IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0739902
(2003-12-17)
|
발명자
/ 주소 |
- Karlsson,L. Niklas
- Pirjanian,Paolo
- Goncalves,Luis Filipe Domingues
- Di Bernardo,Enrico
|
출원인 / 주소 |
|
대리인 / 주소 |
Knobbe Martens Olson &
|
인용정보 |
피인용 횟수 :
166 인용 특허 :
31 |
초록
▼
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 ma
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.
대표청구항
▼
What is claimed is: 1. A method of localizing a mobile device in a multiple-particle autonomous localization and mapping system, the method comprising: performing autonomous localization and mapping with a plurality of particles, where a particle includes a device pose and a map, where the map incl
What is claimed is: 1. A method of localizing a mobile device in a multiple-particle autonomous localization and mapping system, the method comprising: performing autonomous localization and mapping with a plurality of particles, where a particle includes a device pose and a map, where the map includes one or more landmarks; receiving an indication that a landmark has been detected; and updating at least one particle from the plurality of particles at least partly in response to receiving the indication of the detected landmark, wherein updating further comprises: selectively categorizing a particle as one of a first type of particle or a second type of particle; and calculating an updated device pose estimate for a particle, wherein the technique used to calculate the updated device pose estimate is selected according to the type associated with the particle. 2. The method as defined in claim 1, wherein calculating the updated device pose estimate further comprises calculating the updated device pose estimate for a primary particle based at least in part on data, from a first sensor, and calculating the updated device pose estimate for a dual particle based at least in part on data from a second sensor, where the second sensor is different from the first sensor. 3. The method as defined in claim 1, wherein calculating the updated device pose estimate further comprises calculating the updated device pose for a primary type of particle based at least in part on data from a dead reckoning sensor, and calculating the updated device pose estimate for a dual type of particle based at least in part on data from a visual sensor. 4. The method as defined in claim 1, wherein calculating the updated device pose estimate further comprises: using a prior pose estimate and dead reckoning sensor data to compute a new pose for particles of primary type based on the change in pose estimated from the dead reckoning sensor data; receiving a visually-measured relative pose to the landmark, where the landmark has been matched using visual features from a visual sensor coupled to the mobile device, where the relative pose corresponds to a visually-measured difference in pose between a landmark pose and a pose corresponding to the visual observation; and using the landmark pose estimate and the visually-measured relative pose to compute the new pose estimate for particles of dual type. 5. The method as defined in claim 1, further comprising: using dead reckoning data to estimate a change in pose from a prior update to the particles; wherein receiving the indication that a landmark has been detected further comprises receiving a visual measurement of a relative pose of the device with respect to a landmark, where the landmark forms part of the maps of the multiple particles; and wherein calculating the device pose for the particle further comprises using the change in pose estimated from dead reckoning data and using the relative pose to calculate an updated device pose estimate. 6. The method as defined in claim 1, wherein selectively associating the particles is performed each time that the plurality of particles are updated when a landmark is detected. 7. The method as defined in claim 1, wherein selectively associating the particle further comprises randomly selecting which type is associated with the particle such that prior to associating, a first particle and a second particle from the plurality of particles have approximately the same probability of being associated as primary particles. 8. The method as defined in claim 1, wherein selectively associating further comprises apportioning the multiple particles such that a particle has a probability of being associated with the first type of particle with about a predetermined rate of probability. 9. The method as defined in claim 8, wherein the predetermined value is about 0.9 or 90%. 10. The method as defined in claim 1, wherein the technique used to calculate the updated device pose estimate for the first type of particle further comprises: using a prior pose estimate, the dead reckoning sensor data, and simulated random noise to compute a new device pose estimate termed perturbed predicted device pose; using the perturbed predicted device pose and a visually-measured pose of the device relative to the landmark to compute a hypothetical landmark pose; computing an importance factor for the particle, where the importance factor is based at least in part on an uncertainty measure and a comparison between the calculated hypothetical landmark pose and a prior landmark pose estimate; and using the perturbed predicted pose with the importance factor as the updated device pose. 11. The method as defined in claim 10, wherein the simulated random noise exhibits an uncertainty measure for the dead reckoning sensor data. 12. The method as defined in claim 11, wherein: a new device pose Sm,pred equals description="In-line Formulae" end="lead"S m,pred=(xl, yl, θl) T=(xm,pred, ym,pred, θ m,pred)T;description="In-line Formulae" end="tail" a visually-measured pose Sm,meas equals a perturbed visually-measured pose {tilde over (S)}m,meas equals a variable Δ equals a variable Δ3 equals description="In-line Formulae" end="lead"Δ 3=[(Δ3+π)mod2π]-π; anddescription="In-line Formulae" end="tail" an importance factor wm for a particle m equals: 13. The method as defined in claim 1, wherein the technique used to calculate the updated device pose for the second type of particle termed dual particle further comprises: using a landmark pose estimate corresponding to the landmark and a visually-measured relative pose to compute a hypothetical device pose; perturbing the hypothetical device pose with simulated random noise; computing an importance factor for the particle, where the importance factor is based at least in part on an uncertainty measure and a comparison between the hypothetical device pose and a predicted device pose from a prior pose estimate and the dead reckoning sensor data; and using the hypothetical device pose with the importance factor as the updated device pose. 14. The method as defined in 13, wherein the simulated random noise exhibits an uncertainty measure estimated for a visual sensor. 15. The method as defined in 14, where the dead reckoning uncertainty measure corresponds to an odometer covariance matrix Codom. 16. The method as defined in claim 1, further comprising resampling selected particles from the plurality of particles. 17. A circuit for a mobile device that is configured to localize the mobile device in a multiple-particle autonomous localization and mapping system, the circuit comprising: a means for performing autonomous localization and mapping with a plurality of particles, where a particle includes a device pose and a map, where the map includes one or more landmarks; a means for receiving an indication that a landmark has been detected; and a means for updating at least one particle from the plurality of particles at least partly in response to receiving the indication of the detected landmark, wherein the means for updating further comprises: a means for selectively categorizing a particle as one of a first type of particle or a second type of particle; and a means for calculating an updated device pose estimate for a particle, wherein the technique used to calculate the updated device pose estimate is selected according to the type associated with the particle. 18. The circuit as defined in claim 17, wherein the means for calculating the updated device pose estimate further comprises a means for calculating the updated device pose estimate for a primary particle based at least in part on data from a first sensor, and a means for calculating the updated device pose estimate for a dual particle based at least in part on data from a second sensor, where the second sensor is different from the first sensor. 19. The circuit as defined in claim 17, wherein the circuit is embodied in a robot for navigation of the robot. 20. A computer program embodied in a tangible medium for localizing a mobile device in a multiple-particle autonomous localization and mapping system, the computer program comprising: a module with instructions configured to perform autonomous localization and mapping with a plurality of particles, where a particle includes a device pose and a map, where the map includes one or more landmarks; a module with instructions configured to receive an indication that a landmark has been detected; and a module with instructions configured to update at least one particle from the plurality of particles at least partly in response to receiving the indication of the detected landmark, wherein the module with instructions configured to update further comprises: instructions configured to selectively categorize a particle as one of a first type of particle or a second type of particle; and instructions configured to calculate an updated device pose estimate for a particle, wherein the technique used to calculate the updated device pose estimate is selected according to the type associated with the particle. 21. The computer program as defined in claim 20, wherein the module with instructions configured to calculate the updated device pose estimate further comprises instructions configured to calculate the updated device pose estimate for a primary particle based at least in part on data from a first sensor and instructions configured to calculate the updated device pose estimate for a dual particle based at least in part on data from a second sensor, where the second sensor is different from the first sensor. 22. The computer program as defined in claim 20, wherein the module with instructions configured to calculate the updated device pose estimate further comprises instructions configured to calculate the updated device pose for a particle type of based at least in part on data from a dead reckoning sensor and instructions configured to calculate the updated device pose estimate for a particle type of particle based at least in part on data from a visual sensor. 23. The computer program as defined in claim 20, further comprising a module with instruction for resampling selected particles from the plurality of particles. 24. A circuit for localizing a mobile device in a multiple-particle autonomous localization and mapping system, the circuit comprising: a circuit configured to perform autonomous localization and mapping with a plurality of particles, where a particle includes a device pose and a map, where the map includes one or more landmarks; a circuit configured to receive an indication that a landmark has been detected; and a circuit configured to update at least one particle from the plurality of particles at least partly in response to receiving the indication of the detected landmark, wherein the circuit configured to update further comprises: a circuit configured to selectively categorize a particle as one of a first type of particle or a second type of particle; and a circuit configured to calculate an updated device pose estimate for a particle, wherein the technique used to calculate the updated device pose estimate is selected according to the type associated with the particle. 25. The circuit as defined in claim 24, wherein the circuit configured to calculate the updated device pose estimate is further configured to calculate the updated device pose estimate for a particle of primary type based at least in part on data from a first sensor and is further configured to calculate the updated device pose estimate for a particle of dual type based at least in part on data from a second sensor, where the second sensor is different from the first sensor. 26. The circuit as defined in claim 24, wherein the circuit configured to calculate the updated device pose estimate is further configured to calculate the updated device pose for a primary particle based at least in part on data from a dead reckoning sensor and is further configured to calculate the updated device pose estimate for a dual particle based at least in part on data from a visual sensor. 27. The circuit as defined in claim 24, further comprising a circuit configured to resample selected particles from the plurality of particles. 28. The circuit as defined in claim 24, wherein the circuit is embodied in a robot for navigation of the robot.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.