Map quality evaluation framework

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, perform operations comprising:

• receiving sensor data associated with an environment;
• determining, based at least in part on the sensor data and a trajectory, map data representing the environment;
• determining, based at least in part on measurements associated with the sensor data and the trajectory, a first map quality indicator comprising a weighted sum of average link cost (WSALC) value based at least in part on a difference between state data associated with the trajectory and the measurements;
• determining, based at least in part on the map data, a second map quality indicator comprising an average mesh posterior rate (AMPR) value based at least in part on lidar reprojections of the sensor data using the trajectory and the map data;
• determining, based at least in part on the first map quality indicator and the second map quality indicator, a map quality value;
• determining, based at least on the map quality value, an operational map for controlling a vehicle in the environment;
• and
• controlling the vehicle in the environment based at least in part on the operational map.

A method comprising:

• determining sensor data associated with an environment provided by a vehicle traversing the environment;
• determining, based at least in part on the sensor data and a trajectory, map data representing the environment;
• determining, based at least in part on measurements associated with the sensor data and the trajectory, a first map quality indicator comprising a weighted sum of average link cost (WSALC) value based at least in part on a difference between state data associated with the trajectory and the measurements,
• determining, based at least in part on the map data, a second map quality indicator comprising an average mesh posterior rate (AMPR) value based at least in part on lidar reprojections of the sensor data using the trajectory and the map data;
• determining, based at least in part on the first map quality indicator and the second map quality indicator, a map quality value;
• determining, based at least on the map quality value, a map;
• and
• controlling the vehicle in the environment based at least in part on the map.