Hybrid control strategy for trajectory tracking and obstacle avoidance in differential wheeled robots: integrating PSO-NMPC, GA, and fuzzy logic

Abstract

Mobile robots frequently encounter challenges in maintaining accurate trajectory tracking and effective obstacle avoidance in dynamic and uncertain environments. Traditional control methods, such as proportional integral derivative (PID) and standard MPC, often fail to provide the necessary adaptability and robustness for complex navigation tasks. To overcome these limitations, this study proposes a hybrid control framework for differential-drive wheeled robots that integrates particle swarm optimization–based nonlinear model predictive control (PSO-NMPC), adaptive neuro-fuzzy inference system (ANFIS) optimized by PSO, and genetic algorithm (GA) tuning. The PSO-NMPC computes optimal control inputs in real time while satisfying system constraints to ensure precise trajectory tracking, achieving an average RMSE of 0.0941 m (RMSEx = 0.0884 m, RMSEy = 0.0812 m). The ANFIS-PSO controller manages nonlinearities and environmental uncertainties for reliable obstacle avoidance, with an overall RMSE of 0.1084 m (RMSEx = 0.0761 m, RMSEy = 0.0772 m). The GA further optimizes key parameters and trajectories, ensuring global path refinement and robust obstacle clearance, achieving an overall RMSE of 0.1094 m (RMSEx = 0.1059 m, RMSEy = 0.0274 m). Simulation results in Matlab2024b confirm that the proposed hybrid framework provides precise trajectory tracking, smooth control, and robust obstacle avoidance, making it a promising solution for autonomous mobile robots operating in dynamic and uncertain environments.