A Deep Q-Network-Based Algorithm for Obstacle Avoidance and Target Tracking for Drones

This paper introduces a novel algorithm, refer to NEWDQN, which is based on the deep Q-network (DQN) framework. The primary objective of this algorithm is to optimize the successful rate both in autonomous drone obstacle avoidance and target tracking tasks, while this algorithm can also improve the drawbacks of the previous algorithm in convergence. Furthermore, the algorithm endows the drone with environment perception capabilities and incorporates a direction-based reward-penalty function into the reward function, enhancing the drone's generalization ability and overall performance. Extensive simulations demonstrate that compared to conventional DQN and Double DQN (DDQN) algorithms, NEWDQN exhibits faster convergence speed, shorter tracking paths, and more robust adaptability to different environments.