving from sequences of noisy position estimates includes: performing a vehicle velocity prediction for one or more other vehicles in a vicinity of a host automobile vehicle; calculating a first heuristic based on a uniformity test; calculating a second heuristic based on a vehicle speed of the one or more other vehicles; combining the first heuristic and the second heuristic using a weighted sum; determining an uncertainty mask applying the combined first heuristic and the second heuristic and a heuristic threshold; and applying the uncertainty mask to identify a velocity correction for use by the host automobile vehicle.

公开(公告)号：US20220177001A1

公开(公告)日：2022-06-09

申请号：US17114822

申请日：2020-12-08

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Divya P. Kulkarni ,  Hyukseong Kwon ,  Kenji Yamada ,  Tiffany J. Hwu ,  Kyungnam Kim ,  Rajan Bhattacharyya ,  Michael J. Daily

IPC: B60W60/00 ,  G05D1/02

Abstract: A method of path planning for a host vehicle includes: receiving host vehicle, environmental and obstacle information; calculating one or more projected host vehicle locations; computing a projected obstacle location for each obstacle; and determining a collision potential between each projected host vehicle location and each projected obstacle location. Until a maximum number of steps is reached, and while at least one projected host vehicle location has an associated collision potential below a collision threshold, the method further includes repeating the calculating, computing and determining steps.