公开(公告)号：US20240232647A9

公开(公告)日：2024-07-11

申请号：US18492646

申请日：2023-10-23

Applicant: Waymo LLC

Inventor： Zhaoqi Leng ,  Guowang Li ,  Chenxi Liu ,  Pei Sun ,  Tong He ,  Dragomir Anguelov ,  Mingxing Tan

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model on training data. In one aspect, one of the methods include: obtaining a training data set comprising a plurality of training inputs; obtaining data defining an original search space of a plurality of candidate data augmentation policies; generating, from the original search space, a compact search space that has one or more global hyperparameters; and training the machine learning model on the training data using one or more final data augmentation policies generated from the compact search space.

公开(公告)号：US20240135195A1

公开(公告)日：2024-04-25

申请号：US18492646

申请日：2023-10-22

Applicant: Waymo LLC

Inventor： Zhaoqi Leng ,  Guowang Li ,  Chenxi Liu ,  Pei Sun ,  Tong He ,  Dragomir Anguelov ,  Mingxing Tan

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model on training data. In one aspect, one of the methods include: obtaining a training data set comprising a plurality of training inputs; obtaining data defining an original search space of a plurality of candidate data augmentation policies; generating, from the original search space, a compact search space that has one or more global hyperparameters; and training the machine learning model on the training data using one or more final data augmentation policies generated from the compact search space.

公开(公告)号：US20250155578A1

公开(公告)日：2025-05-15

申请号：US18506925

申请日：2023-11-10

Applicant: Waymo LLC

Inventor： Yingwei Li ,  Ruizhongtai Qi ,  Yin Zhou ,  Chenxi Liu ,  Dragomir Anguelov

IPC: G01S17/931

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing point cloud data to generate an output. In one aspect, a method includes obtaining a sequence of multiple point cloud frames, wherein the sequence of multiple point cloud frames comprise a target point cloud frame and a plurality of other point cloud frames; processing one or more other point cloud frames to generate one or more respective predicted locations at the target timestamp for each of one or more objects detected in the one or more other point cloud frames; generating, based on the respective predicted locations at the target timestamp for each of one or more objects, a synthetic point cloud frame that is associated with the target timestamp; and processing at least the synthetic point cloud frame to generate one or more outputs that characterize an environment at the target timestamp.

公开(公告)号：US20240161398A1

公开(公告)日：2024-05-16

申请号：US18511566

申请日：2023-11-16

Applicant: Waymo LLC

Inventor： Tong He ,  Pei Sun ,  Zhaoqi Leng ,  Chenxi Liu ,  Mingxing Tan

IPC: G06T17/00 ,  G01S17/89 ,  G06T7/194 ,  G06T7/20 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06T17/00 ,  G01S17/89 ,  G06T7/194 ,  G06T7/20 ,  G06V10/44 ,  G06V10/82 ,  G06T2207/30241 ,  G06V2201/07

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output that characterizes a scene at a current time step. In one aspect, one of the systems include: a voxel neural network that generates a current early-stage feature representation of the current point cloud, a fusion subsystem that generates a current fused feature representation at the current time step; a backbone neural network that generates a current late-stage feature representation at the current time step, and an output neural network that generate an output that characterizes a scene at the current time step.

公开(公告)号：US20240062386A1

公开(公告)日：2024-02-22

申请号：US18235292

申请日：2023-08-17

Applicant: Waymo LLC

Inventor： Ruizhongtai Qi ,  Yurong You ,  Yingwei Li ,  Chenxi Liu ,  Yin Zhou

IPC: G06T7/246 ,  G06T7/215

CPC classification number: G06T7/246 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20084 ,  G06T2207/30252

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sensor data, e.g., laser sensor data, using neural networks. One of the methods includes obtaining a temporal sequence of multiple three-dimensional point clouds generated from sensor readings of an environment collected by one or more sensors within a given time period, each three-dimensional point cloud comprising a respective plurality of points in a first coordinate system; processing, using a feature extraction neural network, an input that comprises data derived from the temporal sequence of multiple three-dimensional point clouds to generate a feature embedding; receiving a query that specifies one time point within the given time period; and generating, from the feature embedding and conditioned on the query, one or more outputs that characterize one or more objects in the environment at the time point specified in the received query.

公开(公告)号：US20230351691A1

公开(公告)日：2023-11-02

申请号：US18120989

申请日：2023-03-13

Applicant: Waymo LLC

Inventor： Pei Sun ,  Mingxing Tan ,  Weiyue Wang ,  Fei Xia ,  Zhaoqi Leng ,  Dragomir Anguelov ,  Chenxi Liu

IPC: G06T17/20

CPC classification number: G06T17/20 ,  G06T2210/56

Abstract: Methods, systems, and apparatus for processing point clouds using neural networks to perform a machine learning task. In one aspect, a system comprises one or more computers configured to obtain a set of point clouds captured by one or more sensors. Each point cloud includes a respective plurality of three-dimensional points. The one or more computers assign the three-dimensional points to respective voxels in a voxel grid, where the grid of voxels includes non-empty voxels to which one or more points are assigned and empty voxels to which no points are assigned. For each non-empty voxel, the one or more computers generate initial features based on the points that are assigned to the non-empty voxel. The one or more computers generate multi-scale features of the voxel grid, and the one or more computers generate an output for a point cloud processing task using the multi-scale features of the voxel grid.