Loading [MathJax]/extensions/MathMenu.js
Optimization Path Planning Algorithm Based on Deep Reinforcement Learning | IEEE Conference Publication | IEEE Xplore

Optimization Path Planning Algorithm Based on Deep Reinforcement Learning


Abstract:

With the acceleration of urbanization and the growth of traffic demand, traffic congestion has become more and more prominent. In the field of path planning, Deep Reinfor...Show More

Abstract:

With the acceleration of urbanization and the growth of traffic demand, traffic congestion has become more and more prominent. In the field of path planning, Deep Reinforcement Learning (DRL) can effectively deal with the complex traffic environment and learn the optimal path selection strategy. This article aims to explore the optimal path planning algorithm based on DRL to improve the accuracy and efficiency of path planning. The algorithm estimates the state function by establishing a deep neural network, and uses reinforcement learning to optimize the strategy, so as to fully consider the actual traffic flow and provide accurate route suggestions for users. The experimental results show that the optimized path planning algorithm based on DRL has smaller path-finding error and higher path-finding accuracy. After many iterations, the routing accuracy of the algorithm can even reach more than 96%. Therefore, the optimized path planning algorithm based on DRL is an effective path planning method, which can deal with complex traffic scene information and optimize the path planning effect.
Date of Conference: 10-12 January 2024
Date Added to IEEE Xplore: 22 July 2024
ISBN Information:
Conference Location: New Delhi, India

I. Introduction

With the acceleration of urbanization and the growth of traffic demand, traffic congestion has become more and more prominent, which has seriously affected people’ s production and life. In order to alleviate traffic pressure and improve the efficiency of road network, path planning has become an important research field [1]. Traditional path planning algorithms are mainly based on mathematical models and optimization theory. However, these algorithms often do not fully consider the actual traffic flow, so they cannot provide accurate path suggestions for drivers [2]. In recent years, DRL has made breakthroughs in many fields, especially in the fields of games, robots and autonomous driving. This article aims to apply DRL to the field of path planning and design an optimized path planning algorithm that can fully consider the actual traffic flow.

Contact IEEE to Subscribe

References

References is not available for this document.