Skip to main content
European Commission logo
italiano italiano
CORDIS - Risultati della ricerca dell’UE
CORDIS

Human-robot collaborative construction system for shotcrete digitization and automation through advanced perception, cognition, mobility and additive manufacturing skills

Periodic Reporting for period 1 - RobetArme (Human-robot collaborative construction system for shotcrete digitization and automation through advanced perception, cognition, mobility and additive manufacturing skills)

Periodo di rendicontazione: 2022-06-01 al 2023-11-30

The continuous increase of the demand for construction applications, such as tunnels due to rapid urbanization in emerging economies, and the growth in construction repairs in developed countries impose excessive automation of concrete placement. Shotcrete (i.e. sprayed concrete) is the best method for construction of curved surfaces; it is also used in buildings’ façade restoration after fire or earthquakes as well as on bridges. Shotcrete is a typical example in the construction domain, where even though it is a highly mechanized procedure at present, most of construction companies mainly adopt manual shotcrete operation since there are multiple issues that hinder its automation. However, manual operation renders shotcreting time consuming, less accurate and hazardous for the operators.

The RoBétArmé project is developing a collaborative construction system for shotcrete digitization and automation with advanced perception, cognition, mobility and additive manufacturing skills. Through the introduction of new robotic and digital solutions, the project aims towards a step change in the Construction 4.0 by automating particularly laborious construction tasks in all phases of shotcrete application. RoBétArmé will firstly focus towards the digitalization of the construction site by introducing new BIMs accompanied with real-time Digital Twin and simulation environments setting the prerequisites for highly automation. RoBétArmé will deliver two collaborative construction mobile robots, consisting of an (I) Inspection-Reconnaissance mobile manipulator (IRR) to address fast, high precision modelling and rebar reinforcement through metal additive manufacturing and laser-based cleaning in the preparatory phase and (II) a Shotcrete and Finishing mobile manipulator (SFR) to address autonomous shotcrete application and surface finishing during the construction and finishing phase, respectively. New material mix-design for shotcrete will ensure CO2 reduction during this construction application. The project will demonstrate and validate the integrated solution through real diverse construction sites across different countries in Europe covering shotcreting for (1) ground support (retaining) walls, (2) tunnels and/or culverts, (3) beams & piles of buildings, and (4) the posttensioned boxes of bridges, provided by the project end-users.

For more information on RoBétArmé project, please visit: https://www.robetarme-project.eu/
The main results achieved by the project so far can be summarized in the following points:
Construction Requirements: The state-of-the-art analysis for similar technological applications in the construction domain has been performed. The use cases have been analysed in terms of user requirements and have been established. The overall system technical specifications have been set and the first version of the overall architecture has been created.
Digitalization tools: The Building Information Model (BIM) populated with shotcrete parameters has been created and the basic aspects of robot agents and shotcrete simulations have been developed. The main elements of the Digital Twin have been realized and the first IoT set of sensors has been prepared. The construction decision support system has been defined and preliminary human machine interaction interfaces have been realized
Robot Perception: A multitasking –based semantic segmentation method has been developed accompanied by the respective 3D reconstruction software to extract the geometry of the surfaces to be shotcreted. Volumetric models for the basic use cases have been created and methods for shotcrete monitoring have been realized. The sensor fusion for robot perception regarding application monitoring has been defined and the system’s orchestration engine based on Behaviour Trees has been analysed for all use cases.
Robot Hardware: Activities on hardware development have also progressed. The IRR robot manipulator has been defined and preliminary integration steps have been made w.r.t. the selective laser melting component. Its mobile platform has also defined and the sensors’ topology has been established. The first version of the SFR robot arm has been realized with limited amount of degrees of freedom as a proof of concept and experimentation with the planning and control software. A new mix-design with reduced CO2 has been realized.
Robotic skills: Data collection campaigns for shotcrete modelling have been performed. The first model for shotcrete trajectory planning application has been completed. A dynamical system for robot manipulation and control has been realized and tested in simulation environment. A surface finishing inspection module has been implemented based on depth evolution sensing. The navigation strategy in hybrid environment indoor/outdoor has been defined and preliminary implemented.
Integration and testing: A detailed integration plan has been established to guide the relevant project activities. The infrastructure for the iterative software integration based on Git environment has been set. A preliminary design for the construction testbeds has been performed.
Dissemination and communication: Several horizontal activities for diffusing project objectives, concepts and achievements to key stakeholders, and the general public have also taken place including workshops organization and participation in external initiatives.
Technological sovereignty in construction: Safety issues in construction sites and mapping of the existing standards has been conducted. A training seminar related to standards and active users’ involvement has been performed.
The key innovation results achieved so far beyond the state-of-the-art are summarized as follows:

• Definition of a comprehensive literature survey related to the digitalization technologies in the construction domain and particular in the shotcrete application; detailed specifications and overall architecture of the system.
• Development of a novel Building Information Model (BIM) that entails the parameters and specificities for shotcrete applications. Realization of a shotcrete (spray) simulation tool that models the concrete concentration and the rebound phenomenon.
• Realization of the first set of IoT sensors combining temperature, humidity, vibrations and cracks integrated with a preliminary dashboard of the Digital Twin.
• Realization of a novel semantic segmentation approach based on AI for exposed rebar/ defects in surfaces detection. Development of a novel 3D reconstruction method relied on the efficient combination of reconstruction with SLAM; Realization of novel methods for volumetric modeling.
• Development of a model based shotcrete trajectory generation algorithm. Realization of a shotcrete monitoring algorithm through precise depth evolution monitoring.
• Definition of navigation strategies related shotcrete use case. Realization of the first tractor-trailer path planning and navigation based on model predictive control.
• The first prototype of SFR robot has been developed for experimentation with kinematics and shotcrete trajectory planning. The mobile platform for the IRR robot has been identified; the IRR manipulator with the additive manufacturing nozzle has been integrated and preliminary tested.
• A comprehensive analysis related to standards and safety regulatory issues in construction domain has been completed and mapped to the shotcrete application.
RobetArme Logo