Deep Reinforcement Learning based Vehicle Navigation amongst pedestrians using a Grid-based state representation

Autonomous navigation in structured urban environments amongst pedestrians is a challenging and less explored problem. In this work, we propose to use a deep reinforcement learning based method to solve this problem of navigation. A Deep Q-Network based agent is trained in a simulator for a typical intersection crossing setup amongst pedestrians. We propose a grid based representation as a state space input to the learning agent. With this grid based representation and our reward function the agent learns a policy capable of driving safely around pedestrians and also follow the traffic rules.