Force-based perception and manipulation, the DTU team competing in MBZIRC 2017

Christopher Prinds Bilberg, Christian Aamand Witting, Nils Axel Andersen*, Ole Ravn

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

This paper presents how the team from the Technical University of Denmark (DTU) implemented and solved the second challenge of the Mohamed Bin Zayed International Robotics Challenge. The competition was imitating a disaster scene where a robotic platform had to operate autonomously in a partly known environment to localize and manipulate a valve on a panel. To solve the given problem, the robot needs to be able to perceive the environment reliably. This is often accomplished using vision based solutions, however these might not always be feasible. Thus we show how force feedback can successfully be used as an alternative way of perception. To accomplish this the team equipped a robot arm with a force torque sensor, allowing the robot to perceive its environment through direct contact. This approach resulted in a robust solution of the task, independent of several external factors, such as lighting, which might affect a more traditional approach. First the theory and thoughts behind the implementation is presented, followed by an evaluation of the results from physical experiments and the competition itself, ultimately resulting in a robust solution which performed without errors in the competition.

Original languageEnglish
JournalJournal of Field Robotics
Volume36
Issue number3
Pages (from-to)517-530
ISSN1556-4959
DOIs
Publication statusPublished - 2019

Keywords

  • Control
  • Force feedback
  • Mobile manipulation
  • Perception
  • Wheeled robots

Cite this