Localization of Mobile Robot Aided for Large-Scale Construction Based on Optimized Artificial Landmark Map in Ongoing Scene

Abstract

The effectiveness of mobile robot aided for architectural construction depends strongly on its accurate localization ability. Localization of mobile robot is increasingly important for the printing of buildings in the construction scene. Although many available studies on the localization have been conducted, only a few studies have addressed the more challenging problem of localization for mobile robot in large-scale ongoing and featureless scenes. To realize the accurate localization of mobile robot in designated stations, we build an artificial landmark map and propose a novel nonlinear optimization algorithm based on graphs to reduce the uncertainty of the whole map. Then, the performances of localization for mobile robot based on the original and optimized map are compared and evaluated. Finally, experimental results show that the average absolute localization errors that adopted the proposed algorithm is reduced by about 21% compared to that of the original map.

Continuous Mobile Thin-Layer On-Site Printing

“…2, "A"). The majority of mobile platforms are currently in use in a decoupled manner in discrete fabrication mode [13,14], where the base is fixed in position and stabilized for the 3D printing of a concrete building element [15], as demonstrated in the work of current construction robotics start-ups such as CyBe 2 or Apis Cor 3 (Fig. 2, "B").…”

Localization on a-priori information of plane extraction

“…The challenges associated with mobile robot localization are heightened in settings where distinctive features are either sparse or repetitive, such as indoor construction sites [ 7 , 8 ]. In these scenarios, feature-based localization methods face significant challenges due to the lack of unique and easily identifiable features.…”

Application of Automated Guided Vehicles in Smart Automated Warehouse Systems: A Survey

“…Although the classical AGVs route-planning algorithms (e.g., Dijkstra's algorithm [8], A * algorithm [9], D * algorithm [10]) can work well in small warehouses, they could be inefficient in environments with many nodes. Recently, Artificial Intelligence (AI) has become a helpful tool in autonomous decision-making areas [11]. Reinforcement Learning (RL), more specifically, the Qlearning algorithm has shown significant advantages and has been used in route planning [12][13][14], but the convergence time is extended when the number of nodes becomes large.…”