AI-Driven Mobile Robot Navigation with Multi-Objective Task Scheduling and Reinforcement Learning

Mobile robots are increasingly used in dynamic and cluttered environments, where efficient navigation, task execution, and energy management are critical. This study presents a hybrid AI-driven mobile robot navigation framework that integrates multi-objective task scheduling, reinforcement learning–based path planning, and model predictive control for trajectory tracking. A hybrid Sparrow Search–Bat Optimization method is employed to generate energy-efficient task scheduling, while a Deep Q-Network is used for collision-free path planning in dynamic environments. Obstacle detection and avoidance are supported using transformer-based deep learning models for environment perception, and a recharging strategy is included to support continuous operation. The proposed approach is validated through simulation studies in dynamic navigation environments and comparative analysis with existing optimization techniques. energy-efficient task scheduling. The results indicate improvements in navigation efficiency, reduced energy consumption, and higher navigation success rates (up to 97%), indicating the effectiveness of the proposed framework for mobile robot navigation applications.