公开(公告)号：US10310087B2

公开(公告)日：2019-06-04

申请号：US15609256

申请日：2017-05-31

Applicant: Uber Technologies, Inc.

Inventor： Ankit Laddha ,  J. Andrew Bagnell ,  Varun Ramakrishna ,  Yimu Wang ,  Carlos Vallespi-Gonzalez

IPC: G06K9/00 ,  G01S17/89 ,  G01S17/93 ,  G01S17/66 ,  G01S7/48 ,  G01S17/50 ,  G01S13/93

Abstract: Systems and methods for detecting and classifying objects that are proximate to an autonomous vehicle can include receiving, by one or more computing devices, LIDAR data from one or more LIDAR sensors configured to transmit ranging signals relative to an autonomous vehicle, generating, by the one or more computing devices, a data matrix comprising a plurality of data channels based at least in part on the LIDAR data, and inputting the data matrix to a machine-learned model. A class prediction for each of one or more different portions of the data matrix and/or a properties estimation associated with each class prediction generated for the data matrix can be received as an output of the machine-learned model. One or more object segments can be generated based at least in part on the class predictions and properties estimations. The one or more object segments can be provided to an object classification and tracking application.

公开(公告)号：US20180348374A1

公开(公告)日：2018-12-06

申请号：US15609256

申请日：2017-05-31

Applicant: Uber Technologies, Inc.

Inventor： Ankit Laddha ,  James Andrew Bagnall ,  Varun Ramakrishna ,  Yimu Wang ,  Carlos Vallespi-Gonzalez

IPC: G01S17/89 ,  G01S17/42 ,  G01S17/93 ,  G06K9/00 ,  G01S7/481 ,  G01S7/486 ,  G01S17/50

CPC classification number: G01S17/89 ,  G01S7/4815 ,  G01S7/4863 ,  G01S7/4865 ,  G01S17/42 ,  G01S17/50 ,  G01S17/936 ,  G06K9/00201 ,  G06K9/00805

Abstract: Systems and methods for detecting and classifying objects that are proximate to an autonomous vehicle can include receiving, by one or more computing devices, LIDAR data from one or more LIDAR sensors configured to transmit ranging signals relative to an autonomous vehicle, generating, by the one or more computing devices, a data matrix comprising a plurality of data channels based at least in part on the LIDAR data, and inputting the data matrix to a machine-learned model. A class prediction for each of one or more different portions of the data matrix and/or a properties estimation associated with each class prediction generated for the data matrix can be received as an output of the machine-learned model. One or more object segments can be generated based at least in part on the class predictions and properties estimations. The one or more object segments can be provided to an object classification and tracking application.