Learning a System-Level Surrogate for Hydraulic Excavators: A Simulation-to-Real LSTM Approach

2026-07-17

AI Summary

This work addresses the challenges in autonomous hydraulic excavator development, which are hindered by the scarcity of physical platforms and the high cost of real-world experimentation. The authors propose a system-level digital twin approach based on Long Short-Term Memory (LSTM) networks, modeling the excavator as an input–output operator trained entirely within the MuJoCo simulation environment. By integrating consistency-aware state estimation with adaptive Kalman filtering, the method achieves high-fidelity closed-loop behavior transfer to real hardware without requiring explicit modeling of internal dynamics. The resulting digital twin demonstrates high accuracy in both angular velocity response and long-horizon trajectory reproduction, offering a plug-and-play surrogate that effectively bridges simulation and physical deployment.

Abstract

Developing autonomous hydraulic excavators is constrained by limited access to physical machines and the high cost of real-world experimentation. This paper proposes a simulation-to-real framework for learning a system-level digital surrogate using Long Short-Term Memory (LSTM) networks. Instead of modeling internal dynamics, the excavator is treated as an input-output operator, and the surrogate is trained to reproduce its closed-loop behavior under identical control inputs. The approach is first validated in a MuJoCo simulation environment and then transferred to a real excavator. To address measurement inconsistencies in real-world data, a consistency-aware state estimation method based on adaptive Kalman filtering is introduced. Experimental results demonstrate that the learned surrogate achieves high fidelity in both angular velocity and long-horizon trajectory reproduction under closed-loop autoregressive evaluation. These results confirm that the proposed model can serve as a drop-in surrogate for both simulation and physical systems, enabling scalable and efficient development of excavation automation algorithms.

Problem

• hydraulic excavators
• simulation-to-real
• system-level surrogate
• autonomous excavation
• digital twin

Innovation

• simulation-to-real
• LSTM
• digital surrogate
• adaptive Kalman filtering
• hydraulic excavator