Physics-Informed Neural Networks-Based Online Excavation Trajectory Planning for Unmanned Excavator

被引:1
作者
Fu, Tao [1 ,2 ]
Hu, Zhengguo [1 ]
Zhang, Tianci [1 ,3 ]
Bi, Qiushi [4 ]
Song, Xueguan [1 ,5 ]
机构
[1] Dalian Univ Technol, Sch Mech Engn, Dalian 116024, Peoples R China
[2] Beijing Tianma Intelligent Control Technol Co Ltd, Beijing 101399, Peoples R China
[3] Yanshan Univ, Sch Vehicle & Energy, Qinhuangdao 066004, Peoples R China
[4] Jilin Univ, Sch Mech & Aerosp Engn, Changchun 130025, Peoples R China
[5] Dalian Univ Technol, State Key Lab High Performance Precis Mfg, Dalian 116024, Peoples R China
基金
中国国家自然科学基金;
关键词
Online excavation trajectory planning; Physics-informed machine learning; Unmanned excavator; Autonomous excavation; CABLE SHOVEL; ENERGY; OPTIMIZATION;
D O I
10.1186/s10033-024-01109-2
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
As a large-scale mining excavator, the electric shovel (ES) has been extensively employed in open-pit mines for overburden removal and mineral loading. In the development of unmanned operations for ES, dynamic excavation trajectory planning is essential, as it directly influences operational efficiency and energy consumption by guiding the dipper during excavation. However, conventional optimization-based methods for excavation trajectory planning typically start from scratch, resulting in a time-consuming process that fails to meet real-time requirements. To address this challenge, we propose an innovative online trajectory planning framework based on physics-informed neural networks (PINNOTP) that utilizes advanced data-driven techniques. The input to PINNOTP consists of on-site working conditions, including the initial state of the ES and the material surface being excavated. The output is a smooth, polynomial-based curve that serves as the reference trajectory for the dipper. To ensure smooth execution of the generated trajectory, prior domain knowledge-such as physics-based target-oriented constraints, essential system dynamics, and mechanical constraints-is explicitly incorporated into the loss function during training. A case study is presented to validate the proposed method, demonstrating that PINNOTP effectively addresses the challenges of online excavation trajectory planning.
引用
收藏
页数:17
相关论文
共 33 条
[1]   Digging Trajectory Optimization for Cable Shovel Robotic Excavation Based on a Multi-Objective Genetic Algorithm [J].
Bi, Qiushi ;
Wang, Guoqiang ;
Wang, Yongpeng ;
Yao, Zongwei ;
Hall, Robert .
ENERGIES, 2020, 13 (12)
[2]   The point-to-point multi-region energy-saving trajectory planning for a mechatronic elevator system [J].
Chen, Kun-Yung ;
Fung, Rong-Fong .
APPLIED MATHEMATICAL MODELLING, 2016, 40 (21-22) :9269-9285
[3]   APPROXIMATIONS OF CONTINUOUS FUNCTIONALS BY NEURAL NETWORKS WITH APPLICATION TO DYNAMIC-SYSTEMS [J].
CHEN, TP ;
CHEN, H .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (06) :910-918
[4]  
Collobert R., 2008, P 25 INT C MACH LEAR, DOI DOI 10.1145/1390156.1390177
[5]   Key challenges in automation of earth-moving machines [J].
Dadhich, S. ;
Bodin, U. ;
Andersson, U. .
AUTOMATION IN CONSTRUCTION, 2016, 68 :212-222
[6]   Autonomous excavation using a rope shovel [J].
Dunbabin, Matthew ;
Corke, Peter .
JOURNAL OF FIELD ROBOTICS, 2006, 23 (6-7) :379-394
[7]   Sensing, perception, decision, planning and action of autonomous excavators [J].
Eraliev, Oybek Maripjon Ugli ;
Lee, Kwang-Hee ;
Shin, Dae-Young ;
Lee, Chul-Hee .
AUTOMATION IN CONSTRUCTION, 2022, 141
[8]   Mechanics of cable shovel-formation interactions in surface mining excavations [J].
Frimpong, S ;
Hu, YF ;
Awuah-Offei, K .
JOURNAL OF TERRAMECHANICS, 2005, 42 (01) :15-33
[9]   Novel Hybrid Physics-Informed Deep Neural Network for Dynamic Load Prediction of Electric Cable Shovel [J].
Fu, Tao ;
Zhang, Tianci ;
Cui, Yunhao ;
Song, Xueguan .
CHINESE JOURNAL OF MECHANICAL ENGINEERING, 2022, 35 (01)
[10]   Trajectory planning based on minimum absolute input energy for an LCD glass-handling robot [J].
Fung, Rong-Fong ;
Cheng, Yi-Hsin .
APPLIED MATHEMATICAL MODELLING, 2014, 38 (11-12) :2837-2847