IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0159500
(2011-06-14)
|
등록번호 |
US-8594923
(2013-11-26)
|
발명자
/ 주소 |
- Wong, Lisa
- Graham, Andrew Evan
- Goode, Christopher W.
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
11 인용 특허 :
48 |
초록
▼
A method and apparatus for sharing map data between industrial vehicles in a physical environment is described. In one embodiments, the method includes processing local map data associated with a plurality of industrial vehicles, wherein the local map data comprises feature information generated by
A method and apparatus for sharing map data between industrial vehicles in a physical environment is described. In one embodiments, the method includes processing local map data associated with a plurality of industrial vehicles, wherein the local map data comprises feature information generated by the plurality of industrial vehicles regarding features observed by industrial vehicles in the plurality of vehicles; combining the feature information associated with local map data to generate global map data for the physical environment; and navigating an industrial vehicle of the plurality of industrial vehicles using at least a portion of the global map data.
대표청구항
▼
1. A method of constructing a local map feature with a vehicle centric measurement, the method comprising: providing a vehicle pose indicative of a position of an automated guided vehicle with respect to a global coordinate system of global map data, wherein the automated guided vehicle comprises on
1. A method of constructing a local map feature with a vehicle centric measurement, the method comprising: providing a vehicle pose indicative of a position of an automated guided vehicle with respect to a global coordinate system of global map data, wherein the automated guided vehicle comprises one or more sensors;providing local map data on a memory associated with the automated guided vehicle, wherein the local map data comprises feature information and landmark data;capturing, with the one or more sensors, vehicle centric measurement data indicative of one or more objects within the physical environment, the one or more objects comprising an object that changes within the physical environment;determining, automatically with at least one processor, a dynamic feature pose indicative of a position of the object, an orientation of the object, or both with respect to the global coordinate system by superimposing the vehicle centric measurement data onto the vehicle pose; andupdating the feature information of the local map with the dynamic feature pose. 2. The method of claim 1, wherein the automated guided vehicle comprises a transponder, and wherein the vehicle pose is provided via the transponder. 3. The method of claim 1, further comprising: transforming the vehicle centric measurement data into a vehicle centric feature set; anddetermining the vehicle pose based upon the vehicle centric feature set. 4. The method of claim 3, further comprising determining a dynamic feature pose uncertainty indicative of error of the one or more sensors, the vehicle pose, or both. 5. The method of claim 3, further comprising communicating the dynamic feature pose to a central computer remotely located from the automated guided vehicle. 6. The method of claim 3, further comprising: determining an invisible portion of the feature information, the landmark data, or both based upon the vehicle pose and an observable area of the one or more sensors; andpartitioning the local map data into a partitioned map data, wherein the partitioned map data does not include the invisible portion. 7. The method of claim 6, further comprising: transforming the vehicle centric measurement data into a vehicle centric feature set; anddetermining a next vehicle pose indicative of a new position of the automated guided vehicle with respect to the global coordinate system based upon the vehicle centric feature set and the partitioned map data. 8. The method of claim 6, wherein the one or more sensors comprises a camera. 9. The method of claim 6, wherein the one or more sensors comprises a planar laser scanner coupled to one or more sides of the automated guided vehicle. 10. The method of claim 6, wherein the one or more sensors comprises an encoder attached to a wheel of the automated guided vehicle. 11. The method of claim 6, wherein the automated guided vehicle comprises a forklift. 12. The method of claim 6, wherein the physical environment comprises a warehouse or cold store. 13. The method of claim 1, further comprising receiving a new feature, a new landmark or both from the global map data, wherein the global map data is stored on a central computer remotely located from the automated guided vehicle; andupdating the feature information of the local map data, the landmark data of the local map data or both according to the new feature from the global map data, the new landmark from the global map data or both. 14. The method of claim 1, wherein the landmark data comprises slot occupancy data indicative of a presence of a pallet, and the method further comprises storing a pallet feature indicative of the pallet in the memory such that the pallet feature is associated with the feature information of the local map data. 15. A method of determining a vehicle position with a vehicle centric measurement, the method comprising: providing a vehicle pose indicative of a position of an automated guided vehicle with respect to a global coordinate system of a global map data, wherein the automated guided vehicle comprises one or more sensors;providing local map data on a memory associated with the automated guided vehicle, wherein the local map data comprises landmark data;providing an observable area indicative of a visible range of the one or more sensors of the automated guided vehicle;determining an invisible portion of the landmark data based upon the vehicle pose and the observable area of the one or more sensors, wherein the invisible portion is outside the observable area;partitioning the local map data into partitioned map data, wherein the partitioned map data does not include the invisible portion;capturing vehicle centric measurement data with the one or more sensors, wherein the vehicle centric measurement data is indicative of an object within the physical environment;transforming the vehicle centric measurement data into a vehicle centric feature set; anddetermining, automatically with at least one processor, a next vehicle pose indicative of the position of the automated guided vehicle with respect to the global coordinate system based upon the vehicle centric feature set and the partitioned map data. 16. The method of claim 15, wherein the automated guided vehicle comprises a transponder, and wherein the vehicle pose is provided via the transponder. 17. The method of claim 15, further comprising: transforming the vehicle centric measurement data into a feature pose indicative of a position of the object, an orientation of the object, or both with respect to the global coordinate system and a feature pose uncertainty indicative of error of the measurement data;communicating the feature pose, the feature pose uncertainty, or both to a central computer remotely located from the automated guided vehicle; andupdating the global map data according to the feature pose, the feature pose uncertainty, or both, wherein the global map data is stored on memory associated with the central computer. 18. The method of claim 15, wherein the landmark data comprises slot occupancy data indicative of a presence of a pallet. 19. The method of claim 18, further comprising storing, when the slot occupancy data indicates the presence of the pallet, a pallet feature indicative of the pallet in a memory coupled to the automated guided vehicle such that the pallet feature is associated with the feature information of the local map data. 20. The method of claim 15, wherein the object changes within the physical environment. 21. The method of claim 20, wherein the object is a pallet. 22. The method of claim 20, further comprising: superimposing the vehicle centric measurement data onto the vehicle pose or the next vehicle pose to create a superimposed result; anddetermining, based upon the superimposed result, a dynamic feature pose indicative of a position of the object, an orientation of the object, or both with respect to the global coordinate system. 23. A method of updating global map data with a vehicle centric measurement, the method comprising: navigating a first automated guided vehicle through a physical environment using global map data that defines a global coordinate system;capturing a first vehicle centric measurement data with a first sensor array coupled to the first automated guided vehicle, wherein the first vehicle centric measurement data is indicative of an object within the physical environment;transforming the first vehicle centric measurement data into a first feature pose indicative of a position of the object, an orientation of the object, or both with respect to the global coordinate system and a first feature pose uncertainty indicative of error of the first measurement data;capturing a second vehicle centric measurement data with a second sensor array coupled to a second automated guided vehicle, wherein the second vehicle centric measurement data is indicative of the object within the physical environment;transforming the second vehicle centric measurement data into a second feature pose indicative of the position of the object, the orientation of the object, or both with respect to the global coordinate system and a second feature pose uncertainty indicative of error of the second measurement data;transforming, automatically with one or more processors, the first feature pose, the first feature pose uncertainty, the second feature pose, and the second feature pose uncertainty into an estimated feature pose indicative of the position of the object, the orientation of the object, or both with respect to the global coordinate system, wherein the first feature pose, the first feature pose uncertainty, the second feature pose, and the second feature pose uncertainty are transformed into the estimated feature pose according to one or more statistical methods; andupdating the global map data according to the estimated feature pose. 24. The method of claim 23, further comprising: determining a vehicle pose indicative of a position of the first automated guided vehicle with respect to the global coordinate system;providing local map data on a memory associated with the first automated guided vehicle, wherein the local map data comprises feature information and landmark data;determining an invisible portion of the feature information, the landmark data, or both based upon the vehicle pose and an observable area of the first sensor array, wherein the invisible portion is outside the observable area;partitioning the local map data into a partitioned map data, wherein the partitioned map data does not include the invisible portion. 25. The method of claim 23, further comprising: providing local map data on a memory associated with the first automated guided vehicle, wherein the local map data comprises feature information and landmark data, and wherein the landmark data comprises slot occupancy data indicative of a presence of a pallet;storing, when the slot occupancy data indicates the presence of the pallet, a pallet feature indicative of the pallet in the memory such that the pallet feature is associated with the feature information of the local map data. 26. The method of claim 23, further comprising: determining a vehicle pose indicative of a position of the first automated guided vehicle with respect to the global coordinate system, an orientation of the first automated guided vehicle with respect to the global coordinate system, or both, wherein the first vehicle centric measurement data is transformed into the first feature pose by superimposing the first vehicle centric measurement data onto the vehicle pose. 27. The method of claim 23, wherein the object changes within the physical environment. 28. The method of claim 27, further comprising eliminating the estimated feature pose from the global map data after a predefined time period.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.