Optimizing Deep Q-Network for Shortest Path Computation of Mobile Robot Agents

This paper studies the application of Deep Q-Networks (DQN) for shortest-path planning on mobile robots. Implementing DQN on mobile robots poses challenges due to the limited computational resources of embedded systems. The process consists of two mode: the training mode, where an inference model of DQN with weight and bias parameters is generated, and the operational mode, where the DQN model is loaded onto the robot to perform actions in a simulation maze environment with gazebo. This study investigates optimal computational techniques for matrix operations, which are the primary operations in DQN. Computational methods performed on embedded system platforms utilizing GPUs (Jetson Xavier NX) involve studying matrix computation techniques using arrays, 2D arrays with GPUs, and tensors. Based on the experiment, the results show that for the DQN model used in shortest-path planning, computation based on an array matrix significantly speeds up the process.