Inertial navigation aided with multi-interval pose measurements

An apparatus for inertial navigation, comprising:

• a single inertial measurement unit (IMU);
• a transceiver;
• a memory;
• and
• one or more processors communicatively coupled with the transceiver and the memory, wherein the one or more processors are configured to:
• obtain IMU data from the single IMU of the apparatus;
• generate, based on the IMU data obtained from the single IMU of the apparatus, a respective pose measurement vector according to each of a plurality of machine-learning models, resulting in a plurality of pose measurement vectors, wherein each of the plurality of pose measurement vectors is associated with a respective one of multiple motion classes, wherein each of the multiple motion classes corresponds to a different respective time interval value, wherein each of the plurality of machine-learning models generates the respective pose measurement vector based on a respective window of the IMU data having a duration corresponding to the respective time interval value of the motion class associated with that machine-learning model, and wherein each pose measurement vector indicates a change in at least one of position or orientation of the apparatus occurring over the respective time interval value corresponding to the motion class associated with that pose measurement vector;
• and
• determine a device pose estimate for the apparatus based on the IMU data and the plurality of pose measurement vectors, wherein to determine the pose estimate the one or more processors are configured to:
• update a state of a multi-measurement estimation filter bank based on the IMU data and each of the plurality of pose measurement vectors;
• and
• determine the pose estimate based on the updated state of the multi-measurement estimation filter bank.

An apparatus for inertial navigation, comprising:

• means for obtaining inertial measurement unit (IMU) data from a single IMU of the apparatus;
• means for generating, based on the IMU data obtained from the single IMU of the apparatus, a respective pose measurement vector according to each of a plurality of machine-learning models, resulting in a plurality of pose measurement vectors, wherein each of the plurality of pose measurement vectors is associated with a respective one of multiple motion classes, wherein each of the multiple motion classes corresponds to a different respective time interval value, wherein each of the plurality of machine-learning models generates the respective pose measurement vector based on a respective window of the IMU data having a duration corresponding to the respective time interval value of the motion class associated with that machine-learning model, and wherein each pose measurement vector indicates a change in at least one of position or orientation of the apparatus occurring over the respective time interval value corresponding to the motion class associated with that pose measurement vector;
• and
• means for determining a device pose estimate for the apparatus based on the IMU data and each of the plurality of pose measurement vectors, the means for determining including:
• means for updating a state of a multi-measurement estimation filter bank based on the IMU data and each of the plurality of pose measurement vectors;
• and
• means for determining the pose estimate based on the updated state of the multi-measurement estimation filter bank.