EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RL-QPSO net: deep reinforcement learning-enhanced QPSO for efficient mobile robot path planning

Yang Jing, Li Weiya

Frontiers in Neurorobotics · 08.01.2025 · 18

DOI: 10.3389/fnbot.2024.1464572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 08.01.2025. Verfasst von Yang Jing und 1 weiteren Autor:innen. Beteiligte Einrichtung: Hebi Institute of Engineering and Technology, Henan Polytechnic University, Hebi, Henan, China. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Path planning in complex and dynamic environments poses a significant challenge in the field of mobile robotics. Traditional path planning methods such as genetic algorithms, Dijkstra's algorithm, and Floyd's algorithm typically rely on deterministic search strategies, which can lead to local optima and lack global search capabilities in dynamic settings. These methods have high computational costs and are not efficient for real-time applications.

Methods

To address these issues, this paper presents a Quantum-behaved Particle Swarm Optimization model enhanced by deep reinforcement learning (RL-QPSO Net) aimed at improving global optimality and adaptability in path planning. The RL-QPSO Net combines quantum-inspired particle swarm optimization (QPSO) and deep reinforcement learning (DRL) modules through a dual control mechanism to achieve path optimization and environmental adaptation. The QPSO module is responsible for global path optimization, using quantum mechanics to avoid local optima, while the DRL module adjusts strategies in real-time based on environmental feedback, thus enhancing decision-making capabilities in complex high-dimensional scenarios. Results and discussion Experiments were conducted on multiple datasets, including Cityscapes, NYU Depth V2, Mapillary Vistas, and ApolloScape, and the results showed that RL-QPSO Net outperforms traditional methods in terms of accuracy, computational efficiency, and model complexity. This method demonstrated significant improvements in accuracy and computational efficiency, providing an effective path planning solution for real-time applications in complex environments for mobile robots. In the future, this method could be further extended to resource-limited environments to achieve broader practical applications.

Schlagwörter

Stichwörter der Autor:innen

Quantum-behaved Particle Swarm Optimizationcomplex environmentsdeep reinforcement learningmobile roboticspath planning

Autor:innen und Institutionen

  • Hebi Institute of Engineering and Technology, Henan Polytechnic University, Hebi, Henan, China.

Zitieren

APA

Jing, Y., & Weiya, L. (2025). RL-QPSO net: deep reinforcement learning-enhanced QPSO for efficient mobile robot path planning. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1464572

Vancouver

Jing Y, Weiya L. RL-QPSO net: deep reinforcement learning-enhanced QPSO for efficient mobile robot path planning. Frontiers in Neurorobotics. 2025;18. doi:10.3389/fnbot.2024.1464572

BibTeX
@article{Jing2025,
  author = {Jing, Yang and Weiya, Li},
  title = {RL-QPSO net: deep reinforcement learning-enhanced QPSO for efficient mobile robot path planning},
  journal = {Frontiers in Neurorobotics},
  year = {2025},
  volume = {18},
  doi = {10.3389/fnbot.2024.1464572}
}
Kostenlos starten →