Walking on Roofs: Exploring the Potential of Walking Robots for Construction Work on Roofs

2026-10-08

AI Summary

This study addresses the high risks of rooftop operations and the lack of slope-adaptive designs in existing quadruped robots by systematically evaluating the locomotion performance of a Unitree Go2 in simulated roof environments for the first time. Through a custom-built test rig, contact mechanics analysis, and reinforcement learning-based adaptive gait control strategies, we quantify the impact of incline gradients on stability. The results reveal significant slippage defects and failure risks associated with standard footpads on slopes, demonstrating that conventional configurations are unsuitable for steep terrain. By establishing a benchmark for quadrupedal locomotion capabilities on rooftops, this work provides critical insights to guide the future development of specialized foot mechanisms and intelligent control strategies for inclined surface navigation.

Abstract

This paper investigates the feasibility of deploying quadruped walking robots for the automation of work in roof environments. While quadrupeds have demonstrated versatility across various domains, their large-scale deployment remains limited, partly due to lack of application-specific designs. Roof environments represent a novel and unexplored use case, combining high safety risks for human workers with repetitive, strenuous tasks that could benefit from robotic assistance. A dedicated test rig of a roof's surface was designed to evaluate the baseline performance of a commercial quadruped, the \emph{Unitree Go2}, in this new environment. Experiments revealed that standard ball feet are inherently inadequate for locomotion on sloped roofs: slippage increased quadratically with incline angle, get-up and lie-down sequences were only possible on small inclines, and critical failures already occurred regularly on moderate inclines of 25°. This work provides the first systematic assessment of quadruped locomotion in roof environments, highlighting both the potential and the current limitations of this application and establishes a baseline for future research. Effective solutions will require a combination of task-oriented foot designs, advanced contact mechanics and environment-specific control strategies, such as reinforcement learning for roof-adapted gaits.

Problem

• quadruped robots
• roof construction
• locomotion
• sloped surfaces
• construction automation

Innovation

• Quadruped robot
• Roof locomotion
• Sloped terrain
• Reinforcement learning
• Contact mechanics