A graph based hybrid approach of offline pre-planning and online re-planning for efficient assembly under realtime constraints

  • Authors:

  • Daniel Ewert;Sebastian Thelen;Ralph Kunze;Marcel Mayer;Daniel Schilberg;Sabina Jeschke

  • Affiliations:

  • RWTH Aachen University, Center for Learning and Knowledge Management and Institute of Information Management in Mechanical Engineering, Aachen, Germany;RWTH Aachen University, Center for Learning and Knowledge Management and Institute of Information Management in Mechanical Engineering, Aachen, Germany;RWTH Aachen University, Center for Learning and Knowledge Management and Institute of Information Management in Mechanical Engineering, Aachen, Germany;RWTH Aachen University, Chair and Institute of Industrial Engineering and Ergonomics, Aachen, Germany;RWTH Aachen University, Center for Learning and Knowledge Management and Institute of Information Management in Mechanical Engineering, Aachen, Germany;RWTH Aachen University, Center for Learning and Knowledge Management and Institute of Information Management in Mechanical Engineering, Aachen, Germany

  • Venue:
  • ICIRA'10 Proceedings of the Third international conference on Intelligent robotics and applications - Volume Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Assembly tasks, e.g. the assembly of an automobile headlight, are a big challenge for nowadays planning systems. Depending on the problem domain, a planner has to deal with a huge number of objects which can be combined in several ways. Uncertainty about the outcome of actions and the availability of parts to be assembled even worsens the problem. As a result, classic approaches have shown to be of little use for reactive (online) planning during assembly, due to the huge computational complexity. The approach proposed in this paper bypasses this problem by calculating the complex planning problems, e.g. which parts must be mounted in which sequence, prior to the actual assembly. During assembly the precalculated solutions are then used to provide fast decisions allowing an efficient execution of the assembly. Within this paper this online planning combined with offline planning and the assessment of realtime constraints during assembly could be executed in the future will be described.