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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Günthner, W., Borrmann, A.: Digitale Baustelle- innovativer Planen, effizienter Ausführen. Springer, Berlin, Heidelberg (2011). https://doi.org/10.1007/978-3-642-16486-6
Nübel, K., Bühler, M.M., Jelinek, T.: Federated digital platforms: value chain integration for sustainable infrastructure planning and delivery. Sustainability 13, 8996 (2021)
Latombe, J.-C.: Robot Motion Planning. Springer US, Boston, MA (1991). https://doi.org/10.1007/978-1-4615-4022-9
Bergman, K.: On Motion Planning Using Numerical Optimal Control. Linköping University Electronic Press, Linköping (2019)
Mareczek, J.: Grundlagen der Roboter-Manipulatoren – Band 2: Pfad- und Bahnplanung, Antriebsauslegung, Regelung, 1 edn. Aufl. 2020. Springer, Berlin, Heidelberg (2020). https://doi.org/10.1007/978-3-662-59561-9
Sarwar, M.U., Sohail, M., Din, M.U., et al.: A dataset generation tool for deep learning-based motion planning in complex environments. In: IEEE ETFA 2021, pp. 1–4 (2021)
Zhang, J., Chen, H., Song, S., et al.: Reinforcement learning-based motion planning for automatic parking system. IEEE Access 8, 154485–154501 (2020)
Dankar, F.K., Ibrahim, M.: fake it till you make it: guidelines for effective synthetic data generation. Appl. Sci. 11, 2158 (2021)
Dankar, F.K., Ibrahim, M.K., Ismail, L.: A multi-dimensional evaluation of synthetic data generators. IEEE Access 10, 11147–11158 (2022)
Nikolenko, S.I.: Synthetic Data for Deep Learning, vol. 174. Springer International Publishing, Cham (2021). https://doi.org/10.1007/978-3-030-75178-4
Emam, K., Mosquera, L., Hoptroff, R.: Practical Synthetic Data Generation: Balancing Privacy and the Broad Availability of Data, First edition. O’Reilly, Beijing, Boston, Farnham, Sebastopol, Tokyo (2020)
Jair Martínez López, A., Raúl Pale Suarez, J., Tinoco Varela, D.: Execution and analysis of classic neural network algorithms when they are implemented in embedded systems. In: MATEC Web Conference, vol. 292, pp. 1012 (2019)
Shin, J.-H., Lee, J.-J.: Trajectory planning and robust adaptive control for underactuated manipulators. Electron. Lett. 34, 1705 (1998)
Wu, Z., Xia, X.: Optimal motion planning for overhead cranes. IET Control Theory Appl. 8, 1833–1842 (2014)
Wu, Y., Sun, N., Chen, H. et al.: Nonlinear time-optimal trajectory planning for varying-rope-length overhead cranes. AA 38, 587–594 (2018)
Moreno-Valenzuela, J., Aguilar-Avelar, C.: Motion Control of Underactuated Mechanical Systems, vol. 88. Springer International Publishing, Cham (2018). https://doi.org/10.1007/978-3-319-58319-8
Liu, Y., Yu, H.: A survey of underactuated mechanical systems. IET Control Theory Appl. 7, 921–935 (2013)
Acknowledgement
This work was supported by the Bayerische Forschungsstiftung (BFS) through the project “Maschinenführer-zentrierte Parametrierung von Artificial Intelligence für eng gekoppelte, verteilte, vernetzte Steuerungssysteme (OpAI4DNCS)”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Krüger, M. et al. (2024). Synthetic Data Generation for the Enrichment of Civil Engineering Machine Data. In: Fottner, J., Nübel, K., Matt, D. (eds) Construction Logistics, Equipment, and Robotics. CLEaR 2023. Lecture Notes in Civil Engineering, vol 390. Springer, Cham. https://doi.org/10.1007/978-3-031-44021-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-44021-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44020-5
Online ISBN: 978-3-031-44021-2
eBook Packages: EngineeringEngineering (R0)