Vision-Based UAV-UGV Collaboration for Autonomous Construction Site Preparation

Abstract

Construction site preparation tasks rely on experienced operators and heavy machinery for clearing debris, earthmoving, leveling, and soil stabilization. These actions require complex collaboration between human teams to survey the site, estimate the material condition, and guide the operators accordingly. In recent years there has been a critical labor shortage due to increasing demands in construction. Integrating autonomous systems can mitigate this gap by replacing traditional methods with robotic solutions. However, while ideal conditions for automatic systems are static and highly controlled, construction sites are dynamic and unstructured environments. The ability of autonomous systems to overcome these conditions during outdoor construction site preparation tasks relies on their capacity to map the material on-site and continuously perform localization. This study suggests a solution to these problems by collaborating between an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV). In this method, the UAV produces a material map and monitors the UGV's location relative to known static landmarks. These measurements are then sent to the ground vehicle and are added to the onboard sensors using the Extended Kalman Filter (EKF) approach. Thus, the UAV enhances the operation of the UGV by providing an accurate localization and mapping from the air and allowing it to perform a site-preparation task beyond mere sensing. This approach is examined with simulation and validated by outdoor experiments. Additionally, this method is integrated within Shepherd, a custom-developed plugin for computer-aided design applications.

Aggregate-Forming Planner for Autonomous Earth-Moving

“…8-9). The planner is aimed at assisting the production of motion instructions for a ROS-controlled vehicle by complementing two previous publications on controlling the UGV and lo-calizing it using an unmanned aerial vehicle (UAV) [6], [7]. As the planner generates a path for the aggregate-forming task, future work will focus on integrating this capability for large-scale experiments involving outdoor construction site preparation tasks.…”

“…This research is pursued in the context of autonomous earthworks [1], environmental purposes [2], military applications [3], landscape architecture [4], and construction [5]. Existing research includes the development of dedicated tools for automating earthworks [6], methods, and protocols supporting such processes [7]- [9].…”

Assessing the Digital Transformation Readiness of the Construction Industry Utilizing the Delphi Method

“…The availability of robotics on site preparation (e.g., material mapping and localization) [121,122] P03.06 Utilization of GIS for site selection (e.g., land development, selecting soil investigation for proper location) [7,123] P04 Design P04.01 Using BIM modeling for the spacing layout [4] P04.02 Implementation of 5D for detailed engineering optimization [124] P04.03 Using big data and analytics for design optimization [125,126] P04.04 Using drones for site localization [127] P04.05 Utilizing digital twins on project design [19,103,128] P04.06 Implementation of AI to capture and assess during preconstruction (e.g., decision-making, price, experience past project performance for contractor) [5,82] P04.07 Integration of virtual reality with design (e.g., enhance efficiency for planning and project design) [8] P04.08 Utilization of laser scanning during design stage (e.g., as-built drawing, clash checks for MEP, electrical work, and improve quality control) [129][130][131] Table A2. Construction management successful factors.…”

Vision-Based Automated Recognition and 3D Localization Framework for Tower Cranes Using Far-Field Cameras

“…CNN-based object detection algorithms have achieved excellent detection results. CVB technologies are widely used on construction sites for the 3D localization of mobile resources such as workers [ 15 ], trucks [ 16 , 17 ], and components [ 18 ]. However, for monocular cameras, image detection technology can only provide the coordinates of objects in the two-dimensional (2D) pixel plane, resulting in a loss of the depth relationship in 3D space.…”