Dynamic Harris Hawks optimization and deep reinforcement learning framework for autonomous vehicle path planning

english

2025

volume 20, issue 3

autonomous vehicles   bidirectional feedback   deep reinforcement learning   dynamic path planning   dynamic weight fusion   Harris Hawks optimization   intelligent transportation systems   real-time navigation

Univerza v Mariboru, Fakulteta za strojništvo
(Obvezni izvod spletne publikacije)

Urban intelligent transportation systems require real-time, near-optimal routing for autonomous vehicles navigating dynamic and uncertain traffic. We propose a Harris Hawks Optimization–deep reinforcement learning framework (HHO-DRL) that unites HHO’s global exploration with DRL’s adaptive policy search through (i) a dynamic-weight fusion scheme that continuously balances exploration and exploitation and (ii) a bidirectional experience-feedback loop that exchanges elite solutions between the two solvers. On 23 CEC-2014 benchmark functions and five classical multimodal tests, HHO-DRL lowers mean error by up to three orders of magnitude relative to PSO and adaptive HHO, demonstrating superior robustness and precision. In 30?×?30 grid-world simulations with 30?% obstacle density, it generates vehicle routes 35?% shorter than those produced by Grey Wolf Optimization and 25?% shorter than adaptive HHO, while preserving smooth, collision-free trajectories. These results confirm that the proposed dual-mechanism delivers fast, high-quality solutions for high-dimensional, dynamic path-planning and other complex engineering optimization tasks.

06.07.2026