Centralized MPC-Based Mixed-Integer Programming for Cooperative Trajectory Planning in Open-Pit Mines

The rapid evolution of artificial intelligence and Internet of Things (IoT) technology is making autonomous driving an emerging critical trend in open-pit mining operations. However, current systems still suffer from heavy reliance on manual safety interventions, as well as limitations in inertial c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE internet of things journal Ročník 12; číslo 23; s. 51064 - 51076
Hlavní autoři: Zhu, Desheng, Huang, Zhipeng, Xiong, Yijin, Wang, Chunhui, Yang, Kehu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.12.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accidents
Artificial intelligence
Autonomous mining vehicle
Autonomous vehicles
Collision avoidance
Conflict resolution
Constraints
Data mining
Driving
Dynamic models
Freezing
Integer programming
Internet of Things
intersection management
Linear programming
Loading
Mines
Mixed integer
model predictive control (MPC)
nonlinear optimization method
Open pit mining
Pits (excavations)
Planning
Predictive control
Real time
Real-time systems
Roads
Safety
Smoothness
Speed limits
Strategy
Trajectory planning
ISSN:2327-4662, 2327-4662
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The rapid evolution of artificial intelligence and Internet of Things (IoT) technology is making autonomous driving an emerging critical trend in open-pit mining operations. However, current systems still suffer from heavy reliance on manual safety interventions, as well as limitations in inertial control of large vehicles and responses to uncertain environments. To address these issues, this study develops an autonomous driving planning framework based on model predictive control-mixed-integer programming (MPC-MIP). First, it defines three conflict modes for two key conflict areas in open-pit mines-intersections and overlapping sections. By encoding passage order with binary variables and integrating a collision detection algorithm via elliptical contour fitting, conflict resolution conditions are constructed. Second, leveraging a spatial-domain dynamic model and a discretized multivehicle path representation, an objective function for multivehicle cooperative trajectory planning is established, considering total passage time, speed limit loss, and motion smoothness. Conflict resolution conditions are embedded as constraints, forming an MIP model that optimizes both mining trucks' passage order and speed. Finally, an online solution method based on MPC is proposed, incorporating an integer constraint-freezing strategy for state evolution and an accelerated computing strategy to enable real-time multitruck cooperative trajectory planning. Simulations show that in a 12-truck scenario, compared with existing methods, this method has a 10.68% optimality loss rate and online planning time within 500 ms, enhancing efficiency and reducing complexity. Laboratory vehicle tests confirm 100% collision-free performance in typical loading cycle tasks, even with 5% positioning error interference.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2025.3612025