Localization with negative mapping

A system, comprising:

• a robotic vehicle
• a sensor mounted on the robotic vehicle;
• one or more processors;
• a non-transitory computer-readable medium;
• and
• program instructions stored on the non-transitory computer readable medium and executable by the one or more processors to:
• determine a map of an environment, wherein the map comprises locations of a plurality of mapped landmarks within the environment and a false detection source region within the environment, wherein the false detection source region indicates a portion of the environment from which false detections are expected;
• detect a plurality of candidate landmarks based on sensor data from the sensor;
• determine which of the detected candidate landmarks correspond to one of the plurality of mapped landmarks and which correspond to false detections;
• estimate a pose of the robotic vehicle within the environment based on the plurality of candidate landmarks determined to correspond to one of the plurality of mapped landmarks;
• determine, based on the estimated pose of the robotic vehicle, which of the plurality of candidate landmarks determined to correspond to false detections fall within the false detection source region;
• and
• determine a confidence level of the pose estimate of the robotic vehicle based on which of the plurality of candidate landmarks determined to correspond to false detections fall within the false detection source region, wherein determining that a given candidate landmark that corresponds to a false detection does not fall within the false detection source region lowers the confidence level.

A non-transitory computer readable medium having stored thereon instructions executable by one or more processors to cause a computing system to perform functions comprising:

• determining a map of an environment, wherein the map comprises locations of a plurality of mapped landmarks within the environment and a plurality of false detection source regions within the environment, wherein each false detection source region indicates a portion of the environment from which false detections are expected;
• detecting a plurality of candidate landmarks based on sensor data from a sensor mounted on a robotic vehicle;
• determining which of the plurality of candidate landmarks correspond to one of the plurality of mapped landmarks and which correspond to false detections;
• estimating a pose of the robotic vehicle within the environment based on the plurality of candidate landmarks determined to correspond to one of the plurality of mapped landmarks;
• determining, based on the estimated pose of the robotic vehicle, which of the plurality of candidate landmarks determined to correspond to false detections fall within one of the false detection source regions;
• and
• determining a confidence level of the pose estimate of the robotic vehicle based on which of the plurality of candidate landmarks determined to correspond to false detections fall within the false detection source region, wherein determining that a given candidate landmark that corresponds to a false detection does not fall within the false detection source region lowers the confidence level.