Back to results
US 12,716,748 B2Granted
GNSS error quantification and global map alignment
AssigneeGM Global Technology Operations LLC
InventorsKamran Ali, Bo Yu, Shuqing Zeng
Life of this patent
Estimating the term…
Abstract
A method for aligning a plurality of local maps with a global coordinate system includes quantifying a global navigation satellite system (GNSS) error at each of a plurality of locations within an environment. The method further includes determining a plurality of anchor points within the environment based at least in part on the GNSS error at each of the plurality of locations. The method further includes aligning the plurality of local maps with the global coordinate system based at least in part on the plurality of anchor points.
Claims13
A method for aligning a plurality of local maps with a global coordinate system, the method comprising:
- quantifying a global navigation satellite system (GNSS) error at each of a plurality of locations within an environment, wherein quantifying the GNSS error at each of the plurality of locations further comprises:
- collecting the plurality of local maps from a plurality of vehicles, wherein collecting the plurality of local maps further comprises:
- collecting the plurality of local maps from the plurality of vehicles, wherein the plurality of local maps are created using simultaneous localization and mapping (SLAM), wherein each of the plurality of local maps includes a plurality of observation points, and wherein each of the plurality of observation points includes observation data, local map coordinates, and GNSS coordinates;
- identifying the plurality of locations in the plurality of local maps, wherein identifying the plurality of locations in the plurality of local maps further comprises:
- identifying a plurality of proximal observation point pairs based on the plurality of observation points of each of the plurality of local maps, wherein each of the plurality of proximal observation point pairs includes a first observation point of the plurality of observation points and a second observation point of the plurality of observation points located within a first predetermined radius of the first observation point in the environment based at least in part on the observation data of each of the plurality of observation points of each of the plurality of local maps;
- and
- identifying the plurality of locations, wherein each of the plurality of locations includes the first observation point of one of the plurality of proximal observation point pairs;
- and
- quantifying the GNSS error at each of the plurality of locations based at least in part on the plurality of local maps, wherein quantifying the GNSS error at each of the plurality of locations based at least in part on the plurality of local maps further comprises:
- executing a re-localization algorithm to determine a transformation vector between the first observation point and the second observation point, wherein the transformation vector describes a difference in location in the environment between the first observation point and the second observation point;
- determining the GNSS error between the first observation point and the second observation point, wherein the GNSS error is:
- e
- G
-
- N
-
- S
-
- S
- =
-
- GNSS
- 1
- -
- G
-
- N
-
- S
-
- S
- 2
-
- -
-
- T
-
- wherein eGNSS is the GNSS error between the first observation point and the second observation point, GNSS1, is the GNSS coordinates of the first observation point, GNSS2, is the GNSS coordinates of the second observation point, and T is the transformation vector;
- and
- updating the GNSS coordinates of the first observation point based at least in part on the transformation vector;
- determining a plurality of anchor points within the environment based at least in part on the GNSS error at each of the plurality of locations;
- aligning the plurality of local maps with the global coordinate system based at least in part on the plurality of anchor points to generate a plurality of aligned local maps;
- and
- controlling a vehicle based at least in part on one or more of the plurality of aligned local maps as part of an automated driving function.
41 more elements
A system for aligning a plurality of local maps with a global coordinate system, the system comprising:
- a plurality of vehicle sensors including at least a vehicle global navigation satellite system (GNSS), a vehicle perception sensor, and a vehicle communication system;
- and
- a vehicle controller in electrical communication with the plurality of vehicle sensors, wherein the vehicle controller is programmed to:
- collect the plurality of local maps of an environment, wherein the plurality of local maps are created using simultaneous localization and mapping (SLAM), wherein each of the plurality of local maps includes a plurality of observation points, and wherein each of the plurality of observation points includes observation data including observations made using the vehicle perception sensor, local map coordinates, and GNSS coordinates determined using the vehicle GNSS;
- and
- transmit the plurality of local maps to a server system using the vehicle communication system;
- the server system comprising:
- a server communication system;
- and
- a server controller in electrical communication with the server communication system, wherein the server controller is programmed to:
- receive the plurality of local maps using the server communication system;
- identify a plurality of locations in the plurality of local maps, wherein to identify the plurality of locations in the plurality of local maps, the server controller is further programmed to:
- identify a plurality of proximal observation point pairs based on the plurality of observation points of each of the plurality of local maps, wherein each of the plurality of proximal observation point pairs includes a first observation point of the plurality of observation points and a second observation point of the plurality of observation points located within a first predetermined radius of the first observation point in the environment based at least in part on the observation data of each of the plurality of observation points of each of the plurality of local maps;
- and
- identify the plurality of locations, wherein each of the plurality of locations includes the first observation point of one of the plurality of proximal observation point pairs;
- quantify a GNSS error at each of the plurality of locations based at least in part on the plurality of local maps, wherein to quantify the GNSS error at each of the plurality of locations, the server controller is further programmed to:
- execute a re-localization algorithm to determine a transformation vector between the first observation point and the second observation point, wherein the transformation vector describes a difference in location in the environment between the first observation point and the second observation point;
- and
- determine the GNSS error between the first observation point and the second observation point, wherein the GNSS error is:
- e
- G
-
- N
-
- S
-
- S
- =
-
- GNSS
- 1
- -
- G
-
- N
-
- S
-
- S
- 2
-
- -
-
- T
-
- wherein eGNSS is the GNSS error between the first observation point and the second observation point, GNSS1, is the GNSS coordinates of the first observation point, GNSS2, is the GNSS coordinates of the second observation point, and T is the transformation vector;
- determine a plurality of anchor points based at least in part on the GNSS error at each of the plurality of locations;
- align the plurality of local maps with the global coordinate system based at least in part on the plurality of anchor points to generate a plurality of aligned local maps;
- and
- transmit one or more of the plurality of aligned local maps to the vehicle controller using the server communication system;
- and
- wherein the vehicle controller is further programmed to:
- control the vehicle based at least in part on the one or more of the plurality of aligned local maps as part of an automated driving function.
50 more elements
A method for aligning a plurality of local maps with a global coordinate system, the method comprising:
- collecting the plurality of local maps of an environment from a plurality of vehicles, wherein the plurality of local maps are created using simultaneous localization and mapping (SLAM), wherein each of the plurality of local maps includes a plurality of observation points, and wherein each of the plurality of observation points includes observation data, local map coordinates, and GNSS coordinates;
- identifying a plurality of proximal observation point pairs based on the plurality of observation points of each of the plurality of local maps, wherein each of the plurality of proximal observation point pairs includes a first observation point of the plurality of observation points and a second observation point of the plurality of observation points located within a first predetermined radius of the first observation point in the environment based at least in part on the observation data of each of the plurality of observation points of each of the plurality of local maps;
- identifying a plurality of locations, wherein each of the plurality of locations includes the first observation point of one of the plurality of proximal observation point pairs;
- executing a re-localization algorithm to determine a transformation vector between the first observation point and the second observation point, wherein the transformation vector describes a difference in location in the environment between the first observation point and the second observation point;
- determining a GNSS error at each of the plurality of locations, wherein the GNSS error at one of the plurality of locations is:
- e
- G
-
- N
-
- S
-
- S
- =
-
- GNSS
- 1
- -
- G
-
- N
-
- S
-
- S
- 2
-
- -
-
- T
-
- wherein eGNSS is the GNSS error between the first observation point and the second observation point at one of the plurality of locations, GNSS1 is the GNSS coordinates of the first observation point, GNSS2 is the GNSS coordinates of the second observation point, and T is the transformation vector;
- aligning the plurality of local maps with the global coordinate system based at least in part on the GNSS error at each of the plurality of locations to generate a plurality of aligned local maps;
- transmitting one or more of the plurality of aligned local maps to a vehicle;
- and
- controlling the vehicle based at least in part on the one or more of the plurality of aligned local maps as part of an automated driving function.
33 more elements
Dependencies are inferred from the claim text.