Intersection navigation under dynamic constraints using deep reinforcement learning

In this study, we present a unified motion planner with low- level controller for continuous control of a differential drive mobile robot. Deep reinforcement agent takes 10 dimensional state vector as input and calculates each wheel's torque value as a 2 dimensional output vector. These torque values are fed into the dynamic model of the robot, and lastly steering commands are gathered. In previous studies, navigation problem solutions that uses deep - RL methods, have not been considered with agent's own dynamic constraints, but it has been done by only considering kinematic models. This is not reliable enough for real-world scenarios. In this paper, deep-RL based motion planning is performed by considering both kinematic and dynamic constraints. According to the simulations in a dynamic environment, the agent succesfully navigates through the intersection with 99.6% success rate.