EcBot: Data-Driven Energy Consumption Open-Source MATLAB Library for Manipulators

2025-08-08

AI Summary

Existing robotic arm energy consumption models are predominantly derived from traditional industrial robots, exhibiting poor generalizability and insufficient accuracy. To address this, we propose the first open-source, MATLAB-based, data-driven energy modeling toolkit—eliminating reliance on theoretical kinematic and dynamic parameters and enabling accurate electrical power consumption estimation across diverse lightweight robotic arms from multiple manufacturers. Our method integrates Denavit–Hartenberg parameters, link masses, and center-of-mass information, using joint positions, velocities, accelerations, timestamped measured power, and time as inputs to construct a cross-platform, data-driven model. Evaluated on four distinct lightweight robotic arms from different vendors, the model achieves training-set RMSEs of 1.42–2.80 W and test-set RMSEs of 1.45–5.25 W. This represents a substantial improvement in both prediction accuracy and generalization capability, establishing a reliable foundation for energy-aware robot design and task scheduling in low-power applications.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Existing literature proposes models for estimating the electrical power of manipulators, yet two primary limitations prevail. First, most models are predominantly tested using traditional industrial robots. Second, these models often lack accuracy. To address these issues, we introduce an open source Matlab-based library designed to automatically generate ac{ec} models for manipulators. The necessary inputs for the library are Denavit-Hartenberg parameters, link masses, and centers of mass. Additionally, our model is data-driven and requires real operational data, including joint positions, velocities, accelerations, electrical power, and corresponding timestamps. We validated our methodology by testing on four lightweight robots sourced from three distinct manufacturers: Universal Robots, Franka Emika, and Kinova. The model underwent testing, and the results demonstrated an RMSE ranging from 1.42 W to 2.80 W for the training dataset and from 1.45 W to 5.25 W for the testing dataset.

Problem

• Existing models lack accuracy for manipulator energy estimation
• Most models are tested only on traditional industrial robots
• Need for data-driven approach with real operational data

Innovation

• Open-source MATLAB library for manipulator energy models
• Data-driven approach using real operational data
• Validated with lightweight robots from multiple manufacturers