Method for relocating a mobile vehicle in a SLAM map and mobile vehicle

{
  "publication_number": "US11674817B2",
  "country": "US",
  "kind": "B2",
  "title": "Method for relocating a mobile vehicle in a SLAM map and mobile vehicle",
  "abstract": "A method for relocating a mobile vehicle in a simultaneous localization and mapping (SLAM) map is provided. The method can be used in the mobile vehicle moving in an area and includes: using SLAM to establish the SLAM map that corresponds to the area at an initial time point; detecting, by a non-SLAM positioning device, a first position trajectory and a first azimuth trajectory of the mobile vehicle on the SLAM map; detecting, by a SLAM positioning device, a loss probability of the mobile vehicle between a first timestamp and a second timestamp; determining whether a condition is satisfied; and updating the SLAM map to a new SLAM map corresponding to a current time point and updating positioning information of the mobile vehicle in the new SLAM map when the condition is satisfied at the current time point.",
  "claims": [
    "1. A method for relocating a mobile vehicle in a simultaneous localization and mapping (SLAM) map, for use in the mobile vehicle moving in an area, comprising: using SLAM to establish the SLAM map to the area at an initial time point; storing the SLAM map in a memory of the mobile vehicle; detecting, by a non-SLAM positioning device, a first position trajectory and a first azimuth trajectory of the mobile vehicle on the SLAM map; detecting and calculating, by a SLAM positioning device and a processor, a difference probability value between the SLAM map at a first time stamp and the SLAM map at a second time stamp as a loss probability of the mobile vehicle between the first time stamp and the second time stamp; determining whether a condition is satisfied; in response to the condition being satisfied at a current time point, updating, by the processor accessing the memory, the SLAM map stored in the memory to a new SLAM map corresponding to the current time point by using a position and azimuth of the mobile vehicle at the current time point and updating positioning information of the mobile vehicle in the new SLAM map, wherein the position and azimuth of the mobile vehicle are detected by the non-SLAM positioning device, wherein the condition is one of the following: the first position trajectory or the first azimuth trajectory is not within a first range; and the loss probability is not within a second range; and relocating and operating the mobile vehicle in the area according to the new SLAM map stored in the memory.",
    "2. The method as claimed in claim 1, wherein before the step of updating the positioning information of the mobile vehicle in the new SLAM map, the method further comprises: calculating, by the processor, a first trustworthiness value of the mobile vehicle at the current time point; calculating, by the processor, a second trustworthiness value of the mobile vehicle at the current time point; and updating the SLAM map to the new SLAM map corresponding to the current time point and updating the positioning information of the mobile vehicle in the new SLAM map when the first trustworthiness value or the second trustworthiness value is greater than a threshold value.",
    "3. The method as claimed in claim 2, wherein the first trustworthiness value and the second trustworthiness value are mean functions.",
    "4. The method as claimed in claim 1, wherein the loss probability is a mean function.",
    "5. The method as claimed in claim 1, wherein the processor instantly updates the SLAM map to the new SLAM map at the current time point.",
    "6. The method as claimed in claim 1, wherein the processor aperiodically updates the SLAM map to the new SLAM map.",
    "7. The method as claimed in claim 1, wherein the first time stamp and the second time stamp are continuous time stamps.",
    "8. The method as claimed in claim 1, wherein the first time stamp and the second time stamp are discontinuous time stamps.",
    "9. A mobile vehicle, moving in an area, comprising: a processor of a computing device, using SLAM to establish a SLAM map corresponding to the area at an initial time point and storing the SLAM map in a memory of the mobile vehicle; a non-SLAM positioning device, connected to the computing device, detecting a first position trajectory and a first azimuth trajectory of the mobile vehicle on the SLAM map; and a SLAM positioning device and a processor, connected to the computing device, detecting and calculating a difference probability value between the SLAM map at a first time stamp and the SLAM map at a second time stamp as a loss probability of the mobile vehicle between the first time stamp and the second time stamp; wherein in response to a condition being satisfied at a current time point, the computing device updating, by the processor accessing the memory, the SLAM map stored in the memory to a new SLAM map corresponding to the current time point by using a position and azimuth of the mobile vehicle at the current time point and updates the positioning information of the mobile vehicle in the new SLAM map, wherein the position and azimuth of the mobile vehicle are detected by the non-SLAM positioning device; wherein the condition is one of the following: the first position trajectory or the first azimuth trajectory is not within a first range; and the loss probability is not within a second range; and the computing device relocates and operates the mobile vehicle in the area according to the new SLAM map stored in the memory.",
    "10. The mobile vehicle as claimed in claim 9, wherein before the step of updating the positioning information of the mobile vehicle in the new SLAM map, the mobile vehicle further executes: the processor calculates a first trustworthiness value of the mobile vehicle at the current time point; the processor calculates a second trustworthiness value of the mobile vehicle at the current time point; and the processor of the computing device updates the SLAM map to the new SLAM map corresponding to the current time point and updating the positioning information of the mobile vehicle in the new SLAM map when the first trustworthiness value or the second trustworthiness value is greater than a threshold value.",
    "11. The mobile vehicle as claimed in claim 10, wherein the first trustworthiness value and the second trustworthiness value are mean functions.",
    "12. The mobile vehicle as claimed in claim 9, wherein the loss probability is a mean function.",
    "13. The mobile vehicle as claimed in claim 9, wherein the processor instantly updates the SLAM map to the new SLAM map at the current time point.",
    "14. The mobile vehicle as claimed in claim 9, wherein the processor aperiodically updates the SLAM map to the new SLAM map.",
    "15. The mobile vehicle as claimed in claim 9, wherein the first time stamp and the second time stamp are continuous time stamps.",
    "16. The mobile vehicle as claimed in claim 9, wherein the first time stamp and the second time stamp are discontinuous time stamps."
  ],
  "description_excerpt": "The present disclosure generally relates to a method for relocating a mobile vehicle and a mobile vehicle. More specifically, aspects of the present disclosure relate to a method for relocating a mobile vehicle in a simultaneous localization and mapping (SLAM) map and a mobile vehicle.\n\nSimultaneous localization and mapping (SLAM) is an accurate and versatile system that enables a mobile robot to map its environment and maintain working data on its position within that map. Its reliability and suitability for a variety of applications make it a useful element for imparting a robot with some level of autonomy.\n\nCurrently, SLAM technology uses a method of calculating probability to locate the position of a mobile robot and draw a map. Since the use of this technology requires a more precise position or orientation, once the mobile robot encounters some complex environments or the environment changes greatly, the mobile robot may not be able to relocate itself in the currently drawn SLAM map (i.e., the mobile robot gets lost). The map and positioning information previously created by the mobile robot may also be completely invalid.\n\nTherefore, there is a need for a method for relocating a mobile vehicle in a SLAM map and a mobile vehicle to solve the problems.\n\nThe following summary is illustrative only and is not intended to be limiting in any way. That is, the following summary is provided to introduce concepts, highlights, benefits and advantages of the novel and non-obvious techniques described herein. Select, not all, implementations are described further in the detailed description below.",
  "cpc": [
    "G01C 21/3667",
    "B25J 9/161",
    "B25J 9/1661",
    "B25J 9/1664",
    "G01C 21/1652",
    "G01C 21/20",
    "G01C 21/32",
    "G01C 21/3848",
    "G05D 1/0212",
    "G05D 1/0217",
    "G05D 1/0274",
    "G05D 2201/0213"
  ],
  "ipc": [
    "G01C 21/20",
    "G01C 21/32",
    "G01C 21/36",
    "G05D 1/02"
  ],
  "assignees": [
    "MSI Computer Shenzhen Co Ltd",
    "Micro Star International Co Ltd"
  ],
  "inventors": [
    "Hoa-Yu CHAN",
    "Shih-Che HUNG"
  ],
  "filing_date": "2020-09-09",
  "publication_date": "2023-06-13",
  "grant_date": "2023-06-13",
  "priority_date": "2020-05-06",
  "application_number": "US-202017016116-A",
  "family_id": "78377766",
  "cited_by_count": 0,
  "citations": [
    "US20190094869A1",
    "US20190212730A1",
    "WO2020030966A1",
    "US20210278864A1"
  ]
}