← Back ICRA 2026

COMPAct: Computational Optimization and Automated Modular Design of Planetary Actuators

Aman Singh, Deepak Kapa, Suryank Joshi, Shishir Kolathaya

PDF

AI summary

Key figure (auto-extracted from paper)

A unified framework optimizes planetary gearbox parameters for four architectures and automatically generates 3D-printable CAD models, validated through hardware testing.

planetary gearboxes actuator optimization parametric CAD 3D printing robotic design computational design

Problem

Prior robotic actuator design frameworks often neglect gearbox optimization, overlook mass-efficiency trade-offs, and lack automated CAD generation for rapid prototyping.

Approach

COMPAct formulates a constrained optimization problem to minimize mass and width while maximizing efficiency across four planetary gearbox types, then links optimal parameters to a parametric CAD system for automated 3D printing.

Key results

Mass model validated with <0.03 kg RMS error against CAD estimates
Optimal gearbox types identified across 4:1–60:1 ratios
Automated parametric CAD generation enables direct 3D printing
Hardware validation confirms SSPG achieves 60–80% efficiency and 242.7 Nm/rad stiffness

Why it matters

Enables roboticists and engineers to rapidly design, optimize, and fabricate high-performance planetary actuators without manual CAD iteration.

Abstract

The optimal design of robotic actuators is a critical area of research, yet limited attention has been given to optimiz- ing gearbox parameters and automating actuator CAD. This paper introduces COMPAct: Computational Optimization and Automated Modular Design of Planetary Actuators, a framework that systematically identifies optimal gearbox parameters for a given motor across four gearbox types, single-stage planetary gearbox (SSPG), compound planetary gearbox (CPG), Wolfrom planetary gearbox (WPG), and double-stage planetary gearbox (DSPG). The framework minimizes mass and actuator width while maximizing efficiency, and further automates actuator CAD generation to enable direct 3D printing without manual redesign. Using this framework, optimal gearbox designs are ex- plored across a wide range of gear ratios, providing insights into the suitability of different gearbox types while automatically generating CAD models for all four gearbox types with varying gear ratios and motors. Two actuator types are fabricated and experimentally evaluated through power efficiency, no- load backlash, and transmission stiffness tests. Experimental results indicate that the SSPG actuator achieves a mechanical efficiency of 60–80%, a no-load backlash of 0.59◦, and a transmission stiffness of 242.7 Nm/rad, while the CPG actuator demonstrates 60% efficiency, 2.6◦backlash, and a stiffness of 201.6 Nm/rad. CODE: Github VIDEO: Supplemental Video

Index terms

Actuation and Joint Mechanisms Legged Robots Mechanism Design