Holistic Construction Automation With Modular Robots: From High-Level Task Specification to Execution

In situ robotic automation in construction is challenging due to constantly changing environments, a shortage of robotic experts, and a lack of standardized frameworks bridging robotics and construction practices. This work proposes a holistic framework for construction task specification, optimization of robot morphology, and mission execution using a mobile modular reconfigurable robot. Users can specify and monitor the desired robot behavior through a graphical interface. In contrast to existing, monolithic solutions, we automatically identify a new task-tailored robot for every task by integrating Building Information Modeling (BIM). Our framework leverages modular robot components that enable the fast adaption of robot hardware to the specific demands of the construction task. Other than previous works on modular robot optimization, we consider multiple competing objectives, which allow us to explicitly model the challenges of real-world transfer, such as calibration errors. We demonstrate our framework in simulation by optimizing robots for drilling and spray painting. Finally, experimental validation demonstrates that our approach robustly enables the autonomous execution of robotic drilling. Note to Practitioners—Construction sites are unpredictable and constantly changing, making automation difficult. To tackle this, we propose a modular robotic system that can adapt to specific tasks. In this work, we address the challenge of automating robotic drilling and introduce a general framework that also supports other construction tasks. We use Building Information Modelling (BIM) data to automatically determine the best robot configuration by optimizing factors such as setup time and robustness to positioning errors. Through an intuitive interface, workers can specify tasks, after which they assemble the robot following the provided instructions. The result of this work is a robotic system that can be deployed on diverse construction sites while requiring only readily available BIM data and minimal user inputs. Our approach enables the same hardware to be deployed across various scenarios while accounting for site-specific challenges. A core innovation lies in combining modular robotics with automated optimization, task planning, and motion planning to minimize the need for user intervention while delivering robots specifically tailored to each task. To achieve this, we extend methods for modular robot design to account for multiple conflicting objectives in the optimization process. Experimental results demonstrate the ability of the system to perform autonomous drilling with high precision. Beyond drilling, this framework has the potential to support a wide range of applications, and we show its applicability to spray painting in simulation. Overall, it offers a practical and adaptable solution for diverse construction tasks and sites.