Systems and methods for vehicles navigating roads using a control model trained with residual policies

Abstract

Systems, methods, and other embodiments described herein relate to an automated vehicle (AV) navigating on roads with a control model trained using residual policies for reducing error. In one embodiment, a method includes generating a generic policy for a control model used to navigate a road having multiple agents with traffic data acquired, the generic policy applying to general traffic scenarios associated with the road. The method also includes training a task policy with reinforcement learning a plurality of residual functions for error reduction of the generic policy, the residual functions factoring parameters about the multiple agents and specific traffic scenarios. The method also includes communicating the generic policy, the task policy for error reduction, and a domain distribution learned by comparing simulated data with the traffic data to a vehicle.