Navigation using sensor fusion

Patent metadata

Field	Value
Publication number	US-10330489-B1
Application number	US-201715585451-A
Country	US
Kind code	B1
Filing date	May 3, 2017
Priority date	Mar 14, 2014
Publication date	Jun 25, 2019
Grant date	Jun 25, 2019

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving erroneous movement signals and for providing navigation instructions. One of the methods includes receiving data from two or more sensors, synchronizing the received data, determining a first subset of the synchronized data from the camera for a particular period of time and a second subset of the synchronized data from the other sensor for the particular period of time, comparing the first subset with the second subset to determine whether the first subset and the second subset indicate an erroneous movement signal, based on determining that the first subset and the second subset indicate an erroneous movement signal, selecting data for one of the sensors based on a sensor priority scheme for the sensors, and resolving the erroneous movement signal based on the selected data for the one of the sensors.

First claim

What is claimed is:

1. An apparatus, comprising:
two or more sensors comprising a camera and another sensor;
a data processing apparatus; and
a non-transitory computer readable storage medium in data communication with the data processing apparatus and storing instructions executable by the data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising:
receiving data from the two or more sensors;
synchronizing the received data from the two or more sensors so that the data from the camera corresponds in time to the data from the other sensor;
determining a first subset of the synchronized data from the camera for a period of time and a second subset of the synchronized data from the other sensor for the period of time, the first subset of the synchronized data and the second subset of the synchronized data each being representative of movement of the apparatus and the first subset of the synchronized data being representative of objects in a physical area surrounding a physical location of the apparatus;
determining a plurality of feature points of the physical area using at least the first subset of the synchronized data and the second subset of the synchronized data;
determining, using at least the first subset of the synchronized data, that at least one of the plurality of feature points represents a moving object; and
creating a map using one or more of the plurality of feature points, the one or more of the plurality of feature points not including the at least one of the plurality of feature points that represents the moving object.

2. The apparatus of claim 1 , wherein determining the plurality of feature points of the physical area using at least the first subset of the synchronized data and the second subset of the synchronized data comprises:
comparing the first subset of the synchronized data with the second subset of the synchronized data to determine whether the first subset of the synchronized data and the second subset indicate an erroneous movement signal; and
based on determining that the first subset of the synchronized data and the second subset indicate an erroneous movement signal, detecting the plurality of feature points in one or more images captured by the camera and represented by the first subset of the synchronized data.

3. The apparatus of claim 2 , wherein detecting the plurality of feature points in the one or more images captured by the camera and represented by the first subset of the synchronized data comprises detecting the plurality of feature points in two or more images captured by the camera and represented by the first subset of the synchronized data.

4. The apparatus of claim 2 , wherein detecting the plurality of feature points in one or more images captured by the camera and represented by the first subset of the synchronized data comprises:
determining a sensor priority scheme for the two or more sensors;
determining, using the sensor priority scheme, that the camera has a higher priority than the other sensor; and
selecting the first subset of the synchronized data in response to determining that the camera has a higher priority than the other sensor.

5. The apparatus of claim 1 , the operations comprising:
receiving second data from the two or more sensors;
synchronizing the received second data from the two or more sensors so that the second data from the camera corresponds in time to the second data from a third sensor;
determining a third subset of the synchronized second data from the camera for a second period of time and a fourth subset of the synchronized second data from the third sensor for the second period of time;
comparing the third subset of the synchronized second data with the fourth subset of the synchronized second data to determine whether the third subset and the fourth subset indicate an erroneous movement signal;
based on determining that the third subset and the fourth subset indicate an erroneous movement signal, selecting, from the third subset and the fourth subset of the synchronized second data, third data for one of the sensors, the selection based on a sensor priority scheme for the sensors;
determining that the selected third data for one of the sensors indicate that the apparatus is not moving; and
discarding the third subset and the fourth subset of the synchronized second data in response to determining that the selected third data for one of the sensors indicate that the apparatus is not moving.

6. The apparatus of claim 5 , wherein discarding the first subset and the second subset of the synchronized second data comprises determining not to update the map using the third subset and the fourth subset of the synchronized second data.

7. The apparatus of claim 1 , the operations comprising determining navigation instructions using one or more of the plurality of feature points.

8. The apparatus of claim 7 , wherein determining the navigation instructions using one or more of the plurality of feature points comprises determining the navigation instructions using one or more of the at least one of the plurality of feature points that represents the moving object.

9. A computer-implemented method comprising:
receiving, at a computer, data from two or more sensors included in the computer, the two or more sensors including a camera and another sensor;
synchronizing the received data from the two or more sensors so that the data from the camera corresponds in time to the data from the other sensor;
determining a first subset of the synchronized data from the camera for a period of time and a second subset of the synchronized data from the other sensor for the period of time, the first subset of the synchronized data and the second subset of the synchronized data each being representative of movement of the computer and the first subset of the synchronized data being representative of objects in a physical area surrounding a physical location of the computer;
determining a plurality of feature points of the physical area using at least the first subset of the synchronized data and the second subset of the synchronized data;
determining, using at least the first subset of the synchronized data, that at least one of the plurality of feature points represents a moving object; and
creating a map using one or more of the plurality of feature points, the one or more of the plurality of feature points not including the at least one of the plurality of feature points that represents the moving object.

10. The method of claim 9 , wherein determining the plurality of feature points of the physical area using at least the first subset of the synchronized data and the second subset of the synchronized data comprises:
comparing the first subset of the synchronized data with the second subset of the synchronized data to determine whether the first subset of the synchronized data and the second subset indicate an erroneous movement signal; and
based on determining that the first subset of the synchronized data and the second subset indicate an erroneous movement signal, detecting the plurality of feature points in one or more images captured by the camera and represented by the first subset of the synchronized data.

11. The method of claim 10 , wherein detecting the plurality of feature points in the one or more images captured by the camera and represented by the first subset of the synchronized data comprises detecting the plurality of feature points in two or more images captured by the camera and represented by the first subset of the synchronized data.

12. The method of claim 10 , wherein detecting the plurality of feature poin

Assignees

• Google Llc

Inventors

• Andersson Eve Astrid
• Burkhardt Casey John
• Lundblad John Ove Peter Nilsson
• Tseng David
• Chen Charles L
• Zheng Ying
• Raman Tiruvilwamalai Venkatram

Classifications

• H04W4/023

  using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds · CPC title

• H04N13/20 Primary

  Image signal generators · CPC title

• G05D1/00

  Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots (drive control systems specially adapted for autonomous road vehicles B60W60/00) · CPC title

• G01C22/00

  Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers · CPC title

• G01B11/2755

  using photoelectric detection means · CPC title