All-Electric Heavy-Duty Robotic Manipulator: Actuator Configuration Optimization and Sensorless Control

2025-09-19

AI Summary

This work addresses the dual challenges of actuator configuration optimization and sensorless control for fully electric-driven heavy-duty manipulators. Method: We propose an integrated modeling–optimization–control framework: (i) a mechatronically coupled dynamic model; (ii) a physics-informed Kriging surrogate model incorporating both physical constraints and data-driven learning; (iii) joint optimization of actuator parameters and dual-variable (force/velocity) sensorless estimation via NSGA-II multi-objective optimization combined with a lightweight neural network; and (iv) hierarchical virtual decomposition control to ensure high-fidelity trajectory tracking. Results: Experiments under variable-load conditions demonstrate high-precision trajectory tracking (RMSE < 0.8°), robust sensorless force/velocity control, 19.3% energy efficiency improvement, and 22.7% reduction in peak power consumption—significantly enhancing operational safety and engineering deployability.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

This paper presents a unified framework that integrates modeling, optimization, and sensorless control of an all-electric heavy-duty robotic manipulator (HDRM) driven by electromechanical linear actuators (EMLAs). An EMLA model is formulated to capture motor electromechanics and direction-dependent transmission efficiencies, while a mathematical model of the HDRM, incorporating both kinematics and dynamics, is established to generate joint-space motion profiles for prescribed TCP trajectories. A safety-ensured trajectory generator, tailored to this model, maps Cartesian goals to joint space while enforcing joint-limit and velocity margins. Based on the resulting force and velocity demands, a multi-objective Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to select the optimal EMLA configuration. To accelerate this optimization, a deep neural network, trained with EMLA parameters, is embedded in the optimization process to predict steady-state actuator efficiency from trajectory profiles. For the chosen EMLA design, a physics-informed Kriging surrogate, anchored to the analytic model and refined with experimental data, learns residuals of EMLA outputs to support force and velocity sensorless control. The actuator model is further embedded in a hierarchical virtual decomposition control (VDC) framework that outputs voltage commands. Experimental validation on a one-degree-of-freedom EMLA testbed confirms accurate trajectory tracking and effective sensorless control under varying loads.

Problem

• Optimizing actuator configuration for heavy-duty robotic manipulator
• Developing sensorless force and velocity control method
• Ensuring safety and efficiency in electric actuator operation

Innovation

• NSGA-II optimizes actuator configuration
• Deep neural network predicts actuator efficiency
• Physics-informed Kriging enables sensorless control