Research Analyzer
← Back ICRA 2026

Leveraging Two Robotic Arms for Tight Assembly Performance Gains

Dror Livnat, Yuval Lavi, Michael M. Bilevich, Dan Halperin

PDF

AI summary

Key figure (auto-extracted from paper)
Coordinated two-arm assembly reduces average execution time by over 50% while improving trajectory accuracy and search efficiency compared to single-arm systems.
Two-arm robotics Tight assembly Motion planning Inverse kinematics Industrial automation CAD-to-robotics

Problem

Single-arm robotic assembly is often slow and constrained in tight environments, lacking efficient methods for coordinated multi-arm planning that translate CAD models directly into collision-free trajectories.

Approach

The authors introduce a novel end-to-end framework with two new algorithms (CPW-IK and GPW-IK) that compute synchronized, collision-free joint-space trajectories for two robotic arms directly from CAD models, optimizing per-segment motion splits to minimize makespan.

Key results

  • Over 50% reduction in average assembly execution time with GPW-IK
  • Higher-quality trajectories with bounded path accuracy
  • Accelerated search for valid robot placements
  • Theoretical execution time guarantees validated on real hardware

Why it matters

Accelerates industrial assembly processes, enabling faster, more flexible, and scalable robotic manufacturing for Industry 4.0.

Abstract

We provide a novel end-to-end framework for the execution of an assembly operation by two robotic arms, given the digital CAD models of the parts and their desired relative placement in their assembled state. We analyze and demonstrate the advantages of using two robotic arms simultaneously in tight assembly operations, compared to single-arm systems. Our method is implemented in both simulation and using physical robots. It provides theoretical guarantees on execution time and trajectory accuracy, supported by empirical evidence. In partic- ular, we show that coordinated movement of two arms reduces average execution time by more than 50% compared to using a single arm only, produces higher-quality trajectories, and accel- erates the search for valid robot placements. Furthermore, we establish bounds on the required dimensions of the robotic cell. Our open source software together with real-life video demonstrations are available in our project page.

Index terms

Dual Arm Manipulation Assembly Motion and Path Planning

Related papers