Deep Reinforcement Learning for Motion Planning of Mobile Robots
This addresses motion planning challenges for mobile robots, but it is incremental as it applies existing deep reinforcement learning methods to a specific domain.
The paper tackles motion planning for nonholonomic mobile robots by using deep reinforcement learning to handle continuous state and action spaces, achieving successful navigation from random initial states to arbitrary targets while considering kinematic and dynamic constraints in simulation.
This paper presents a novel motion and trajectory planning algorithm for nonholonomic mobile robots that uses recent advances in deep reinforcement learning. Starting from a random initial state, i.e., position, velocity and orientation, the robot reaches an arbitrary target state while taking both kinematic and dynamic constraints into account. Our deep reinforcement learning agent not only processes a continuous state space it also executes continuous actions, i.e., the acceleration of wheels and the adaptation of the steering angle. We evaluate our motion and trajectory planning on a mobile robot with a differential drive in a simulation environment.