Localization via machine learning based on perceived channel properties and inertial measurement unit supervision

A processing system comprising:

• one or more memories comprising computer-executable instructions;
• and
• one or more processors configured to execute the computer-executable instructions and cause the processing system to perform an operation comprising:
• accessing a sequence of data records, each respective data record in the sequence of data records comprising a respective set of one or more wireless channel measurements and a respective set of inertial measurement unit (IMU) data;
• accessing known position information corresponding to at least a first data record of the sequence of data records;
• determining a first sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a forward double integration operation;
• determining a second sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a backward double integration operation;
• generating an IMU adjustment parameter based on the first and second sequences of positions;
• generating a pseudo-label for a second data record of the sequence of data records based on the IMU adjustment parameter and the sets of IMU data;
• and
• training a machine learning model, based on the second data record and the pseudo-label, to predict positions based on one or more wireless channel measurements.

One or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform an operation comprising:

• accessing a sequence of data records, each respective data record in the sequence of data records comprising a respective set of one or more wireless channel measurements and a respective set of inertial measurement unit (IMU) data;
• accessing known position information corresponding to at least a first data record of the sequence of data records;
• determining a first sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a forward double integration operation;
• determining a second sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a backward double integration operation;
• generating an IMU adjustment parameter based on the first and second sequences of positions;
• generating a pseudo-label for a second data record of the sequence of data records based on the IMU adjustment parameter and the sets of IMU data;
• and
• training a machine learning model, based on the second data record and the pseudo-label, to predict positions based on one or more wireless channel measurements.

A processing system, comprising:

• means for accessing a sequence of data records, each respective data record in the sequence of data records comprising a respective set of one or more wireless channel measurements and a respective set of inertial measurement unit (IMU) data;
• means for accessing known position information corresponding to at least a first data record of the sequence of data records;
• means for determining a first sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a forward double integration operation;
• means for determining a second sequence of positions based on processing the sets of IMU data and at least a subset of the known position information using a backward double integration operation;
• means for generating an IMU adjustment parameter based on the first and second sequences of positions;
• means for generating a pseudo-label for a second data record of the sequence of data records based on the IMU adjustment parameter and the sets of IMU data;
• and
• means for training a machine learning model, based on the second data record and the pseudo-label, to predict positions based on one or more wireless channel measurements.