Embedded Files
[2024] AGV Indoor Localization: A High Fidelity Positioning and Map Building Solution based on Drawstring Displacement Sensors.
In this paper, a novel method is presented to significantly enhance the positioning precision of indoor unmanned guided vehicles. The approach involves several steps, including setting up hardware configurations and collecting relevant data by installing necessary devices and system packages within the robot operating system (ROS). Trilateration is employed to determine the relative position of the mobile robot using distance measurements. Coordinate transformation is then conducted to convert the collected input data of relative distances and orientations. Trajectory paths are obtained, and occupancy maps are constructed to estimate the resulting trajectory and generate a 2D grid map. Indoor localization and mapping are achieved using three drawstring displacement sensors along with orientation information from an Inertial Measurement Unit (IMU). The proposed method is extensively evaluated through experimentation on predefined navigation paths, and its performance is compared to state-of-the-art methods such as RealSense T265, Hector SLAM, and wheel odometry. The results show that the proposed method exhibits compelling performance in both mean error and occupancy map construction.
[2024] GNN-based Reverse Design for Mechanical Systems: Bridging Trajectory and Mechanical Design
This paper takes up the mantle of presenting a streamlined and accurate approach for devising trajectory-mechanism designs. This is achieved through the synergistic integration of multiple deep-learning prediction models, which serve to unveil the intricate interplay between the components of a linkage mechanism and the intended trajectory. To establish a robust foundation, a ground truth generation system is crafted using Rhino 3D modeling software. This system lays the groundwork for producing essential data to be harnessed in the training and testing of the models. A comprehensive series of experiments is then conducted to unearth solutions that can generate predictive trajectories aligned with stringent design requisites.
[2023] Cost-effective Concrete Fabrication for Large Irregularly Shaped Architectural Structures
This paper presents a pipeline for 3DCP by optimizing the material used in an irregularly shaped PETG formwork to ensure sufficient stiffness under dynamic loading conditions, while reducing the supporting equipment and costs in the manufacturing industry. The developed framework was validated through a case study that fabricated a concrete wall using a six-axis industrial robotic arm with a custom 3D printing system and parametric design modeling. Comprehensive failure analysis and numerical prediction performance were conducted to validate the proposed pipeline's viability. The formwork reinforcement process encourages smart manufacturing automation and customization, improving production precision. The presented insights offer exciting challenges and inspiration for future manufacturing industries.
This paper presents the first comprehensive attempt to use Long Short Term Memory (LSTM), a deep learning architecture, to approximate load trajectories using a dataset collected through simulation and real-world conditions. The presented framework establishes reasonably high correlations between crane motion and load movement, indicating its effectiveness and robustness. Unlike previous works, this study uses two approaches to collect the dataset: simulation and real-world conditions. For the real-world scenario, a time-based robotic crane controller is equipped with an IMU tracking camera to record on-the-fly movement of the hanging load. For simulation data, the Unity3D platform is used to mimic a virtual environment scenario and perform effortless data generation. The proposed framework’s novelty is demonstrated by an impressive RMSE of 8.11 and graphical visualizations that provide further insights into the analyses and evaluations conducted.
This paper presents a complete system that is capable of reconstructing the detailed surface coordinates in real-time conditions. To verify the effectiveness of the proposed method, a metal board is used as the primary material to create different curvatures physically and virtually. In particular, the real-time performance of the overall 3D surface reconstruction has been experimentally evaluated using several tools, such as KUKA KR90 R3100 robots, HoloLens 2, displacement sensor, and ArUco markers.
A novel pipeline is developed to localize the dense surface of a large-scale object at different twisting angles. A shallow artificial neural network with a single hidden layer is devised to learn the correlation between the simulated frame and ground-truth data points. As a result, the proposed framework demonstrates the robustness of the model by providing a valid and reasonable prediction performance in practical problems. Notably, remarkably low RMSE of 8 and a high 𝑅2 of 1 are yielded when evaluated in a dataset of 211 sample data. Specifically, a curvature dataset is constructed by twisting a 90 kg metal board at several angles, using two six-axis articulated industrial robots.
[2021] How Many Bedrooms Do You Need? A Real-Estate Recommender System from Architectural Floor Plan Images
This paper introduces an automated image processing method to analyze an architectural floor plan database. .e floor plan information, such as the measurement of the rooms, dimension lines, and even the location of each room, can be automatically produced. This assists the real-estate agents to maximise the chances of the closure of deals by providing explicit insights to the prospective purchasers. With a clear idea about the layout of the place, customers can quickly make an analytical decision. Succinctly, this paper utilizes both the traditional image processing and convolutional neural networks (CNNs) to detect the bedrooms by undergoing the segmentation and classification processes. A thorough experiment, analysis, and evaluation had been performed to verify the effectiveness of the proposed framework. As a result, a three-class bedroom classification accuracy of ∼ 90% was achieved when validating on more than 500 image samples that consist of the different room numbers.
[2020] Who is the designer? Arc-100 database and benchmark on architecture classification
This paper performs an architect classification based on the outward appearance of the building. An architecture database with 100 images (ARC-100) that have balanced class distribution is constructed. Among the architectural buildings, the best performance is 71% for 5-class classification. Convolutional neural networks (CNNs) have demonstrated breakthrough performance on various classification tasks in recent studies, and even outperform human experts in specific tasks. Thus, for the baseline evaluation, multiple pretrained CNN models are employed with slight modifications. Prior to the feature extraction and classification processes, the removal of background noise is performed using two approaches: manually and automatically. The former approach requires high human intervention, while the latter utilizes the cutting-edge object segmentation technology, namely mask regional convolutional neural network (R-CNN). The illustration of the experiment training progress and the confusion matrix are reported, to allow further interpretation and analysis for the model trained.
Page updated
Report abuse