Onboard MuJoCo-based Model Predictive Control for Shipboard Crane with Double-Pendulum Sway Suppression

2026-03-17

AI Summary

This work addresses the challenge of controlling offshore cranes, where wind and wave disturbances readily excite severe double-pendulum oscillations in suspended loads. Conventional control strategies rely on oversimplified models, while reinforcement learning approaches often suffer from limited generalization. To overcome these limitations, the paper proposes a real-time model predictive control (MPC) framework leveraging MuJoCo-based physics simulation, integrated with the cross-entropy method (CEM) for sampling-based receding-horizon optimization. The approach directly evaluates action sequences within the simulator to jointly optimize target tracking and swing suppression, eliminating the need for complex analytical models or extensive offline training. Notably, it achieves efficient and robust control of the double-pendulum system—including unmodeled perturbations such as added payloads and external disturbances—on resource-constrained embedded platforms. Experimental results demonstrate significant performance improvements over traditional PID and deep reinforcement learning baselines, with full real-time deployability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Transferring heavy payloads in maritime settings relies on efficient crane operation, limited by hazardous double-pendulum payload sway. This sway motion is further exacerbated in offshore environments by external perturbations from wind and ocean waves. Manual suppression of these oscillations on an underactuated crane system by human operators is challenging. Existing control methods struggle in such settings, often relying on simplified analytical models, while deep reinforcement learning (RL) approaches tend to generalise poorly to unseen conditions. Deploying a predictive controller onto compute-constrained, highly non-linear physical systems without relying on extensive offline training or complex analytical models remains a significant challenge. Here we show a complete real-time control pipeline centered on the MuJoCo MPC framework that leverages a cross-entropy method planner to evaluate candidate action sequences directly within a physics simulator. By using simulated rollouts, this sampling-based approach successfully reconciles the conflicting objectives of dynamic target tracking and sway damping without relying on complex analytical models. We demonstrate that the controller can run effectively on a resource-constrained embedded hardware, while outperforming traditional PID and RL baselines in counteracting external base perturbations. Furthermore, our system demonstrates robustness even when subjected to unmodeled physical discrepancies like the introduction of a second payload.

Problem

• double-pendulum sway
• shipboard crane
• model predictive control
• external perturbations
• underactuated system

Innovation

• Model Predictive Control
• MuJoCo
• Double-Pendulum Sway Suppression
• Cross-Entropy Method
• Embedded Real-Time Control