Research Analyzer
← Back ICRA 2026

Autonomous Block Assembly for Boom Cranes with Passive Joint Dynamics: Integrated Vision MPC Control

Gerald Ebmer, Minh Nhat Vu, Tobias Glück, Wolfgang Kemmetmueller

PDF

AI summary

Key figure (auto-extracted from paper)
An integrated vision-MPC framework successfully suppresses passive joint sway and enables precise autonomous block assembly on a laboratory-scale crane testbed.
Autonomous cranes Model predictive control Passive joint dynamics Vision-based control Collision-aware planning Construction automation

Problem

Articulated boom cranes suffer from pendulum-like sway due to passive joints, which severely hinders precise autonomous placement of prefabricated blocks in cluttered construction sites. Prior work addresses perception, planning, and control in isolation, leaving a gap for unified closed-loop autonomy.

Approach

The authors combine real-time vision pose estimation, collision-aware B-spline path planning, and nonlinear model predictive control into a single closed-loop system that actively dampens sway while tracking feasible trajectories.

Key results

  • Integrated perception-planning-control architecture for under-actuated cranes
  • Real-time collision-aware B-spline path planner with anytime CPU performance
  • Laboratory-scale validation of autonomous pick-and-place and obstacle avoidance
  • Sway damping reducing settling times by over an order of magnitude

Why it matters

Establishes a real-time feasible foundation for automating precise, sway-compensated assembly tasks in dynamic construction environments.

Abstract

This paper presents an autonomous control frame- work for articulated boom cranes performing prefabricated block assembly in construction environments. The key challenge addressed is precise placement control under passive joint dynamics that cause pendulum-like sway, complicating the accurate positioning of building components. Our integrated approach combines real-time vision-based pose estimation of building blocks, collision-aware B-spline path planning, and nonlinear model predictive control (NMPC) to achieve au- tonomous pickup, placement, and obstacle-avoidance assem- bly operations. The framework is validated on a laboratory- scale testbed that emulates crane kinematics and passive dy- namics while enabling rapid experimentation. The collision- aware planner generates feasible B-spline references in real- time on CPU hardware with anytime performance, while the NMPC controller actively suppresses passive joint sway and tracks the planned trajectory under continuous vision feedback. Experimental results demonstrate autonomous block stacking and obstacle-avoidance assembly, with sway damping reducing settling times by more than an order of magnitude compared to uncontrolled passive dynamics, confirming the real-time feasibility of the integrated approach for construction automation.

Index terms

Robotics and Automation in Construction Integrated Planning and Control Building Automation

Related papers