TY - GEN
T1 - Modeling Weakly-Instrumented Excavator Arm Dynamics with Stacked-Input LSTM
AU - Hoffmann, Nicolas
AU - Cohen, Max
AU - Preda, Marius
AU - Zaharia, Titus
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - The application of machine learning for modeling complex dynamic systems, such as excavators, is gaining momentum as it offers flexibility beyond traditional mathematical models. Recent advances leverage neural networks to create data-driven models that can handle the non-linear and intricate dynamics of real machinery. However, these models often depend on expensive sensors and controlled environments. This study presents a cost-effective approach to modeling the dynamics of a weakly-instrumented 25-ton CAT 323 excavator arm using stacked-input Long Short-Term Memory (LSTM) networks. We evaluate the performance of Multi-Layer Perceptron (MLP) and LSTM architectures, both with and without input stacking, to accurately simulate excavator arm motion. Our results show that combining LSTM with stacked inputs significantly improves the model’s predictive capabilities, challenging the notion that LSTM and input stacking are redundant. These findings highlight the potential of data-driven neural network models to provide accurate and efficient solutions for dynamics modeling in complex, real-world settings, paving the way for advanced AI-based strategies in the earthworks and construction industries.
AB - The application of machine learning for modeling complex dynamic systems, such as excavators, is gaining momentum as it offers flexibility beyond traditional mathematical models. Recent advances leverage neural networks to create data-driven models that can handle the non-linear and intricate dynamics of real machinery. However, these models often depend on expensive sensors and controlled environments. This study presents a cost-effective approach to modeling the dynamics of a weakly-instrumented 25-ton CAT 323 excavator arm using stacked-input Long Short-Term Memory (LSTM) networks. We evaluate the performance of Multi-Layer Perceptron (MLP) and LSTM architectures, both with and without input stacking, to accurately simulate excavator arm motion. Our results show that combining LSTM with stacked inputs significantly improves the model’s predictive capabilities, challenging the notion that LSTM and input stacking are redundant. These findings highlight the potential of data-driven neural network models to provide accurate and efficient solutions for dynamics modeling in complex, real-world settings, paving the way for advanced AI-based strategies in the earthworks and construction industries.
KW - Construction 4.0
KW - Deep learning
KW - Excavator dynamics modelling
KW - MLP and LSTM neural networks
KW - Robotics
KW - System identification
KW - Weak instrumentation
UR - https://www.scopus.com/pages/publications/105011974308
U2 - 10.1007/978-3-031-92011-0_17
DO - 10.1007/978-3-031-92011-0_17
M3 - Conference contribution
AN - SCOPUS:105011974308
SN - 9783031920103
T3 - Lecture Notes in Networks and Systems
SP - 206
EP - 218
BT - Robot Intelligence Technology and Applications 9 - Results from the 12th International Conference on Robot Intelligence Technology and Applications
A2 - Park, Daehyung
A2 - Lee, Dae-Young
A2 - Kim, Min Jun
A2 - Liu, Cunjia
PB - Springer Science and Business Media Deutschland GmbH
T2 - 12th International Conference on Robot Intelligence Technology and Applications, RiTA 2024
Y2 - 4 December 2024 through 7 December 2024
ER -