DiG-Net: Enhancing Quality of Life through Hyper-Range Dynamic Gesture Recognition in Assistive Robotics

Dynamic hand gestures play a pivotal role in assistive human-robot interaction (HRI), facilitating intuitive, non-verbal communication, particularly for individuals with mobility constraints or those operating robots remotely. Current gesture recognition methods are mostly limited to short-range interactions, reducing their utility in scenarios demanding robust assistive communication from afar. In this paper, we introduce a novel approach designed specifically for assistive robotics, enabling dynamic gesture recognition at extended distances of up to 30 meters, thereby significantly improving accessibility and quality of life. Our proposed Distance-aware Gesture Network (DiG-Net) effectively combines Depth-Conditioned Deformable Alignment (DADA) blocks with Spatio-Temporal Graph modules, enabling robust processing and classification of gesture sequences captured under challenging conditions, including significant physical attenuation, reduced resolution, and dynamic gesture variations commonly experienced in real-world assistive environments. We further introduce the Radiometric Spatio-Temporal Depth Attenuation Loss (RSTDAL), shown to enhance learning and strengthen model robustness across varying distances. Our model demonstrates significant performance improvement over state-of-the-art gesture recognition frameworks, achieving a recognition accuracy of 97.3% on a diverse dataset with challenging hyper-range gestures. Introduction The growing number of individuals living with disabilities and requiring assistance has created a pressing demand for assistive technologies that enhance users' independence, safety, and quality of life [1]. Among these, assistive robotic systems are increasingly integrated into environments where intuitive, nonverbal communication is essential for enabling natural interaction with individuals of varied abilities. Gesture-based interaction is particularly important in scenarios where speech is not an option. To contextualize our contribution, Table 1 presents a comparative overview of recent systems in this area, outlining their target users, sensing modalities, application domains, and level of human involvement. Our method is the only one to support dynamic gesture recognition at hyper-range distances, defined here as up to 30 meters, and to operate reliably in both indoor and outdoor environments, making it uniquely suited for real-world assistive deployment. Recent research has catalyzed a new generation of assistive systems capable of perceiving complex environments and interacting with humans in context-aware, natural ways [2, 3, 4].