In the era of an expected increase in the presence of autonomous systems, in industrial settings, the need to develop intelligent interfaces for human workers is gaining attention. Worker mistrust and stress result because autonomous systems don’t provide any facial, auditory, or visual cues which workers normally use to predict behaviour. The seamless integration of humans with autonomous systems is not possible without intelligent industrial robots which can act in unforeseen situations, based on the information about collaborative humans and the environment. It is important to quantify human workers’ frustration, intention, and cognitive stress, not only for performance improvement but also to fulfil the integration requirements of autonomous systems on factory floors. This study aims to offer a seamless, real-time monitoring solution for cognitive stress and fatigue of human workers in production and logistics scenarios. An experiment mimicking the actual factory scenario has been designed to assess and quantify the cognitive stress of participants using physiological, behavioural, and subjective measures. The data is trained using machine learning to develop stress categorisation in the form of a stress scale that has the potential to become a solution in contemporary industrial and logistics sectors. Two Android applications have been developed. The first application focuses on the stress management and monitoring of factory workers using physiological and subjective data to provide a quantified form of stress for the users and managers. The second application targets drivers in logistics setups and aims to detect the emotions of drivers in real-time. This is a useful application for drivers that can provide precautionary alerts to prevent accidents due to the fatigued state of the driver. Holistically, this research has the potential to optimise the interface between humans and interacting autonomous systems and develop innovative solutions to improve workplace health and safety hence enhancing productivity across various occupational settings.