Learning-Enabled and Human-Centric Robotics with Wearable and Sensor Systems

Wearable and ambient sensor systems are increasingly becoming the backbone of human-centric robotics and cyber-physical systems, providing rich multimodal data that capture human activities, physiological states, and environmental context. By integrating such sensing modalities into robotic and autonomous platforms, it becomes possible to design systems that are more adaptive, personalized, and capable of seamless human-robot interaction.

At the same time, advances in learning-enabled methods and generative AI, including diffusion models, transformers, and large language models, are opening new opportunities for system modeling, simulation, and adaptive control. These approaches promise to extend traditional model-based control to high-dimensional, uncertain, and dynamic domains but also introduce new challenges in terms of safety, interpretability, and efficiency.

This open invited track seeks contributions that bridge control theory, robotics, and AI to advance the next generation of safe, efficient, and human-aware autonomous systems. By fostering dialogue between researchers in control, robotics, and AI, this track will provide a unique forum to shape the future of sensor-driven, learning-enabled, and safe autonomy.