Data-driven control of hydraulic impact hammers under strict operational and control constraints

2026-01-12

AI Summary

This work addresses the challenge of precise end-effector pose control in hydraulic impact hammers, which stems from sensor deficiencies and discrete joint actuation. The authors propose a modeling and control approach that relies solely on approximately 68 minutes of teleoperation data. By employing supervised learning for system identification to construct an approximate dynamics model, and integrating reinforcement learning with model predictive control to synthesize a control policy, the method achieves high-fidelity sim-to-real transfer without fine-tuning. In real-world experiments, the approach attains an end-effector position error below 12 cm and a pitch angle error under 0.08 rad, satisfying the 4 cm chisel-tip accuracy requirement for rock breaking. This significantly reduces reliance on highly accurate analytical models and large-scale interactive training data.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents a data-driven methodology for the control of static hydraulic impact hammers, also known as rock breakers, which are commonly used in the mining industry. The task addressed in this work is that of controlling the rock-breaker so its end-effector reaches arbitrary target poses, which is required in normal operation to place the hammer on top of rocks that need to be fractured. The proposed approach considers several constraints, such as unobserved state variables due to limited sensing and the strict requirement of using a discrete control interface at the joint level. First, the proposed methodology addresses the problem of system identification to obtain an approximate dynamic model of the hydraulic arm. This is done via supervised learning, using only teleoperation data. The learned dynamic model is then exploited to obtain a controller capable of reaching target end-effector poses. For policy synthesis, both reinforcement learning (RL) and model predictive control (MPC) algorithms are utilized and contrasted. As a case study, we consider the automation of a Bobcat E10 mini-excavator arm with a hydraulic impact hammer attached as end-effector. Using this machine, both the system identification and policy synthesis stages are studied in simulation and in the real world. The best RL-based policy consistently reaches target end-effector poses with position errors below 12 cm and pitch angle errors below 0.08 rad in the real world. Considering that the impact hammer has a 4 cm diameter chisel, this level of precision is sufficient for breaking rocks. Notably, this is accomplished by relying only on approximately 68 min of teleoperation data to train and 8 min to evaluate the dynamic model, and without performing any adjustments for a successful policy Sim2Real transfer. A demonstration of policy execution in the real world can be found in https://youtu.be/e-7tDhZ4ZgA.

Problem

• hydraulic impact hammer
• data-driven control
• end-effector pose control
• operational constraints
• discrete control interface

Innovation

• data-driven control
• hydraulic impact hammer
• system identification
• reinforcement learning
• Sim2Real transfer