Reinforcement Learning Path Planning based on Step Batch Q-Learning Algorithm

Yin, Zhiqian; Cao, Wei; Song, Tao; Xu, Yang; Zhang, Tianhao

doi:10.1109/icaica54878.2022.9844553

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outcomes are then projected back to geographic latitude and longitude coordinates. As the primary purpose of real-time path planning for USVs is obstacle avoidance, obstacles within the grid space are regarded as threats [3][4][5] . Additionally, to simplify the design and considering the predominant application scenarios of small-scale water areas, the grid space is treated as a flat plane for mapping purposes.…”

Section: 1scene Mappingmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Q-learning algorithm with eligibility traces for safe path planning of unmanned surface vehicles in dynamic unknown environment

Wu,

Liu,

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

This study explores the application of a path planning algorithm based on Q-learning and eligibility traces in autonomous task execution for Unmanned Surface Vehicles (USVs). The algorithm aims to provide secure path planning for USVs in dynamic unknown environments, taking into account obstacles, potential threats, and multiple constraints. Initially, a detailed Markov Decision Process (MDP) model was designed. Subsequently, the introduced Q-learning and eligibility trace algorithm demonstrated significant advantages in path planning, utilizing the Upper Confidence Bound (UCB) strategy for action selection. Finally, simulation experiment results indicate that, compared to traditional Q-learning methods, the algorithm can more effectively plan paths for USVs, avoid threat areas, and achieve faster convergence.

show abstract

Section: 1scene Mappingmentioning

confidence: 99%

“…The heading states are discretized, and based on the chosen discrete heading states, seven actions are defined as depicted in the diagram. As shown in Figure 1, the action space is denoted as A = [0, 1,2,3,4,5,6], where each number represents a distinct action. The diagram illustrating the action space.…”

Section: 2action Spacementioning

confidence: 99%