Perception-and-action system for humanoid robot task execution in construction
2026-08-03 • Robotics
Robotics
AI summaryⓘ
The authors developed a system that helps humanoid robots learn how to do construction tasks by watching humans. Their system uses two deep learning networks: one to understand human poses and convert them into robot-friendly movements, and another to translate those into actions the robot can perform. They tested this with a humanoid robot completing eight construction-related tasks, with good accuracy in matching human movement. This work shows a first step toward robots working safely alongside humans on construction sites.
humanoid robotsdeep learningpose estimationrobot motion planningconstruction automationhuman-robot collaborationMean Per Joint Position Errorrobot perceptionrobot action learning
Authors
Yanxi Liu, Yizhi Liu
Abstract
Humanoid robots, with their human-like shape and multi-tasking capabilities, are well-aligned with human-dominated workplaces, like those in civil and construction engineering, where they could collaborate with human workers or autonomously perform physically demanding and hazardous tasks. Despite this promise, limited research has explored how to endow these robots with the practical capabilities needed to perform construction tasks. To this end, this study proposes a novel perception-and-action system that enables humanoid robots to learn and perform construction tasks from worker demonstrations. This system contains two deep networks: Humanoid-PoseNet, which extracts human postures and translates them into mechanically feasible poses for a humanoid robot; and Humanoid-ActionNet, which learns robot-executable actions based on these translated poses. Experimental results demonstrate that the humanoid robot reliably executed eight construction-related actions, achieving an average motion-tracking error of 82.45 mm MPJPE (Mean Per Joint Position Error). This work provides an early step toward deploying humanoid collaborators in construction.