High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

2025-09-22

AI Summary

Hydraulic excavators exhibit strong nonlinearity, time-varying delays, and actuator coupling, making high-precision trajectory tracking challenging; conventional model-based control lacks robustness, while pure data-driven reinforcement learning (RL) suffers from high interaction costs and poor generalization. This paper proposes EfficientTrack—a model-augmented RL framework integrating closed-loop dynamical priors. It unifies nonlinear system modeling, model predictive control (MPC), and policy optimization within a feedback-closed architecture, drastically reducing environmental interaction requirements and enabling continuous online adaptation. Simulation and real-world experiments demonstrate that EfficientTrack achieves a 52% reduction in tracking error and a 37% improvement in motion smoothness while requiring over 40% fewer interactions than baseline RL methods. Moreover, it maintains stable, high-performance tracking under dynamic disturbances such as abrupt load changes. EfficientTrack establishes a new paradigm for intelligent, efficient, and reliable control of construction machinery.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

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

Abstract

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinearities, while commonly used learning-based methods require extensive interactions with the environment, leading to inefficiency. To address these issues, we introduce EfficientTrack, a trajectory tracking method that integrates model-based learning to manage nonlinear dynamics and leverages closed-loop dynamics to improve learning efficiency, ultimately minimizing tracking errors. We validate our method through comprehensive experiments both in simulation and on a real-world excavator. Comparative experiments in simulation demonstrate that our method outperforms existing learning-based approaches, achieving the highest tracking precision and smoothness with the fewest interactions. Real-world experiments further show that our method remains effective under load conditions and possesses the ability for continual learning, highlighting its practical applicability. For implementation details and source code, please refer to https://github.com/ZiqingZou/EfficientTrack.

Problem

• Addresses complex nonlinear dynamics in hydraulic excavator trajectory tracking
• Overcomes limitations of traditional and learning-based control methods
• Improves tracking precision while reducing required environmental interactions

Innovation

• Integrates model-based learning for nonlinear dynamics
• Leverages closed-loop dynamics to improve efficiency
• Achieves high precision tracking with minimal interactions