公开(公告)号：US20180077534A1

公开(公告)日：2018-03-15

申请号：US15703779

申请日：2017-09-13

Applicant: GOOGLE INC.

Inventor： Etienne Le Grand ,  Mohammed Khider ,  Luigi Bruno

IPC: H04W4/02 ,  H04W4/04 ,  H04W24/10

CPC classification number: H04W4/029 ,  H04W4/04 ,  H04W24/10

Abstract: Traces are collected by multiple portable devices moving with an area that includes an indoor region, with each of the traces including measurements of wireless signals at different times, including measurements of wireless signals from signal sources disposed within the area. A motion map for the geographic area is constructed by determining, for each of the cells that make the motion map, respective probabilities of moving in various directions relative to each cell. Location estimates for the portable devices and the signal sources are generated using graph-based SLAM optimization of the location estimates. The graph-based SLAM optimization includes determining to which of the cells of the motion map the location estimate corresponds and applying the measurements of wireless signals sources and the set of probabilities of the cells as a first constraint and a second constraint, respectively, in the graph-based SLAM optimization.

公开(公告)号：US10075818B2

公开(公告)日：2018-09-11

申请号：US15703779

申请日：2017-09-13

Applicant: GOOGLE INC.

Inventor： Etienne Le Grand ,  Mohammed Khider ,  Luigi Bruno

IPC: H04W64/00 ,  H04W4/029 ,  H04W4/02 ,  H04W24/10 ,  H04W4/04

CPC classification number: H04W4/029 ,  G01C21/206 ,  H04W4/025 ,  H04W4/30 ,  H04W4/33 ,  H04W24/10

Abstract: Traces are collected by multiple portable devices moving with an area that includes an indoor region, with each of the traces including measurements of wireless signals at different times, including measurements of wireless signals from signal sources disposed within the area. A motion map for the geographic area is constructed by determining, for each of the cells that make the motion map, respective probabilities of moving in various directions relative to each cell. Location estimates for the portable devices and the signal sources are generated using graph-based SLAM optimization of the location estimates. The graph-based SLAM optimization includes determining to which of the cells of the motion map the location estimate corresponds and applying the measurements of wireless signals sources and the set of probabilities of the cells as a first constraint and a second constraint, respectively, in the graph-based SLAM optimization.