{"ID":2894742,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10055","arxiv_id":"2507.10055","title":"Hand Gesture Recognition for Collaborative Robots Using Lightweight Deep Learning in Real-Time Robotic Systems","abstract":"Direct and natural interaction is essential for intuitive human-robot collaboration, eliminating the need for additional devices such as joysticks, tablets, or wearable sensors. In this paper, we present a lightweight deep learning-based hand gesture recognition system that enables humans to control collaborative robots naturally and efficiently. This model recognizes eight distinct hand gestures with only 1,103 parameters and a compact size of 22 KB, achieving an accuracy of 93.5%. To further optimize the model for real-world deployment on edge devices, we applied quantization and pruning using TensorFlow Lite, reducing the final model size to just 7 KB. The system was successfully implemented and tested on a Universal Robot UR5 collaborative robot within a real-time robotic framework based on ROS2. The results demonstrate that even extremely lightweight models can deliver accurate and responsive hand gesture-based control for collaborative robots, opening new possibilities for natural human-robot interaction in constrained environments.","short_abstract":"Direct and natural interaction is essential for intuitive human-robot collaboration, eliminating the need for additional devices such as joysticks, tablets, or wearable sensors. In this paper, we present a lightweight deep learning-based hand gesture recognition system that enables humans to control collaborative robot...","url_abs":"https://arxiv.org/abs/2507.10055","url_pdf":"https://arxiv.org/pdf/2507.10055v2","authors":"[\"Muhtadin\",\"I Wayan Agus Darmawan\",\"Muhammad Hilmi Rusydiansyah\",\"I Ketut Eddy Purnama\",\"Chastine Fatichah\",\"Mauridhi Hery Purnomo\"]","published":"2025-07-14T08:40:24Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}