Research Analyzer
← Back ICRA 2026

Run-Time Optimization of Overall Energy Consumption in Lightweight Collaborative Arms for Repetitive Tasks

Ahmadreza Zarei, Sajad Shahsavari, Juha Plosila, Hashem Haghbayan

PDF

AI summary

Key figure (auto-extracted from paper)
Jointly optimizing mechanical motion and computational frequency at runtime significantly reduces total energy consumption in lightweight collaborative robots.
Energy optimization Collaborative robots Bayesian optimization Dynamic voltage scaling Runtime control Computational load

Problem

Current energy optimization methods for lightweight industrial robots treat mechanical motion and computational load as independent, ignoring their interdependence and leading to suboptimal energy efficiency.

Approach

A runtime Bayesian optimization framework that simultaneously tunes the robot's motion velocity and acceleration alongside the CPU's dynamic voltage/frequency scaling to minimize total energy while meeting task constraints.

Key results

  • Computational energy consumption is comparable to mechanical energy in lightweight arms
  • A Bayesian optimization framework for joint motion and CPU frequency tuning
  • 3.7% energy reduction in pick-and-place tasks
  • 6.2% energy reduction in sorting tasks compared to separate optimization

Why it matters

Enables more energy-efficient and sustainable deployment of intelligent collaborative robots in modern manufacturing and automation.

Abstract

Lightweight industrial robots are increasingly de- ployed alongside humans to perform diverse and intelligent industrial tasks. A major concern with these robots is energy efficiency, driven by rising operational costs and environmental impacts. A growing contributor to energy use is the heavy computational workload of their electronic components. Al- though motion configurations and computational load are often interdependent, current state-of-the-art energy optimization methods tend to address them separately, focusing on individual consumption. In this work, we demonstrate that computational energy is comparable to mechanical energy and show how their dependency affects overall consumption in a Franka Emika Panda robot equipped with a multi-core processing system and two depth cameras. Building on this understanding, we propose a Bayesian approach for the joint optimization of mechanical motion and computational frequency in a robotic arm. Experiments show that the proposed method enables the Franka arm to reduce energy use by 3.7% in pick-and-place tasks and 6.2% in sorting tasks, compared to methods that optimize locomotion and computation separately.

Index terms

Optimization and Optimal Control Energy and Environment-Aware Automation Manipulation Planning

Related papers