Robot Construction Simulation using Deep Reinforcement Learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

1 Citation (Scopus)


Currently, various types of construction robots are introduced in prefabrication construction, leading to a new research domain of Robot-Oriented Design. Although construction robotics display huge potential, its application in real construction projects is still limited. One of the reasons is the lack of a framework for collaborative robots (‘cobots’) to complete more complex tasks. Its main intention is to integrate standalone Single Task Construction Robots (STCRs) into controlled environments that enable the implementation of networked robot systems, in which various robots can be used for different types of tasks in a (semi-)automated manner. Before putting this into practice, such innovation obviously needs to be tested in a simulation environment. In this paper, we present a training mechanism for the collaborative work of the Single Task Robots in the construction process to achieve cobots’ construction simulation based on a deep reinforcement learning method.
Original languageEnglish
Title of host publicationEG-ICE 2020 Workshop on Intelligent Computing in Engineering, Proceedings
EditorsLucian-Constantin Ungureanu, Timo Hartmann
Number of pages9
ISBN (Electronic)9783798331556
Publication statusPublished - 3 Jul 2020


Dive into the research topics of 'Robot Construction Simulation using Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this