GENERATING TRAINING DATA FOR MACHINE LEARNING BASED MODELS FOR AUTONOMOUS VEHICLES

A system receives information describing paths traversed by vehicles of a vehicle type, for example, a bicycle or a motorcycle. The system determines locations along the paths. For each location the system determines a measure of likelihood of encountering vehicles of the vehicle type in traffic at the location. The system selects a subset of locations based on the measure of likelihood and obtains sensor data captured at the subset of locations. The system uses the sensor data as training dataset for training a machine learning based model configured to receive input sensor data describing traffic and output a score used for navigation of autonomous vehicles. The machine learning model is provided to a vehicle, for example, an autonomous vehicle for navigation of the autonomous vehicle.