Lower-limb exoskeletons require accurate dynamic models to achieve stable and compliant human–robot interactions. However, least-squares-based identification often relies on demanding experiments and may yield limited accuracy for exoskeletons with non-standard structures and actuator-induced uncertainties. This paper proposes a two-stage dynamic parameter identification method that integrates recursive least squares (RLS) and a genetic algorithm (GA), denoted as RLS-GA. RLS is first executed offline to estimate the variation ranges of the inertial parameter vector and to construct a finite, physically meaningful search space. GA then refines the parameters within these bounds by minimizing the regression residual norm. Experiments on a hip exoskeleton show that RLS-GA achieves higher identification accuracy than LS and unconstrained GA, while converging faster than GA under identical conditions.

Accurate dynamic parameters are required for model-based control of lower-limb exoskeletons, but limited excitation, transmission friction, and assembly-dependent uncertainty can degrade conventional estimates. This study examines a two-stage method that combines recursive least squares (RLS) with an adaptive grey wolf optimizer (AGWO). Offline RLS tracks the base-parameter trajectory and expands its post-convergence extrema to construct a finite search space; a non-smooth friction severity index then modulates the GWO convergence schedule. The method was evaluated on a pedestal-mounted, single-degree-of-freedom hip mechanism using a 5 s calibration trajectory and a separate 7 s validation trajectory. Deterministic least squares (LS) and bound-constrained least squares (BCLS) were compared with standard PSO, RLS–PSO, RLS–GA, RLS–GWO, and RLS–AGWO. Each stochastic method used a population of 30, with 80 iterations (2400 fitness evaluations) and 30 independent seeds. On the independent trajectory, BCLS obtained an RMSE of 0.1152 Nm. Median validation RMSEs were 0.1152, 0.1152, 0.1562, and 0.1516 Nm for RLS–PSO, RLS–GA, RLS–GWO, and RLS–AGWO, respectively. Thus, the adaptive schedule improved median GWO error by 3.0%, but deterministic BCLS was both more accurate and faster for the present linear-in-parameters model. AGWO is therefore not mathematically necessary for the current convex objective; its potential advantage should be tested with genuinely nonlinear friction parameterizations. The conclusions remain limited to a single-axis pedestal experiment and do not establish performance during human-worn gait.