Floor-cleaning robots are primarily designed to clean on a single floor, while multi-floor environments are usually not considered target applications. However, it is more efficient to have an autonomous floor-cleaning robot that can climb stairs and reach the next floors in a multi-floor building. To operate in such environments, the ability of a mobile robot to autonomously traverse staircases is very important. For this operation, staircase detection and localization are essential components for planning the traversal route on staircases. This article describes a deep learning approach using a convolutional neural network (CNN)-based robot operation system (ROS) framework for staircase detection, localization, and maneuvering of the robot to the detected stair. We present a real-time object detection framework to detect staircases in incoming images. We also localize these staircases using a contour detection algorithm to detect the target point: a point close to the center of the first step, and an angle of approach to the target point with respect to the current location of the robot. Experiments are performed with data from images captured on different types of staircases at different viewpoints/angles. The experimental results show that the presented approach can achieve an accuracy of 95% and a recall of 86.81%. A total runtime of 155 ms is taken to identify the presence of a staircase and the detection of the first step in the working environment, as well as being able to locate the target point with an accuracy of ±2 cm, ±1 degree.

This work presents a low-cost, vision-based safety monitoring system for human–robot collaboration (HRC) in industrial environments. A power-bank assembly case study involving two robots and a human operator is used for validation. One robot performs pick-and-place operations, while the second robot executes screwing tasks, and a human assistant performs soldering. Human presence is detected using a YOLOv8 instance-segmentation model with a single overhead RGB camera. Based on the detected human position, the workspace is divided into three adaptive safety zones: red, yellow, and green. The red zone is derived from the robot’s reachable workspace in RoboDK and triggers a functional stop when a human enters the hazardous region. The yellow zone reduces robot speed by 50 %, while the green zone allows full operation. A RoboDK digital twin is used for real-time monitoring of robot motion, enabling additional collision awareness during operation. Experimental results using real robotic systems demonstrate that integrating lightweight vision-based detection with digital-twin monitoring provides an effective and scalable approach for improving safety awareness in collaborative robotic work cells.

Fault detection in Air Handling Units (AHUs) is critical for improving energy efficiency and maintaining indoor environmental quality in modern buildings. However, the practical deployment of data-driven fault detection remains challenging due to the scarcity of labeled fault data, the need for expert annotation, and the presence of noisy, incomplete, and low-resolution building management system (BMS) data. This study aims to evaluate the effectiveness of multiple unsupervised learning methods for fault detection in fully unlabeled industrial AHU data. To address these challenges, this study investigates robust unsupervised methods for fault detection using a real industrial AHU dataset that contains missing values, measurement noise, outliers, and low-resolution sampling. A comparative framework is developed to evaluate multiple unsupervised learning approaches, including Principal Component Analysis (PCA), autoencoders, K-Means clustering, and statistical control charts, without relying on labeled data. The results show that autoencoder-based models achieve the best overall performance by effectively capturing complex nonlinear relationships, while PCA and K-Means identify more pronounced patterns, and control charts provide simple but limited univariate insights. These findings highlight the importance of robust data preprocessing and demonstrate that unsupervised methods can provide practical and scalable solutions for fault detection in real-world Heating, Ventilation, and Air Conditioning (HVAC) systems under realistic data constraints.