Search

The appearance of construction defects in buildings can arise from a variety of factors, ranging from issues during the design and construction phases to problems that develop over time with the lifecycle of a building. These defects require repairs, often in the context of a significant shortage of skilled labor. In addition, such work is often physically demanding and carried out in hazardous environments. Consequently, adopting autonomous robotic systems in the construction industry becomes essential, as they can relieve labor shortages, promote safety, and enhance the quality and efficiency of repair and maintenance tasks. Hereupon, the present study introduces an end-to-end framework towards the automation of shotcreting tasks in cases where construction or repair actions are required. The proposed system can scan a construction scene using a stereo-vision camera mounted on a robotic platform, identify regions of defects, and reconstruct a 3D model of these areas. Furthermore, it automatically calculates the required 3D volumes to be constructed to treat a detected defect. To achieve all of the above-mentioned technological tools, the developed software framework employs semantic segmentation and 3D reconstruction modules based on YOLOv8m-seg, SiamMask, InfiniTAM, and RTAB-Map, respectively. In addition, the segmented 3D regions are processed by the volumetric modeling component, which determines the amount of concrete needed to fill the defects. It generates the exact 3D model that can repair the investigated defect. Finally, the precision and effectiveness of the proposed pipeline are evaluated in actual construction site scenarios, featuring reinforcement bars as defective areas.

Purpose – This study aims to present a vision-guided robotic system design for application in vat photopolymerization additive manufacturing (AM), enabling vat photopolymerization AM hybrid with injection molding process. Design/methodology/approach – In the system, a robot equipped with a camera and a custom-made gripper as well as driven by a visual servoing (VS) controller is expected to perceive objective, handle variation, connect multi-process steps in soft tooling process and realize automation of vat photopolymerization AM. Meanwhile, the vat photopolymerization AM printer is customized in both hardware and software to interact with the robotic system. Findings – By ArUco marker-based vision-guided robotic system, the printing platform can be manipulated in arbitrary initial position quickly and robustly, which constitutes the first step in exploring automation of vat photopolymerization AM hybrid with soft tooling process. Originality/value – The vision-guided robotic system monitors and controls vat photopolymerization AM process, which has potential for vat photopolymerization AM hybrid with other mass production methods, for instance, injection molding.

The importance of construction automation has grown worldwide, aiming to deliver new machineries for the automation of roads, tunnels, bridges, buildings and earth-work construction. This need is mainly driven by (i) the shortage and rising costs of skilled workers, (ii) the tremendous increased needs for new infrastructures to serve the daily activities and (iii) the immense demand for maintenance of ageing infrastructure. Shotcrete (sprayed concrete) is increasingly becoming popular technology among contractors and builders, as its application is extremely economical and flexible as the growth in construction repairs in developed countries demand excessive automation of concrete placement. Even if shotcrete technology is heavily mechanized, the actual application is still performed manually at a large extend. RoBétArméEuropean project targets the Construction 4.0 transformation of the construction with shotcrete with the adoption of breakthrough technologies such as sensors, augmented reality systems, high-performance computing, additive manufacturing, advanced materials, autonomous robots and simulation systems, technologies that have already been studied and applied so far in Industry 4.0. The paper at hand showcases the development of a novel robotic system with advanced perception, cognition and digitization capabilities for the automation of all phases of shotcrete application. In particular, the challenges and barriers in shotcrete automation are presented and the RoBétArmésuggested solutions are outlined. We introduce a basic conceptual architecture of the system to be developed and we demonstrate the four application scenarios on which the system is designated to operate.

Real-time prediction of human location combined with the capability to perceive obstacles is crucial for socially-aware navigation in robotics. Our work focuses on localizing humans in the world and predicting the free space around them by incorporating other static and dynamic obstacles. We propose a multi-task learning strategy to handle both tasks, achieving this goal with minimal computational demands. We use a dataset captured in a typical warehouse environment by mounting a perception module consisting of a Jetson Xavier AGX and an Intel L515 LiDAR camera on a MiR100 mobile robot. Our method, which is built upon prior works in the field of human detection and localization demonstrates improved results in difficult cases that are not tackled in other works, such as human instances at a close distance or at the limits of the field of view of the capturing sensor. We further extend this work by using a lightweight network structure and integrating a free space segmentation branch that can independently segment the floor space without any prior maps or 3D data, relying instead on the characteristics of the floor. In conclusion, our method presents a lightweight and efficient solution for predicting human 3D location and segmenting the floor space for low-energy consumption platforms, tested in an industrial environment.

Autonomous weeding robots need to accurately detect the joint stem of grassland weeds in order to control those weeds in an effective and energy-efficient manner. In this work, keypoints on joint stems and bounding boxes around weeds in grasslands are detected jointly using multi-task learning. We compare a two-stage, heatmap-based architecture to a single-stage, regression-based architecture—both based on the popular YOLOv5 object detector. Our results show that introducing joint-stem detection as a second task boosts the individual weed detection performance in both architectures. Furthermore, the single-stage architecture clearly outperforms its competitors with an OKS of 56.3 in joint-stem detection while also achieving real-time performance of 12.2 FPS on Nvidia Jetson NX, suitable for agricultural robots. Finally, we make the newly created joint-stem ground-truth annotations publicly available for the relevant research community.

Machine learning and specifically deep learning techniques address many of the issues faced in visual object detection and classification tasks. However, they have the caveat of needing large amounts of annotated training data. In the maritime domain one may encounter objects fairly infrequently, depending on weather and location. This creates an issue of data collection. Areas such as harbors and channels see a lot of traffic, but the ships are of a specific class. Furthermore, the variability of the buoys from region to region and within regions is difficult and expensive to sample. Thus the amount and quality of available data is severely lacking. Furthermore very few publicly available maritime datasets exist In this work, we present a novel approach that detects possible “poor” training samples and automatically re-annotates them, based on the current state of the object detector. We show the applicability of our approach on real-life maritime data and show that the poor annotation quality of the datasets used can be mitigated. We show performance gain with respect to a baseline approach is proportional to the amount of poorly annotated data in the dataset. When 25% of the data is poor we achieve a 5.5%, 13.7%, and 8.0% increase in performance on 3 separate datasets, compared to a baseline model. With 50% noise we reach 58.5%, 18.7% and 94.2% increase respectively. Our approach also allows for the iterative improvement of a given dataset by providing a set of pseudo-annotations to replace the current incorrect ones.

Abstract Object detection has been in the focus of researchers within varying applications propelled by the recent advances in deep learning and neural networks. Many applications require both detection of class instances as well as a quantification of the spatial coverage of the class instances. While the performance of deep learning approaches for these tasks has been extensively studied there has not been much effort into creating a unified network structure to achieve both goals. The purpose of this paper is to present a regressor to the faster R‐CNN architecture that can help quantify the spatial coverage estimation of some detected object. The goal of the regressor is to provide a reproducible result of the spatial coverage. To demonstrate the developed architecture, an example use‐case of land cover estimation is used. The experiments conducted in this paper show that the network does not sacrifice object detection accuracy, and indicate that the network is able to estimate the spatial coverage of six different types of land.

Mobile robots should possess accurate self-localization capabilities in order to be successfully deployed in their environment. A solution to this challenge may be derived from visual odometry (VO), which is responsible for estimating the robot's pose by analysing a sequence of images. The present paper proposes an accurate, computationally-efficient VO algorithm relying solely on stereo vision images as inputs. The contribution of this work is twofold. Firstly, it suggests a non-iterative outlier detection technique capable of efficiently discarding the outliers of matched features. Secondly, it introduces a hierarchical motion estimation approach that produces refinements to the global position and orientation for each successive step. Moreover, for each subordinate module of the proposed VO algorithm, custom non-iterative solutions have been adopted. The accuracy of the proposed system has been evaluated and compared with competent VO methods along DGPS-assessed benchmark routes. Experimental results of relevance to rough terrain routes, including both simulated and real outdoors data, exhibit remarkable accuracy, with positioning errors lower than 2%.