-
公开(公告)号：US10013773B1
公开(公告)日：2018-07-03
申请号：US15381288
申请日：2016-12-16
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Alexander Krizhevsky , Wan-Yen Lo
CPC classification number: G06N3/08 , G06K9/00791 , G06K9/627 , G06K9/68 , G06N3/0454 , G06N3/084 , G06T7/74 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084
Abstract: A neural network system for identifying positions of objects in an input image can include an object detector neural network, a memory interface subsystem, and an external memory. The object detector neural network is configured to, at each time step of multiple successive time steps, (i) receive a first neural network input that represents the input image and a second neural network input that identifies a first set of positions of the input image that have each been classified as showing a respective object of the set of objects, and (ii) process the first and second inputs to generate a set of output scores that each represents a respective likelihood that an object that is not one of the objects shown at any of the positions in the first set of positions is shown at a respective position of the input image that corresponds to the output score.
-
公开(公告)号：US20190033085A1
公开(公告)日：2019-01-31
申请号：US15662007
申请日：2017-07-27
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Mayank Bansal , Alexander Krizhevsky
Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.
-
公开(公告)号：US11928866B2
公开(公告)日：2024-03-12
申请号：US17567729
申请日：2022-01-03
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Alexander Krizhevsky
CPC classification number: G06V20/58 , G05D1/0221 , G06N3/045 , G06N3/08 , G06N3/084 , B60R2300/8093
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.
-
公开(公告)号：US11256983B2
公开(公告)日：2022-02-22
申请号：US15662031
申请日：2017-07-27
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Mayank Bansal , Alexander Krizhevsky
IPC: G06N3/08 , G05D1/02 , G06N3/04 , G06N3/00 , G01C21/34 , G01S17/931 , G01S17/42 , G01S13/86 , G01S17/86 , G01S13/931
Abstract: Systems, methods, devices, and other techniques for training a trajectory planning neural network system to determine waypoints for trajectories of vehicles. A neural network training system can train the trajectory planning neural network system on the multiple training data sets. Each training data set can include: (i) a first training input that characterizes a set of waypoints that represent respective locations of a vehicle at each of a series of first time steps, (ii) a second training input that characterizes at least one of (a) environmental data that represents a current state of an environment of the vehicle or (b) navigation data that represents a planned navigation route for the vehicle, and (iii) a target output characterizing a waypoint that represents a target location of the vehicle at a second time step that follows the series of first time steps.
-
公开(公告)号：US11216674B2
公开(公告)日：2022-01-04
申请号：US16853517
申请日：2020-04-20
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Alexander Krizhevsky
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.
-
Patent Agency Ranking
公开(公告)号：US10883844B2
公开(公告)日：2021-01-05
申请号：US15662007
申请日：2017-07-27
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Mayank Bansal , Alexander Krizhevsky
Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.
-
公开(公告)号：US20200174490A1
公开(公告)日：2020-06-04
申请号：US16628086
申请日：2018-07-27
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Mayank Bansal , Alexander Krizhevsky
Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.
-
公开(公告)号：US20190034794A1
公开(公告)日：2019-01-31
申请号：US15662031
申请日：2017-07-27
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Mayank Bansal , Alexander Krizhevsky
Abstract: Systems, methods, devices, and other techniques for training a trajectory planning neural network system to determine waypoints for trajectories of vehicles. A neural network training system can train the trajectory planning neural network system on the multiple training data sets. Each training data set can include: (i) a first training input that characterizes a set of waypoints that represent respective locations of a vehicle at each of a series of first time steps, (ii) a second training input that characterizes at least one of (a) environmental data that represents a current state of an environment of the vehicle or (b) navigation data that represents a planned navigation route for the vehicle, and (iii) a target output characterizing a waypoint that represents a target location of the vehicle at a second time step that follows the series of first time steps.
-
公开(公告)号：US11783180B1
公开(公告)日：2023-10-10
申请号：US16983957
申请日：2020-08-03
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Alexander Krizhevsky , Wan-Yen Lo
CPC classification number: G06N3/08 , G05D1/0088 , G06N3/04 , G06N7/01
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating object predictions using a neural network. One of the methods includes receiving respective projections of a plurality of channels of input sensor data, wherein each channel of input sensor data represents different respective characteristics of electromagnetic radiation reflected off of one or more objects. Each of the projections of the plurality of channels of input sensor data are provided to a neural network subsystem trained to receive projections of input sensor data as input and to provide an object prediction as an output. At the output of the neural network subsystem, an object prediction that predicts a region of space that is likely to be occupied by an object is received.
-
公开(公告)号：US11531894B1
公开(公告)日：2022-12-20
申请号：US17013117
申请日：2020-09-04
Applicant: Waymo LLC
Inventor： Abhijit Ogale , Alexander Krizhevsky , Wan-Yen Lo
Abstract: A neural network system for identifying positions of objects in an input image can include an object detector neural network, a memory interface subsystem, and an external memory. The object detector neural network is configured to, at each time step of multiple successive time steps, (i) receive a first neural network input that represents the input image and a second neural network input that identifies a first set of positions of the input image that have each been classified as showing a respective object of the set of objects, and (ii) process the first and second inputs to generate a set of output scores that each represents a respective likelihood that an object that is not one of the objects shown at any of the positions in the first set of positions is shown at a respective position of the input image that corresponds to the output score.
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.013 seconds)
