Synthetic Data Generation for the Enrichment of Civil Engineering Machine Data

Marius Krüger, Birgit Vogel-Heuser, Dominik Hujo, Johanna Walch, Theresa Prinz, Daniel Pohl, Suhyun Cha, Cornelia Kerausch

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

Abstract

Artificial Intelligence (AI) is one of the most auspicious technologies in the mobile machine domain. It promises to optimize the machine operation to reduce energy consumption or provide an assistant function to support the operator in challenging machine movements. A large amount of machine data is required to train and build AI models. These data sets are often not available due to missing or faulty sensors in the machine. However, construction machines are partly equipped with temporary sensors for data collection so that small data sets are available. Nevertheless, these data sets are very small and must be extended with more realistic data. Generating synthetic data to enrich real data is a promising approach to overcome the obstacle of small data sets. This paper presents a data generator to produce synthetic, physically-informed data for the pendulum trajectory of a flexible attachment tool on a construction machine. The data generator calculates a reference trajectory based on a physical model of the machine. This reference trajectory is generated by solving an optimization problem to cover the machine movement that an experienced machine operator would drive. Reasonable deviations of these trajectories are generated by varying machine characteristics and adding external forces to the physical model to simulate rough environmental conditions. The data generator is implemented for the grab system movement of a civil engineering machine.

Original languageEnglish
Title of host publicationConstruction Logistics, Equipment, and Robotics - Proceedings of the CLEaR Conference 2023
EditorsJohannes Fottner, Konrad Nübel, Dominik Matt
PublisherSpringer Science and Business Media Deutschland GmbH
Pages166-175
Number of pages10
ISBN (Print)9783031440205
DOIs
StatePublished - 2024
EventInternational Conference on Construction Logistics, Equipment, and Robotics, CLEaR 2023 - Munich , Germany
Duration: 9 Oct 202311 Oct 2023

Publication series

NameLecture Notes in Civil Engineering
Volume390 LNCE
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

ConferenceInternational Conference on Construction Logistics, Equipment, and Robotics, CLEaR 2023
Country/TerritoryGermany
CityMunich
Period9/10/2311/10/23

Keywords

  • Civil Engineering Machine
  • Synthetic Data
  • Trajectory Planning

Fingerprint

Dive into the research topics of 'Synthetic Data Generation for the Enrichment of Civil Engineering Machine Data'. Together they form a unique fingerprint.

Cite this