The Playback Trajectory Optimization Algorithm for Collaborative Robot

  • Youdong Chen*
  • , Qiangguo Feng
  • , Jiaxin Guo
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Teaching is a basic function of many collaborative robots. The recorded trajectories with teaching may contain noises and jumps due to hand trembling and sensor errors. When the robot replays these trajectories, these noises and jumps may cause vibrations and shocks, even damage the body of the robot. An algorithm based on CHOMP (Covariant Hamiltonian Optimization for Motion Planning) algorithm is proposed to optimize the playback trajectories of collaborative robot. The algorithm is composed of two norms in the Hilbert space. One Euclidian norm is used for the evaluation of the replay of trajectories. The other norm that combines the first and second order derivatives of trajectories is used for the evaluation of trajectory dynamic characters. Experiments of UR3 robot in both obstacle-free and obstacle environments prove that the proposed algorithm can optimize the recorded trajectories of a collaborative robot as well as enabling the trajectory to maintain useful.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1671-1676
Number of pages6
ISBN (Electronic)9781728103761
DOIs
StatePublished - 2 Jul 2018
Event2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018 - Kuala Lumpur, Malaysia
Duration: 12 Dec 201815 Dec 2018

Publication series

Name2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018

Conference

Conference2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018
Country/TerritoryMalaysia
CityKuala Lumpur
Period12/12/1815/12/18

Fingerprint

Dive into the research topics of 'The Playback Trajectory Optimization Algorithm for Collaborative Robot'. Together they form a unique fingerprint.

Cite this