Waymo secures grants for predicting occluded pedestrians and traffic signal states.
The filing
Waymo LLC received two US patents on November 10, 2026, covering systems to identify and respond to target objects hidden in occluded areas of driving environments and to improve traffic signal state estimation by analyzing relationships between different traffic signals in a network. The first patent describes training a machine learning model to determine the location of a masked target object and using that output to train a second model that generates a probability map of objects in occluded regions for deployment on autonomous vehicles (USPTO 12,789,826 (opens in a new tab)). The second patent covers methods to use the relationship between activities of different traffic signals to refine the estimation of their states (USPTO 12,793,440 (opens in a new tab)).
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.