Traffic light detection auto-labeling and federated learning based on vehicle-to-infrastructure communications

A non-transitory computer-readable medium having program code recorded thereon for traffic light auto-labeling, the program code being executed by a processor and comprising:

• program code to aggregate vehicle-to-infrastructure (V2I) traffic light signals at an intersection to determine transition states of each driving lane at the intersection during operation of an ego vehicle;
• program code to automatically label image training data to form auto-labeled image training data for a traffic light recognition model within the ego vehicle according to the determined transition states of each driving lane at the intersection;
• and
• program code to plan a trajectory of the ego vehicle to comply with a right-of-way according to the determined transition states of each driving lane at the intersection according to a trained traffic light detection model.

A system for traffic light auto-labeling, the system comprising:

• a traffic light learning model to aggregate vehicle-to-infrastructure (V2I) traffic light signals at an intersection to determine transition states of each driving lane at the intersection during operation of an ego vehicle;
• a traffic light auto-labeling module to automatically label image training data to form auto-labeled image training data for a traffic light recognition model within the ego vehicle according to the determined transition states of each driving lane at the intersection;
• and
• a planner module to plan a trajectory of the ego vehicle to comply with a right-of-way according to the determined transition states of each driving lane at the intersection according to a trained traffic light detection model.