Neuroergonomics of Human-AI and Human-Machine-Robot Teaming

As autonomous systems and AI become more capable, human operators are increasingly working alongside AI agents, collaborative robots, robotic swarms, powered exoskeletons, and intelligent decision-support systems across manufacturing, logistics, search and rescue, rehabilitation, healthcare, education, scientific discovery, and defense. Effective teaming in these settings demands more than task allocation. It requires real-time mutual understanding of intent, cognitive state, and situational awareness. The rapid growth of large language models has sharpened this challenge: AI agents are now active collaborators that interpret goals, generate plans, support learning and decision-making, and adapt in real time, raising distinct neuroergonomic questions around trust, coordination, mental model formation, explainability, and appropriate reliance.Neural markers offer a direct window into these processes. Signals such as EEG, fNIRS, and EMG capture moment-to-moment fluctuations in attentional state, motor intent, workload, and coordination readiness. Integrated into shared autonomy frameworks, they enable robotic and AI partners to adapt their behavior based on the operator’s cognitive and physical state, rather than relying solely on explicit commands or post-hoc metrics. Extended reality (XR) technologies complement this by providing immersive platforms for training, teleoperation, and situated feedback, allowing operators to build accurate mental models of AI and robot behavior before and during deployment.Scaling these interactions introduces new complexity. Operators managing swarms or multi-robot systems face fundamentally different cognitive demands than those in one-to-one dyads. Across all contexts, the core challenge is designing human-in-the-loop systems that remain responsive, interpretable, and safe as the number of agents and pace of operations grow.This Research Topic welcomes contributions that advance understanding of the neural, physiological, behavioral, and cognitive mechanisms underlying human-AI and human-machine-robot teaming, including human-robot collaboration, shared autonomy, and adaptive human-machine partnerships, and their application to adaptive, scalable collaborative systems in both physical and cognitive work environments.We accept all article types published by Frontiers in Neuroergonomics, on the following subthemes and more:- Neural and physiological markers of teaming: decoding intent, coordination readiness, and cognitive state from EEG, fNIRS, EMG, and multimodal signals during human-robot and human-AI interaction.Human-AI teaming and large language models: cognitive and neural correlates of collaborating with AI agents, trust calibration, mental model formation, explainability, and the neuroergonomics of LLM-assisted decision-making.- Human-robot teaming and collaborative interaction: neural, physiological, behavioral, and cognitive mechanisms underlying collaboration between humans and robotic teammates, including intent communication, shared situational awareness, coordination, trust, role allocation, physical collaboration, and adaptive human-robot partnerships.- Shared autonomy and adaptive behavior: frameworks for translating real-time neural or physiological input into dynamic adjustment of robot or AI autonomy, task allocation, and assistance levels.- XR for training and teleoperation: use of virtual, augmented, and mixed reality environments for immersive human-robot/AI training, operator skill development, and teleoperation support.- Multi-agent and swarm teaming: cognitive demands, workload management, and supervisory control strategies for operators managing multiple robots or autonomous agents simultaneously.- Exoskeleton integration and motor intent decoding: neural interfaces for synchronized human-exoskeleton control in rehabilitation, labor, and operational environments.- Human-AI teaming for learning, decision support, and knowledge work: neural, physiological, and behavioral mechanisms underlying collaboration with AI tutors, decision-support systems, generative AI assistants, and intelligent agents in education, healthcare, engineering, scientific discovery, and other cognitive work domains.- System design, trust, and human factors at scale: operator trust, situational awareness, transparency of AI and robot intent, explainability, and safety considerations in large-scale human-in-the-loop teams. Topic editors: Ehsan T Esfahani, Hemanth Manjunatha Source: https://www.frontiersin.org/research-topics/84804/neuroergonomics-of-human-ai-and-human-machine-robot-teaming