Robot Path Planning Based on the Integration of an Improved Black-Winged Kite Algorithm and the Dynamic Window Approach
Year: 2026
Type: article
Abstract: To address the issues of low global search efficiency, susceptibility to local optima, and insufficient obstacle avoidance performance of the Black-winged Kite Algorithm in robot path planning problems, a collaborative path planning method integrating the Modified Enhanced Black-winged Kite Algorithm (MEBKA) and the Improved Dynamic Window Approach (IDWA), termed MEBKA-IDWA, is proposed. First, in the global planning stage, MEBKA is proposed. To enhance population diversity, a good point set strategy is introduced during the initialization phase. To prevent the population from falling into local optima, a leader-based Lévy flight search strategy is incorporated in the attack behavior phase. Furthermore, to improve solution accuracy, a spiral search strategy is adopted in the migration behavior phase. Second, in the local planning stage, IDWA is developed. A dynamic safety distance mechanism is introduced to ensure the operational safety of the robot. In addition, a nonlinear parameter adaptive strategy is employed to optimize the heading weight, obstacle avoidance weight, and velocity weight coefficients of the conventional DWA, thereby preventing the local planner from being trapped in local optima. Finally, the global path information generated by MEBKA is incorporated into the velocity sampling space of the local planner IDWA, forming a two-layer planning framework that combines global information guidance with local motion refinement. Simulation results demonstrate that, compared with the standalone global algorithm MEBKA, the proposed hybrid MEBKA-IDWA algorithm achieves an average path length reduction of approximately 0.66% and a standard deviation decrease of about 3.27%, indicating improved robustness and path smoothness, and enabling the mobile robot to generate more optimal trajectories.
Source: IEEE Access
Authors: Chao Wang, Qingni Yuan, Pengju Qu
Institution: Guizhou University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W7128301326