# US 12,015,966 B2 · Method and apparatus for sensor selection for localization and tracking > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,015,966 B2 - Document ID: US12015966B2 - Status: Granted - Kind: B2 - Application number: 17/760,540 - Filed: 2019-09-25 - Published: 2022-11-10 - Granted: 2024-06-18 - Earliest claimed: 2019-09-25 - Assignees: Nokia Solutions and Networks Oy - Applicants: Nokia Solutions and Networks Oy - Inventors: Fei Gao; Chaojun Xu; Gang Shen - Web page: https://patentgrep.com/patent/US12015966B2 ## CPC - H04W 4/029: Location-based management or tracking services - G01S 5/0205: {Details} - G01S 5/04: Position of source determined by a plurality of spaced direction-finders - G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)} - G01S 2205/02: Indoor - H04W 4/33: for indoor environments, e.g. buildings - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES ## Abstract Methods and apparatus for sensor selection for localization and tracking are provided. A method (300) performed at an access point (101, 101a, 101b, 101c, 901, 902, 903) comprises: determining, a detectability of the access point (101, 101a, 101b, 101c, 901, 902, 903) for localization for a target device (102), based on channel state information of a radio link between the target device (102) and the access point (101, 101a, 101b, 101c, 901, 902, 903) (302); and determining whether the access point (101, 101a, 101b, 101c, 901, 902, 903) is to be used for position estimation of the target device (102) or not based on the detectability (304). A localization server (103) may further eliminate access points (101, 101a, 101b, 101c, 901, 902, 903) at poor positions from position estimation, by using a predefined weighted-kernel approach. ## Claims ### Claim 1 A method performed at a localization server, comprising: determining weights of at least two access points, wherein a weight of an access point is associated with a detectability of the access point for localization of a target device; constructing respective weighted kernel functions for each of the at least two access points; computing for each of the at least two access points, an inner product of the weight of the respective access point with a weighted kernel function constructed for the respective access point; constructing an estimation error function by using inner product for the at least two access points; determining weight parameters of the respective weighted kernel functions, to optimize the estimation error function with a constrain condition of L1 regularization; and selecting one or more access points to be used for position estimation of the target device from the at least two access points, according to the determined weight parameters. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein determining the weights of the at least two access points further comprises: receiving the weights from respective access points of the at least two access points. ### Claim 3 (depends on 1) The method as claimed in claim 1, wherein the selecting further comprises: if the determined weight parameter of the weighted kernel function constructed for an access point is non-zero, determining that the access point is to be used for the position estimation. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein optimization to the estimation error function is further constrained by a distance range of possible movement of the target device. ### Claim 5 (depends on 1) The method as claimed in claim 1, further comprising: receiving channel state information of a radio link between the target device and a particular access point of the at least two access points; and utilizing the received channel state information for estimating the position for the target device. ### Claim 6 (depends on 3) The method as claimed in claim 3, further comprising: determining, a detectability of the particular access point for localization of the target device, based on the channel state information; and determining whether the particular access point is to be used for position estimation of the target device or not based on the determined detectability. ### Claim 7 (depends on 5) The method as claimed in claim 5, wherein determining whether the particular access point is to be used for position estimation of the target device or not comprises: determining that the particular access point is not to be used for position estimation of the target device, if the detectability is lower than a predetermined threshold. ### Claim 8 (depends on 5) The method as claimed in claim 5, further comprising: receiving information on an adjustment to the radio link between the target device and the particular access point, and wherein the determining of the detectability of the particular access point is further based on the adjustment. ### Claim 9 (depends on 5) The method as claimed in claim 5, further comprising: determining a weight for the particular access point based on the determined detectability. ### Claim 10 An apparatus at a localization server, comprising: at least one processor; and at least one memory including computer program code, the memory and the computer program code configured to, with the processor, cause the apparatus at least to, determine weights of at least two access points, where a weight of an access point is associated with a detectability of the access point for localizing a target device; construct respective weighted kernel functions for each of the at least two access points; compute for each of the at least two access points, an inner product of the weight of the respective access point with a weighted kernel function constructed for the respective access point; construct an estimation error function by using inner product for the at least two access points; determine weight parameters of the respective weighted kernel functions, to optimize the estimation error function with a constrain condition of L1 regularization; and select one or more access points to be used for position estimation of the target device from the at least two access points, according to the determined weight parameters. ### Claim 11 (depends on 10) The apparatus as claimed in claim 10, wherein the memory and the computer program code is configured to, with the processor, further cause the apparatus to: receive the weights from respective access points of at least two access points. ### Claim 12 (depends on 10) The apparatus as claimed in claim 10, wherein the memory and the computer program code is configured to, with the processor, further cause the apparatus to, if the determined weight parameters of the weighted kernel function constructed for an access point is non-zero, determine that the access point is to be used for the position estimation. ### Claim 13 (depends on 10) The apparatus as claimed in claim 10, wherein the memory and the computer program code is configured to, with the processor, further cause the apparatus to, receive channel state information of a radio link between the target device and an particular access point of the at least two access points. ### Claim 14 (depends on 10) The apparatus as claimed in claim 10, wherein the memory and the computer program code is configured to, with the processor, further cause the apparatus to, determine, a detectability of the particular access point for localization for the target device, based on the channel state information; and determine whether the particular access point is to be used for the position estimation of the target device or not based on the determined detectability. ### Claim 15 (depends on 14) The apparatus as claimed in claim 14, wherein the memory and the computer program code is configured to, with the processor, further cause the apparatus to, determine a weight for the particular access point based on the determined detectability.