Hybrid integral sliding mode and fuzzy logic control for omnidirectional robots: modified elephant herding optimization for trajectory tracking

Trajectory tracking and robust motion control remain central challenges in autonomous robotic systems operating under nonlinear and uncertain conditions. This study proposes a novel hybrid control framework that integrates Integral Sliding Mode Control (ISMC), whose control parameters are calculated using a Sugeno-type Fuzzy Logic Controller (FLC) and a Modified Elephant Herding Optimization (MEHO) algorithm. The approach is implemented on a three-wheeled omnidirectional mobile robot (TOMR), with detailed dynamic and kinematic modeling. The MEHO algorithm enhances exploration-exploitation balance and accelerates convergence through adaptive update mechanisms. To assess the performance of the proposed controller, a triangle and C-shape trajectories are implemented. Simulation results using MATLAB R2022b show that the proposed system reduces positional errors in the X and Y axes to below 0.005 m, and orientation error to 0.0014 rad within 2 s. The root mean square errors (RMSE) for X, Y, and orientation for the triangle trajectory are 3.48 × 10⁻⁵ m, 2.51 × 10⁻⁶ m, and 0.00287 rad, respectively and for the C-shape trajectory are 6.538*10^{- 6} m, 2.614*10^{- 6} m, and 1.051*10^{- 5} rad for X, Y, and orientation, respectively. Compared to classical EHO-based and adaptive neural sliding controllers, the proposed method achieves up to 50% lower torque variation and over 60% faster settling time. The modular and learning-based design enables generalization to other robotic platforms, including aerial robots operating in uncertain or dynamic environments.