Localization by learning of wave-signal distributions
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G05D-001/02
G05B-019/00
B25J-009/16
G06F-019/00
B25J-005/00
출원번호
US-0248352
(2016-08-26)
등록번호
US-9623557
(2017-04-18)
발명자
/ 주소
Gutmann, Steffen
Eade, Ethan
Fong, Philip
Munich, Mario
출원인 / 주소
iRobot Corporation
대리인 / 주소
Fish & Richardson P.C.
인용정보
피인용 횟수 :
1인용 특허 :
77
초록▼
A robot having a signal sensor configured to measure a signal, a motion sensor configured to measure a relative change in pose, a local correlation component configured to correlate the signal with the position and/or orientation of the robot in a local region including the robot's current position,
A robot having a signal sensor configured to measure a signal, a motion sensor configured to measure a relative change in pose, a local correlation component configured to correlate the signal with the position and/or orientation of the robot in a local region including the robot's current position, and a localization component configured to apply a filter to estimate the position and optionally the orientation of the robot based at least on a location reported by the motion sensor, a signal detected by the signal sensor, and the signal predicted by the local correlation component. The local correlation component and/or the localization component may take into account rotational variability of the signal sensor and other parameters related to time and pose dependent variability in how the signal and motion sensor perform. Each estimated pose may be used to formulate new or updated navigational or operational instructions for the robot.
대표청구항▼
1. An autonomous mobile robot comprising: a signal sensor configured to detect a portion of a signal emitted into an environment of the robot and provide a value representing a property of the detected portion of the signal;a movement system configured to move the robot along a floor surface of the
1. An autonomous mobile robot comprising: a signal sensor configured to detect a portion of a signal emitted into an environment of the robot and provide a value representing a property of the detected portion of the signal;a movement system configured to move the robot along a floor surface of the environment;a motion sensor configured to detect a motion of the robot; anda controller configured to: determine a predicted value of the property of the detected portion of the signal for a particular pose of the robot,estimate a pose of the robot based at least in part on the provided value of the property, the detected motion of the robot, and the predicted value of the property for the particular pose, andcontrol, based on the estimated pose, an operation of the movement system to navigate the robot about the floor surface. 2. The robot of claim 1, wherein the emitted signal comprises a Wi-Fi signal, and the property is an electromagnetic property of the Wi-Fi signal. 3. The robot of claim 1, wherein the emitted signal comprises a magnetic field, and the property is a property of the magnetic field. 4. The robot of claim 1, wherein the property of the emitted signal is a strength of the signal. 5. The robot of claim 1, wherein the motion sensor is configured to detect the motion of the robot by detecting a relative change in location of the robot. 6. The robot of claim 1, wherein the motion sensor is further configured to detect the motion of the robot by detecting a relative change in orientation of the robot. 7. The robot of claim 1, wherein the signal sensor is configured to detect another portion of the emitted signal and provide another value representing a property of the other detected portion of the emitted signal;the motion sensor is configured to detect another motion of the robot; andthe controller is configured to: determine another predicted value of the property of the other detected portion based at least in part on extrapolating from the predicted value,estimate another pose of the robot based at least in part on the other detected motion, the other predicted value, and the other provided value, andcontrol the operation of the movement system to navigate the robot about the floor surface based on the other estimated pose. 8. The robot of claim 1, wherein the controller is configured to control the operation of the movement system to navigate the robot by localizing the robot based on an observation of a feature represented by a set of values of the property of the detected portion of the signal. 9. The robot of claim 1, wherein the controller is configured to generate a map representing a distribution of the signal throughout the environment, andcontrol the operation of the movement system to navigate the robot about the floor surface based on the map. 10. The robot of claim 1, wherein the robot is an autonomous vacuum cleaner. 11. A method of navigating an autonomous mobile robot through an environment, the method comprising: detecting a portion of a signal emitted into the environment;determining a value representing a property of the detected portion of the signal;detecting a motion of the robot along a floor surface of the environment;determining a predicted value of the property of the signal for a particular pose of the robot;estimating a pose of the robot based at least in part on the determined value of the property, the detected motion of the robot, and the predicted value of the property; andnavigate the robot about the floor surface based on the estimated pose. 12. The method of claim 11, wherein the emitted signal comprises a Wi-Fi signal, and the property is a property of the Wi-Fi signal. 13. The method of claim 11, wherein the emitted signal comprises a magnetic field, and the property is a property of the magnetic field. 14. The method of claim 11, wherein the property of the emitted signal is a strength of the signal. 15. The method of claim 11, wherein detecting the motion of the robot comprises detecting a relative change in location of the robot. 16. The method of claim 11, wherein detecting the motion of the robot comprises detecting a relative change in orientation of the robot. 17. The method of claim 11, further comprising: detecting another portion of a signal emitted into an environment of the robot and providing another value representing a property of the other detected portion of the signal; detecting another motion of the robot;determining another predicted value of the property based at least in part on extrapolating from the predicted value of the property;estimating another pose of the robot based at least in part on the other detected motion, the other predicted value, and the other provided value; andnavigating the robot about the floor surface based on the other estimated pose. 18. The method of claim 11, wherein navigating the robot about the floor surface based on the estimated pose comprises localizing the robot based on an observation of a feature corresponding to a set of values of the property of the detected portion of the signal. 19. The method of claim 11, further comprising generating a map representing a distribution of the signal throughout the environment, wherein navigating the robot about the environment comprises navigating the robot about the floor surface based on the map. 20. The method of claim 11, wherein navigating the robot about the environment comprises navigating the robot about the floor surface while executing a cleaning operation in the environment.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (77)
Lofgren Gunnar K. (Charlotte NC) Netzler Gran P. R. (Frilless SEX), Apparatus and method for optical guidance system for automatic guided vehicle.
Halsall James R. (Runcorn GB2) Larcombe Michael H. E. (Cannon Park GB2) Robertson James R. (Northwich GB2) Rogers Mark A. M. (Chester GB2), Driverless vehicle autoguide by light signals and two directional detectors.
Burke Steven A. (Champlin MN) Liang Cao Z. (Tianjin OH CNX) Hall Ernest L. (Cincinnati OH), Guiding an unmanned vehicle by reference to overhead features.
Eric Richard Bartsch ; Charles William Fisher ; Paul Amaat France ; James Frederick Kirkpatrick ; Gary Gordon Heaton ; Thomas Charles Hortel ; Arseni Velerevich Radomyselski ; James Randy Stig, Home cleaning robot.
Boultinghouse Karlan D. (Sandia Park NM) Schoeneman J. Lee (Albuquerque NM) Tise Bertice L. (Albuquerque NM), Method for laser-based two-dimensional navigation system in a structured environment.
Bauer Rudolf (Neubiberg DEX), Method for producing a cellularly structured environment map of a self-propelled, mobile unit that orients itself in the.
Evans ; Jr. John M. (Brookfield CT) King Steven J. (Woodbury CT) Weiman Carl F. R. (Westport CT), Mobile robot navigation employing retroreflective ceiling features.
Everett ; Jr. Hobart R. (San Diego CA) Gilbreath Gary A. (San Diego CA) Laird Robin T. (San Diego CA), Navigational control system for an autonomous vehicle.
Dyer Robert D. (Richland WA) Eschbach Eugene A. (Richland WA) Griffin Jeffrey W. (Kennewick WA) Lind Michael A. (Durham OR) Buck Erville C. (Eugene OR) Buck Roger L. (Springfield OR), Optical guidance system for industrial vehicles.
Bauer Rudolf,DEX ; Wienkop Uwe,DEX, Process for preparing an area plan having a cellular structure and comprising a unit moving automatically and positioned in said area using sensors based on wave reflection.
Scheible, Guntram; Smailus, Bernd; Klaus, Martin; Garrels, Kai; Heinemann, Lothar, System for wirelessly supplying a large number of actuators of a machine with electrical power.
Evans ; Jr. John M. (Brookfield CT) Weiman Carl F. R. (Westport CT) King Steven J. (Woodbury CT), Visual navigation and obstacle avoidance structured light system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.