Systems and methods for graph-based localization and mapping
First Claim
1. A method of performing simultaneous localization and mapping (SLAM) optimization, the method comprising:
- receiving, by one or more processors, traces collected by multiple portable devices moving within a geographic area that includes an indoor region, each of the traces including measurements of wireless signals sources at different times by a same device;
determining, for each of a plurality of cells in the geographic area, respective probabilities of moving in various directions relative to the cell, the plurality of cells defining a motion map for the geographic area; and
generating, by the one or more processors, location estimates for the portable devices and the signal sources using graph-based SLAM optimization of the location estimates, including, for at least some of the location estimates;
determining to which of the plurality of cells of the motion map the location estimate corresponds, andapplying 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.
1 Assignment
0 Petitions
Accused Products
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.
19 Citations
15 Claims
-
1. A method of performing simultaneous localization and mapping (SLAM) optimization, the method comprising:
-
receiving, by one or more processors, traces collected by multiple portable devices moving within a geographic area that includes an indoor region, each of the traces including measurements of wireless signals sources at different times by a same device; determining, for each of a plurality of cells in the geographic area, respective probabilities of moving in various directions relative to the cell, the plurality of cells defining a motion map for the geographic area; and generating, by the one or more processors, location estimates for the portable devices and the signal sources using graph-based SLAM optimization of the location estimates, including, for at least some of the location estimates; determining to which of the plurality of 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. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computing system configured to perform simultaneous localization and mapping (SLAM) optimization, the computing system comprising:
-
processing hardware; and a non-transitory computer-readable medium storing thereon instructions that, when executed by the processing hardware, cause the system to; receive traces collected by multiple portable devices moving within a geographic area that includes an indoor region, each of the traces including measurements of wireless signals sources at different times by a same device, determine, for each of a plurality of cells in the geographic area, respective probabilities of moving in various directions relative to the cell, the plurality of cells defining a motion map for the geographic area, generate location estimates for the portable devices and the signal sources using graph-based SLAM optimization of the location estimates, including, for at least some of the location estimates; determine to which of the plurality of cells of the motion map the location estimate corresponds, and apply 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. - View Dependent Claims (9, 10, 11, 12, 13, 14, 15)
-
Specification