公开(公告)号：US10671083B2

公开(公告)日：2020-06-02

申请号：US15703879

申请日：2017-09-13

Applicant: TuSimple, Inc.

Inventor： Wentao Zhu ,  Yi Wang ,  Yi Luo

IPC: G05D1/02 ,  G06K9/46 ,  G01C21/32 ,  G06K9/62 ,  G06T7/246 ,  G01C21/16 ,  G01S17/89 ,  G06N5/02 ,  G06N20/00 ,  G06T7/269 ,  G01C22/00 ,  G01S17/42 ,  G01S7/48 ,  G01S17/86

Abstract: A system for visual odometry is disclosed. The system includes: an internet server, comprising: an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: extracting representative features from a pair input images in a first convolution neural network (CNN) in a visual odometry model; merging, in a first merge module, outputs from the first CNN; decreasing feature map size in a second CNN; generating a first flow output for each layer in a first deconvolution neural network (DNN); merging, in a second merge module, outputs from the second CNN and the first DNN; generating a second flow output for each layer in a second DNN; and reducing accumulated errors in a recurrent neural network (RNN).