A YOLOv7-Based Method for Detecting Buttons in Service Robots during Autonomous Elevator-Taking Tasks

This paper presents a novel visual algorithm based on YOLOv7, designed to enhance the robustness of automated elevator-taking service robots in detecting elevator buttons. Traditional solutions for elevator interaction, such as image processing methods, feature selection, or wireless communication protocols, have inherent limitations related to communication security issues and additional equipment costs. In order to overcome these challenges, our method leverages a physical robotic arm and the YOLOv7 object detection neural network to improve the accuracy of elevator button detection and enable effective robot-elevator interaction. To identify elevator buttons, we employ single-stage object detection algorithms along with multiple cameras to capture comprehensive environmental information during experimental trials. By utilizing these techniques, our proposed method ensures the safety and reliability of the automated elevator-taking process for service robots. Experimental results demonstrate the effectiveness of our algorithm in accurately detecting elevator buttons across various testing scenarios. Overall, our method offers a more suitable solution for service robots to autonomously navigate elevators and perform their intended tasks.