Abstract: Systems and methods for determining a current state of at least one traffic light (“TL”) for use in controlling an autonomous vehicle are described herein. Implementations can generate a corresponding numerical measure, for each of multiple candidate states of the TL, based on processing an image capturing a region that is predicted to include the TL using machine learning classifier(s). Implementations further generate a corresponding final measure, for each of the candidate states, based on processing each of the corresponding numerical measures using TL model(s), select one of the candidate states as a current state of the TL based on the final measures, and control the autonomous vehicle based on the current state of the TL. Notably, each of the corresponding final measures can be generated as a function of the corresponding numerical measures of the candidate states, and the corresponding numerical measures of the other candidate states.

Abstract: Systems and methods for determining a current state, of at least one traffic light, for use in controlling an autonomous vehicle are described herein. Implementations determine, based on a pose instance of the autonomous vehicle and a stored mapping of an environment of the autonomous vehicle, a region of the environment includes the traffic light and a configuration that is assigned to the traffic light. Further, those implementations process an image capturing the region, using a machine learning classifier, to generate predicted output associated with multiple candidate states of the traffic light, and determine a current state of the traffic light based on the predicted output. Processing the image using the machine learning classifier can be based on the configuration of the traffic light.