Edge-Deployed Generative AI for Context-Aware Decision Support in Wearable Robotic Systems

Recent advances in Generative Artificial Intelligence (GenAI), particularly large language models (LLMs), have transformed how machines interpret, reason, and communicate. At the same time, robotics research has made significant progress in edge computing, sensor fusion, and real-time perception systems, enabling deployment in dynamic and resource-constrained environments. Despite these developments, a critical gap remains in the integration of generative AI with embodied robotic systems operating at the edge, especially in wearable robotics such as smart helmets, assistive devices, and human-augmentation systems. Current research topics emphasise either cloud-based intelligence or isolated edge AI solutions, but lack a unified framework for real-time, context-aware decision support that combines perception, reasoning, and action under strict computational constraints.Wearable robotic systems represent a particularly compelling domain due to their direct interaction with human users in safety-critical scenarios such as construction, mining, emergency response, and industrial maintenance. These environments demand low-latency, interpretable, and adaptive AI systems capable of understanding context and assisting decision-making without reliance on continuous cloud connectivity. This Research Topic aims to bridge this gap by exploring how edge-deployed generative AI models can be integrated with robotic perception systems (e.g., VSLAM, multimodal sensing) to enable context-aware, human-centric decision support in wearable robotics.This Research Topic aims to advance the integration of generative artificial intelligence with edge-based robotic systems, with a particular focus on wearable and human-centered robotics operating in real-world environments. The objective is to develop and showcase novel frameworks, algorithms, and system architectures that enable real-time, context-aware decision support by combining robotic perception, multimodal sensing, and generative reasoning under computational and energy constraints.Specifically, this topic seeks to:I. Enable efficient deployment of generative AI models on edge and embedded platforms II. Foster integration between perception systems (e.g., visual SLAM, sensor fusion) and AI-driven reasoning III. Advance human-centric wearable robotics capable of assisting users in dynamic and safety-critical environments IV. Address challenges related to latency, robustness, interpretability, and energy efficiency V. Promote practical, real-world applications, particularly in constrained and infrastructure-limited settings By bridging the gap between embodied intelligence and generative AI, this Research Topic aims to establish scalable solutions for adaptive, autonomous, and assistive robotic systems deployed outside controlled laboratory conditions. This Research Topic focuses on the deployment of generative AI for wearable and edge-based robotic systems within computationally constrained, context-rich environments. The scope includes experimental, theoretical, and application-oriented studies addressing the challenges of perception, reasoning, and interaction in human–AI collaboration.To gather further insights in this area, we welcome contributions addressing, but not limited to, the following themes:- Edge deployment of generative AI and optimization of LLMs for embedded platforms- Multimodal perception, VSLAM, and sensor fusion for contextual awareness- Generative reasoning and language-guided behavior in embodied systems- Wearable and human-centered robotics for assistive and augmented cognition applications- Real-time decision support systems for hazard detection, risk assessment, and adaptive navigation- Energy-efficient algorithms and performance–latency trade-offs for wearable devices- Deployment in infrastructure-limited, industrial, or field environments- Explainability, safety, and ethical frameworks for trustworthy edge AI Topic editors: Samuel Moveh, MAZIAH Mohamad, Emmanuel Alejandro Merchán-Cruz Source: https://www.frontiersin.org/research-topics/82444/edge-deployed-generative-ai-for-context-aware-decision-support-in-wearable-robotic-systems