Graph Neural Network-Based Predictive Modeling for Robotic Plaster Printing

2025-03-31

AI Summary

Accurate prediction and autonomous control of wall surface morphology remain challenging in robotic shotcrete plastering. Method: This paper proposes an end-to-end graph neural network (GNN)-based simulation framework for spray processes. It introduces a novel particle-based wall domain representation coupled with dynamic end-effector interaction modeling, implements an encoder–processor–decoder GNN architecture, integrates trajectory features (position, velocity, orientation) and process parameters, and employs Bayesian hyperparameter optimization for joint trajectory generation and parameter tuning. Contribution/Results: Experiments demonstrate significantly lower prediction error on unseen test data compared to baselines, with high multi-step prediction stability and strong generalization. This work is the first to deeply integrate GNNs with particle systems, empirically validating the framework’s feasibility as a high-fidelity digital twin simulator for fully autonomous plastering operations.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This work proposes a Graph Neural Network (GNN) modeling approach to predict the resulting surface from a particle based fabrication process. The latter consists of spray-based printing of cementitious plaster on a wall and is facilitated with the use of a robotic arm. The predictions are computed using the robotic arm trajectory features, such as position, velocity and direction, as well as the printing process parameters. The proposed approach, based on a particle representation of the wall domain and the end effector, allows for the adoption of a graph-based solution. The GNN model consists of an encoder-processor-decoder architecture and is trained using data from laboratory tests, while the hyperparameters are optimized by means of a Bayesian scheme. The aim of this model is to act as a simulator of the printing process, and ultimately used for the generation of the robotic arm trajectory and the optimization of the printing parameters, towards the materialization of an autonomous plastering process. The performance of the proposed model is assessed in terms of the prediction error against unseen ground truth data, which shows its generality in varied scenarios, as well as in comparison with the performance of an existing benchmark model. The results demonstrate a significant improvement over the benchmark model, with notably better performance and enhanced error scaling across prediction steps.

Problem

• Predicts plaster surface using robotic arm trajectory features
• Optimizes printing parameters for autonomous plastering process
• Improves performance over benchmark models in prediction accuracy

Innovation

• GNN predicts plaster surface from robotic trajectory
• Particle-based graph model optimizes printing parameters
• Bayesian-optimized encoder-processor-decoder architecture