Navigation using high visibility non-ephemeral geographic features

A computer-implemented method comprising:

• receiving a plurality of images captured using an image sensor of an autonomous vehicle;
• processing a periodic subset of the plurality of images using a machine learning model;
• based upon processing by the machine learning model and an output of the machine learning model, determining the autonomous vehicle, at a first time, is approaching or in a city area;
• upon determining the autonomous vehicle is approaching or in the city area, employing a conventional odometry algorithm for determining a first location of the autonomous vehicle;
• based upon processing by the machine learning model and the output of the machine learning model, determining the autonomous vehicle, at a second time, is leaving or not in the city area;
• and
• upon determining the autonomous vehicle is leaving or not in the city area, employing an alternative odometry algorithm for determining the current location of the autonomous vehicle.

An autonomous vehicle comprising:

• an image sensor;
• at least one memory configured to store machine executable instructions;
• and
• at least one processor coupled to the at least one memory and configured to execute the machine executable instructions to configure the at least one processor to:
• receive a plurality of images captured using the image sensor;
• process a periodic subset of the plurality of images using a machine learning model;
• based upon processing by the machine learning model and an output of the machine learning model, determine the autonomous vehicle, at a first time, is approaching or in a city area;
• upon determining the autonomous vehicle is approaching or in the city area, employ a conventional odometry algorithm for determining a first location of the autonomous vehicle;
• based upon processing by the machine learning model and the output of the machine learning model, determine the autonomous vehicle, at a second time, is leaving or not in the city area;
• and
• upon determining the autonomous vehicle is leaving or not in the city area, employ an alternative odometry algorithm for determining the current location of the autonomous vehicle.