Systems and methods for using multiple hypotheses in a visual simultaneous localization and mapping system
First Claim
1. A method for localizing a mobile device in a visual simultaneous localization and mapping system, the method comprising:
- visually observing an environment via a camera of the mobile device;
maintaining a map of landmarks in a data store on the mobile device based at least in part on visual observations of the environment obtained from the camera of the mobile device using a processing system on the mobile device;
receiving an indication that a landmark has been recognized and estimating a visually-measured relative pose to the landmark, wherein the relative pose reveals a change in pose from (i) the pose when the landmark was created and stored in the data store to (ii) the pose when the physical landmark was re-observed;
receiving data from at least one dead reckoning sensor of the mobile device at the processing system on the mobile device and storing the data, wherein the data from the dead reckoning sensor relates to movement of the mobile device within the environment;
using data from the dead reckoning sensor to estimate a change in pose;
determining a current device pose estimate based upon the relative pose and the data from the dead reckoning sensor, wherein visual observations of landmarks obtained from the camera sensor compensates for drift in the dead reckoning sensors,wherein determining a current device pose further comprises using the change in pose estimated from the data from the dead reckoning sensor and using a relative pose to calculate the current device pose estimate.
3 Assignments
0 Petitions
Accused Products
Abstract
The invention is related to methods and apparatus that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments, such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.
9 Citations
20 Claims
-
1. A method for localizing a mobile device in a visual simultaneous localization and mapping system, the method comprising:
-
visually observing an environment via a camera of the mobile device; maintaining a map of landmarks in a data store on the mobile device based at least in part on visual observations of the environment obtained from the camera of the mobile device using a processing system on the mobile device; receiving an indication that a landmark has been recognized and estimating a visually-measured relative pose to the landmark, wherein the relative pose reveals a change in pose from (i) the pose when the landmark was created and stored in the data store to (ii) the pose when the physical landmark was re-observed; receiving data from at least one dead reckoning sensor of the mobile device at the processing system on the mobile device and storing the data, wherein the data from the dead reckoning sensor relates to movement of the mobile device within the environment; using data from the dead reckoning sensor to estimate a change in pose; determining a current device pose estimate based upon the relative pose and the data from the dead reckoning sensor, wherein visual observations of landmarks obtained from the camera sensor compensates for drift in the dead reckoning sensors, wherein determining a current device pose further comprises using the change in pose estimated from the data from the dead reckoning sensor and using a relative pose to calculate the current device pose estimate. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 19, 20)
-
-
14. An apparatus for autonomous localization and mapping, the apparatus comprising:
-
a camera configured to visually observe an environment; a processor configured to execute computer instructions; a tangible, non-transitory computer readable medium configured to store a computer program, wherein the computer program directs the processor to; maintain a map of landmarks in a data store based at least in part on visual observations of the environment obtained from the camera; receive an indication that a landmark has been recognized and estimating a visually-measured relative pose to the landmark, wherein the relative pose reveals a change in pose from (i) the pose when the landmark was created and stored in the data store to (ii) the pose when the physical landmark was re-observed; receive data from at least one dead reckoning sensor and storing the data, wherein the data from the dead reckoning sensor relates to movement of the camera within the environment; using data from the dead reckoning sensor to estimate a change in pose; and determine a current device pose estimate based upon the relative pose and the data from the dead reckoning sensor, wherein visual observations of landmarks obtained from the camera compensates for drift in the dead reckoning sensors, wherein determining a current device pose further comprises using the change in pose estimated from the data from the dead reckoning sensor and using a relative pose to calculate the current device pose estimate. - View Dependent Claims (15, 16, 17, 18)
-
Specification