US 12,292,517 B2
Method and system for position estimation using domain adaptation
Kyeong-Jin Kim, Cambridge, MA (US); Remy Zawislak, Cambridge, AL (US); Karl Berntorp, Cambridge, MA (US); Marcus Greiff, Cambridge, AL (US); Stefano Di Calrano, Cambridge, MA (US); Kieran Parsons, Cambridge, AL (US); and Philip Orlik, Cambridge, MA (US)
Assigned to Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA (US)
Filed by Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA (US)
Filed on Sep. 6, 2022, as Appl. No. 17/929,967.
Prior Publication US 2024/0077622 A1, Mar. 7, 2024
Int. Cl. G01S 19/22 (2010.01); G01S 19/37 (2010.01); G06N 3/08 (2023.01)
CPC G01S 19/22 (2013.01) [G01S 19/37 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A positioning device for tracking a position of one or more moving objects based on transmissions from a global navigation satellite system (GNSS), the positioning device comprising: a processor; and a memory having instructions stored thereon that, when executed by the processor, cause the positioning device to:
collect GNSS measurement data of satellite signals transmitted from multiple satellites of the GNSS, wherein the GNSS measurement data are collected during motion of the one or more moving objects in a target domain;
extract values of a plurality of features from the GNSS measurement data indicative of one or a combination of code and phase values, carrier-to-noise-power-density-ratio, and Doppler shifts of the satellite signals collected in the target domain, such that a statistical distribution of the extracted values of the plurality of features is governed by the target domain;
map the extracted values of the plurality of features from the target domain to a source domain, such that a statistical distribution of the mapped values of the plurality of features resembles a statistical distribution of values of a plurality of training features collected in the source domain, wherein the processor is configured to map the extracted values of the plurality of features using a cycle-consistent Generative Adversarial Network (CGAN) performing a tensor-to-tensor translation of tensors formed by the extracted values of the plurality of features and tensors formed by training features used for training the neural network;
classify the mapped values of the plurality of features using a neural network trained with the training features sampled from the source domain to identify the GNSS measurement data affected by multipath; and
track the position of the one or more moving objects by processing the GNSS measurement data based on the identified GNSS measurement data affected by multipath.