Scholarlink

<p>Coastal pollution, with an estimated 8 million metric tons of plastic entering the oceans annually, threatens global marine ecosystems, biodiversity, and coastal economies. This paper introduces EcoBot, an autonomous beach cleaning robot designed to address this crisis by efficiently collecting and sorting waste, promoting sustainable coastal management worldwide. EcoBot integrates YOLOv11, a state-of-the-art computer vision model, to detect plastic, glass, and metal in real time across diverse beach environments. Powered by Raspberry Pi 5, it processes data from HC-SR04 ultrasonic and infrared sensors for reliable navigation and a 5-DOF robotic arm for precise waste collection. A Kotlin-based mobile app enables remote control via Wi-Fi, providing user-friendly operation for global deployment. Tests conducted on a 10 × 10-m beach area showed that EcoBot collected 50 pieces of waste in 12&#xa0;min, sorting it for recycling with high efficiency. Compared to manual cleaning or existing robots such as BeachBot and BeBot, EcoBot reduces operating and labor costs, making it a scalable solution for coastal areas worldwide. By facilitating waste sorting for recycling, EcoBot reduces landfill use, supports the circular economy, and preserves marine habitats, thereby promoting tourism and environmental health. Development challenges, including limited training data for YOLOv11, were addressed by augmenting datasets with additional images through data augmentation, while hardware integration issues were resolved through custom motor mounts and firmware updates for Raspberry Pi 5 and GA25-370 motors. Power stability and connectivity for sensors and the Kotlin application were improved through optimized battery management and error handling protocols. Future improvements include deploying EcoBot along international coastlines, integrating solar panels for energy efficiency, and upgrading the mobile app with real-time waste analytics and multilingual support to enhance accessibility. These developments position as a global leader in robotic beach cleaning, offering a cost-effective and environmentally friendly solution to combat coastal pollution. This work underscores the transformative potential of robotics and artificial intelligence in addressing global environmental challenges, paving the way for innovative and sustainable waste management systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EcoBot: an autonomous beach-cleaning robot for environmental sustainability applications

  • 期刊论文

  • 发表日期：

    2026年4月10日

查看全文
  • Fatma M. Talaat,
  • Ahmed Morshedy,
  • Marwan Khaled,
  • Mohamed Salem

摘要

Coastal pollution, with an estimated 8 million metric tons of plastic entering the oceans annually, threatens global marine ecosystems, biodiversity, and coastal economies. This paper introduces EcoBot, an autonomous beach cleaning robot designed to address this crisis by efficiently collecting and sorting waste, promoting sustainable coastal management worldwide. EcoBot integrates YOLOv11, a state-of-the-art computer vision model, to detect plastic, glass, and metal in real time across diverse beach environments. Powered by Raspberry Pi 5, it processes data from HC-SR04 ultrasonic and infrared sensors for reliable navigation and a 5-DOF robotic arm for precise waste collection. A Kotlin-based mobile app enables remote control via Wi-Fi, providing user-friendly operation for global deployment. Tests conducted on a 10 × 10-m beach area showed that EcoBot collected 50 pieces of waste in 12 min, sorting it for recycling with high efficiency. Compared to manual cleaning or existing robots such as BeachBot and BeBot, EcoBot reduces operating and labor costs, making it a scalable solution for coastal areas worldwide. By facilitating waste sorting for recycling, EcoBot reduces landfill use, supports the circular economy, and preserves marine habitats, thereby promoting tourism and environmental health. Development challenges, including limited training data for YOLOv11, were addressed by augmenting datasets with additional images through data augmentation, while hardware integration issues were resolved through custom motor mounts and firmware updates for Raspberry Pi 5 and GA25-370 motors. Power stability and connectivity for sensors and the Kotlin application were improved through optimized battery management and error handling protocols. Future improvements include deploying EcoBot along international coastlines, integrating solar panels for energy efficiency, and upgrading the mobile app with real-time waste analytics and multilingual support to enhance accessibility. These developments position as a global leader in robotic beach cleaning, offering a cost-effective and environmentally friendly solution to combat coastal pollution. This work underscores the transformative potential of robotics and artificial intelligence in addressing global environmental challenges, paving the way for innovative and sustainable waste management systems.