Time-Optimal Trajectory Planning for Industrial Robots Based on Improved Fire Hawk Optimizer

Abstract

Focusing on joint-space time-optimal trajectory planning for industrial robots, this study integrates 3-5-3 piecewise polynomial parameterization with an improved Fire Hawk Optimization algorithm (TFHO). Subject to joint position, velocity, and acceleration limits, segment durations are optimized as decision variables. TFHO employs Tent-chaotic initialization to improve the uniformity of initial solutions and a two-phase adaptive Lévy–Gaussian–Cauchy hybrid mutation to balance early global exploration with late local exploitation, mitigating premature convergence and enhancing stability. On benchmark functions, TFHO attains the lowest mean area under the convergence curve (AUC; lower is better). Wilcoxon signed-rank tests show statistically significant improvements over FHO, PSO, GWO, and WOA $(p\le 0.05)$. Ablation studies indicate a pronounced reduction in run-to-run variability: the standard deviation decreases from 0.3157 (FHO) to 0.0023 with TFHO, a 99.27% drop. In an ABB IRB-2600 simulation case, the execution time is shortened from 12.00 s to 9.88 s (−17.66%) while preserving smooth and continuous kinematic profiles (position, velocity, and acceleration), demonstrating practical engineering applicability.