Toward Preventing Accidents in Process Industries by Inferring the Cognitive State of Control Room Operators through Eye Tracking

While modern chemical plants have numerous layers of protection to ensure safety, the human operator is often the final arbiter, especially during abnormal situations. It is therefore not surprising that when operators lose control over the plant, undesirable consequences including property damage, injury, and sometimes loss of lives follow. It is therefore important to continuously monitor the plant operators' situation awareness based on their cognitive state. In this study, we make the first known attempt to infer the cognitive state of control room operators and its evolution over the course of carrying out tasks in a control room. First, we study the operator's actions to distinguish consistent actions from inconsistent ones that allows us to identify major events in the evolution of their cognitive state. Next, we conduct experimental studies with human participants and explore the evolution of their cognitive state through patterns in their eye tracking data. Our studies reveal that two eye tracking measures, fixation duration and saccade duration, are sensitive to the cognitive state and can be used to monitor control room operators and thus prevent human error.