Uncertainty-aware Path Planning using Reinforcement Learning and Deep Learning Methods

This paper proposes new algorithms to improve Reinforcement Learning (RL) and Deep Q-Network (DQN) methods for path planning considering uncertainty in the perception of environment. The study aimed to formulate and solve the path planning optimization problem by optimizing the path, avoiding obstacles, and minimizing the related uncertainty. In this regard, a reward function is constructed based on the weighted features of the environment images. In this study, Deep Learning (DL) is used for two purposes. First, for perceiving a real environment to find the state transition matrix of the mobile robot path planning problem, and second, for extracting the features of state directly from an image of the environment to select the appropriate actions. To solve the path planning problem, it is formed in the context of an RL problem, and a Convolutional Neural Network (CNN) is used to approximate Q-values as a linear parameterized function. Implementing this approach improves the Q-learning, SARSA, and DQN algorithms as the new versions, called POQL, POSARSA, and PODQN. The learning process results show that using newly improved algorithms increases path planning performance by more than 20%, 21%, and 5% compared to the Q-learning, SARSA, and DQN, respectively.