Research Analyzer
← Back ICRA 2026

Singularity Analysis of ABB's GoFa 5 Robot Arm

Axel Refalo, Ilian Bonev, Clement Gosselin

PDF

AI summary

Key figure (auto-extracted from paper)
The paper identifies twelve distinct singularity types in ABB’s GoFa 5 cobot and provides simplified joint-angle thresholds to reliably avoid them, while quantifying that its complex architecture actually increases singularity risk compared to traditional designs.
Singularity analysis Collaborative robots Grassmann geometry Inverse kinematics Robot safety Kinematic architecture

Problem

Collaborative robots like the ABB GoFa 5 lack closed-form inverse kinematics and exhibit numerous, complex singularities that are poorly documented, creating safety risks and control ambiguities for programmers.

Approach

The authors apply Grassmann line geometry and wedge products to classify all unique singular configurations in the joint space, derive simplified sufficient conditions to avoid them, and compare singularity density against traditional robot architectures.

Key results

  • Classified 12 distinct singularity types in the GoFa 5 joint space
  • Mapped geometric conditions and volumes for each singularity manifold
  • Derived simplified, conservative joint-angle thresholds to avoid all singularities
  • Quantified and compared singularity prevalence across GoFa 5, UR5e, and A0509 architectures

Why it matters

Provides essential safety guidelines and architectural insights for cobot programmers and designers navigating complex kinematic behaviors.

Abstract

In the past decade, manipulator arms with non- traditional architectures—once found mainly in space and painting applications—have become popular as collaborative robots. Examples include ABB’s YuMi and GoFa, Kinova’s Link 6, and Fanuc’s CRX. These cobots lack closed-form inverse kinematics solutions, making it impossible to unambiguously select one configuration among the 16 (or infinitely many) that correspond to a given end-effector pose, which may create safety risks. Moreover, they exhibit far more singularities than typical manipulators, and most of them are far more complex to describe. Nevertheless, many authors argue these manipulators can provide improved dexterity and a larger workspace. In this paper, we analyze the singularities of ABB’s GoFa using Grassmann line geometry and provide straightforward, sufficient (though conservative) conditions for avoiding them. Then, while GoFa can exhibit over a dozen distinct singularities compared to only three (wrist, shoulder, and elbow) for traditional robot arms, we attempt to quantify which architecture actually possesses a greater amount of singular and near-singular configurations.

Index terms

Kinematics Mechanism Design Performance Evaluation and Benchmarking

Related papers