Neural Adaptive Nonlinear MIMO Control for Bipedal Walking Robot Locomotion in Hazardous and Complex Task Applications

This paper introduces a robust neural adaptive MIMO control strategy to improve the stability and adaptability of bipedal locomotion amid uncertainties and external disturbances. The control combines nonlinear dynamic inversion, finite-time convergence, and radial basis function (RBF) neural networks for fast, accurate trajectory tracking. The main novelty of the presented control strategy lies in unifying instantaneous feedback, real-time learning, and dynamic adaptation within a multivariable feedback framework, delivering superior robustness, precision, and real-time performance under extreme conditions. The control scheme is implemented on a 5-DOF underactuated RABBIT robot using a dSPACEDS1103 platform with a sampling rate of ∆t=1.5 ms (667 Hz). The experimental results show excellent performance with the following: The robot achieved stable cyclic gaits while keeping the tracking error within e=±0.04 rad under nominal conditions. Under severe uncertainties of trunk mass variations ∆mtrunk=+100%, limb inertia changes ∆Ilimb=±30%, and actuator torque saturation at τ=±150 Nm, the robot maintains stable limit cycles with smooth control. The performance of the proposed controller is compared with classical nonlinear decoupling, non-adaptive finite-time, neural-fuzzy learning, and deep learning controls. The results demonstrate that the proposed method outperforms the four benchmark strategies, achieving the lowest errors and fastest convergence with the following: IAE=1.36, ITAE=2.43, ISE=0.68, tss=1.24 s, and Mp=2.21%. These results demonstrate evidence of high stability, rapid convergence, and robustness to disturbances and foot-slip.