Published papers Archives - ETF Robotics

🤖 𝗘𝗧𝗙 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗮𝘁 𝗜𝗖𝗥𝗔 𝟮𝟬𝟮𝟱

ETF Robotics — Mon, 19 May 2025 13:18:56 +0000

We’re proud to share that Nikola Knežević, a member of the ETF Robotics team, will be presenting our latest research at the IEEE International Conference on Robotics and Automation (ICRA) 📍 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗟𝗼𝗰𝗮𝘁𝗶𝗼𝗻: Atlanta, USA 📅 𝗣𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗗𝗮𝘁𝗲: Tomorrow – May 20th, 2025 🕚 𝗧𝗶𝗺𝗲: 11:15 – 11:20 📌 𝗥𝗲𝗴𝘂𝗹𝗮𝗿 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝟰𝟬𝟭 – 𝗥𝗲𝗵𝗮𝗯𝗶𝗹𝗶𝘁𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗘𝗿𝗴𝗼𝗻𝗼𝗺𝗶𝗰𝘀 Nikola will present our concept of a 𝗻𝗲𝘂𝗿𝗼𝗲𝗿𝗴𝗼𝗻𝗼𝗺𝗶𝗰 𝘄𝗼𝗿𝗸𝗰𝗲𝗹𝗹, recently published in 𝗜𝗘𝗘𝗘 𝗥𝗔𝗠 jurnal, which proposes a human-centered approach to improving 𝘄𝗼𝗿𝗸𝗲𝗿 𝘄𝗲𝗹𝗹-𝗯𝗲𝗶𝗻𝗴 𝗮𝗻𝗱 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝘃𝗶𝘁𝘆 in industrial environments. This system combines 𝗽𝘀𝘆𝗰𝗵𝗼𝗹𝗼𝗴𝗶𝗰𝗮𝗹 𝗮𝗻𝗱 𝗽𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗮𝘀𝘀𝗲𝘀𝘀𝗺𝗲𝗻𝘁𝘀 with real-time task support, and has been validated in a real factory setting during industrial assembly tasks. If you’re at ICRA2025, join Nikola’s session and learn how technologies can be designed to better support the people who use them. Whether you’re in research, industry, or policy, we’re always open to collaborations that bridge human needs and robotic capabilities. 🎥 Dive deeper into the project: 𝗣𝗮𝗽𝗲𝗿 and 𝗩𝗶𝗱𝗲𝗼 The work is part of the BrainWatch experiment under the SHOP4CF Horizon 2020 project, and continues to evolve within the BrAIn | Interreg Danube Region Programme, where we explore how neuroergonomics can drive 𝗮𝗱𝗮𝗽𝘁𝗶𝘃𝗲, 𝗶𝗻𝗰𝗹𝘂𝘀𝗶𝘃𝗲, 𝗮𝗻𝗱 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗜𝗻𝗱𝘂𝘀𝘁𝗿𝘆 𝟱.𝟬 systems across […]

The post 🤖 𝗘𝗧𝗙 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗮𝘁 𝗜𝗖𝗥𝗔 𝟮𝟬𝟮𝟱 appeared first on ETF Robotics.

📒 𝗡𝗲𝘄 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗽𝗮𝗽𝗲𝗿 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝗖𝗶𝗿𝗰𝘂𝗯𝗼𝘁 𝗣𝗿𝗼𝗷𝗲𝗰𝘁: Advancing robotic waste sorting with AI ♻️

ETF Robotics — Wed, 02 Apr 2025 11:44:58 +0000

The rise of LEAN and small-batch manufacturing calls for 𝗳𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝘄𝗼𝗿𝗸𝘀𝘁𝗮𝘁𝗶𝗼𝗻𝘀 that can seamlessly switch between different waste types over time. Our latest study explored deep learning models from the Segment Anything Model (SAM) family for extracting waste objects from raw images, followed by a classification stage to ensure accurate waste sorting. This two-step procedure eliminates the need for dedicated waste detection and segmentation algorithms, enhancing robotic waste sorting by efficiently segmenting and classifying highly variable objects. Tested on 𝗳𝗼𝘂𝗿 𝘂𝘀𝗲 𝗰𝗮𝘀𝗲𝘀 (floating waste, municipal waste, e-waste and smart bins), 𝗼𝘂𝗿 𝗺𝗲𝘁𝗵𝗼𝗱 𝗮𝗰𝗵𝗶𝗲𝘃𝗲𝗱 𝟴𝟲-𝟵𝟳% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆, demonstrating its robustness and industrial applicability. By simplifying deployment, improving efficiency, and reducing costs, this approach has the potential to enhence robotic waste sorting and boost recycling and material utilization in manufacturing. You can explore the full study here 𝗔𝘂𝘁𝗵𝗼𝗿𝘀: Arso Vukicevic, Milos Petrovic, Nebojša Jurišević, Djapan Marko PhD, Nikola Knežević, Dr Aleksandar Novakovic & Kosta Jovanovic 𝗦𝘁𝗮𝘆 𝘁𝘂𝗻𝗲𝗱 𝗳𝗼𝗿 𝗺𝗼𝗿𝗲 𝘂𝗽𝗱𝗮𝘁𝗲𝘀 𝗳𝗿𝗼𝗺 𝗖𝗶𝗿𝗰𝘂𝗯𝗼𝘁 𝗮𝘀 𝘄𝗲 𝗮𝗽𝗽𝗿𝗼𝗮𝗰𝗵 𝘁𝗵𝗲 𝗳𝗶𝗻𝗮𝗹 𝗽𝗵𝗮𝘀𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗽𝗿𝗼𝗷𝗲𝗰𝘁! While the project is nearing its conclusion, this milestone brings exciting new insights, results, and key takeaways that we’ll be sharing in the coming period. This research was supported by the […]

The post 📒 𝗡𝗲𝘄 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗽𝗮𝗽𝗲𝗿 𝗳𝗿𝗼𝗺 𝘁𝗵𝗲 𝗖𝗶𝗿𝗰𝘂𝗯𝗼𝘁 𝗣𝗿𝗼𝗷𝗲𝗰𝘁: Advancing robotic waste sorting with AI ♻️ appeared first on ETF Robotics.

📢 📓Publication Announcement: Neuroergonomic Workcell

ETF Robotics — Fri, 27 Dec 2024 11:47:00 +0000

We are pleased to share that our a novel concept of a neuroergonomic workcell aimed at enhancing worker well-being and productivity as a pivotal point for new Industry5.0 has been published in the prestigious IEEE RAM journal. The study outlines the essential components of such workcells, including psychological and physical assessment, as well as non-physical, physical, and strategic support mechanisms. To validate this concept, a proof-of-concept neuroergonomic human-centered workstation was demonstrated in a real factory setting, focusing on the task of industrial assembly. You can explore the full study hereAnd supplementary video material that demonstrate the concept here This research received funding from the European Union’s Horizon 2020 research and innovation program under Grant 873087 SHOP4CF (Smart Human Oriented Platform for Connected Factories), within the BrainWatch experiment. The presented concept provides valuable insights into improving workplace ergonomics and efficiency, marking a step forward in applying neuroergonomics in industrial environments across Danube region within our ongoing actions in BrAIn | Interreg Danube Region Programme project. We are looking forward to seeing the next steps and further advancement on human-centric industry by the paper authors: Nikola Knežević, Andrej Savic, Zavisa Gordic, Arash Ajoudani, and Kosta Jovanovic!

The post 📢 📓Publication Announcement: Neuroergonomic Workcell appeared first on ETF Robotics.

New research paper in the Artificial Intelligence Review journal

ETF Robotics — Thu, 14 Nov 2024 10:26:48 +0000

We are thrilled to announce the publication of a new research paper in the esteemed Artificial Intelligence Review journal, showcasing the latest achievements from the Circubot project, which we have been developing over the past year. Led by Arso Vukicevic, the project’s principal investigator, this study explores advanced analysis with a focus on computer vision-based Personal Protective Equipment (PPE) compliance. As a critical emerging topic, PPE compliance aims to improve workplace safety through the automation of compliance and prevention of PPE misuse, which traditionally depends on manual oversight. A significant part of this research was driven by Milos Petrovic, our doctoral researcher, who contributed substantially to material analysis and preparation as part of his Ph.D. focus. This publication highlights the commitment and innovation of our collaborative team as we push the research boundaries. You can explore the full study here Special thanks to co-authors Pavle Milosevic, Aleksandar Peulic, Kosta Jovanovic, and Dr Aleksandar Novakovic for their valuable contributions.

The post New research paper in the Artificial Intelligence Review journal appeared first on ETF Robotics.