Modeling and dynamic analysis of integral vertical transport system for deep-sea mining in three-dimensional space

Cao, Yuhan; Gu, Honglu; Guo, Haiyan; Li, Xiaomin

doi:10.1016/j.oceaneng.2023.113749

Cited by 4 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few years, there have been unprecedented developments in unmanned mobile vehicles, which have wide applications in multiple fields such as logistics [11], minerals [12], agriculture [13], etc. Unlike those on land, deep-sea sediments are characterized by low shear strength, high adhesion [14], large pores, and some fluid properties. Traditional unmanned vehicles are not adapted to this particular environment and usually have problems with skidding or sinking.…”

Section: Introductionmentioning

confidence: 99%

The Wide-Area Coverage Path Planning Strategy for Deep-Sea Mining Vehicle Cluster Based on Deep Reinforcement Learning

Xing,

Wang,

Liu

2024

JMSE

View full text Add to dashboard Cite

The path planning strategy of deep-sea mining vehicles is an important factor affecting the efficiency of deep-sea mining missions. However, the current traditional path planning algorithms suffer from hose entanglement problems and small coverage in the path planning of mining vehicle cluster. To improve the security and coverage of deep-sea mining systems, this paper proposes a cluster-coverage path planning strategy based on a traditional algorithm and Deep Q Network (DQN). First, we designed a deep-sea mining environment modeling and map decomposition method. Subsequently, the path planning strategy design is based on traditional algorithms and DQN. Considering the actual needs of deep-sea mining missions, the mining vehicle cluster path planning algorithm is optimized in several aspects, such as loss function, neural network structure, sample selection mechanism, constraints, and reward function. Finally, we conducted simulation experiments and analysis of the algorithm on the simulation platform. The experimental results show that the deep-sea mining cluster path planning strategy proposed in this paper performs better in terms of security, coverage, and coverage rate.

show abstract