Tracking trust in human-robot work interactions

We are in the era of globalization. Every human is dependent on machines in some or the other way. What is the probability that these machines are trustworthy? Has anyone thought about this? It is very important that the robots which we are dependent on complete our requirements in an effective and time-saving way. For the proper working of industries, the relationship between humans and robots must be trustworthy.

Keywords: human, robots, trust levels, human-autonomy trust, brain behavior, operator, near-infrared spectroscopy, distrust, reliability

A recent study by the Wm Michael Barnes '64 Department of Industrial and Systems Engineering at Texas A&M University aimed to resolve the issue of human trust levels in robots and machines. 

Dr. Ranjana Mehta, associate professor and director of the NeuroErgonomics Lab is this research's pioneer. His latest National Science Foundation (NSF) funded work on human-autonomy trust research stemmed from a series of projects on human-robot Interactions in safety-critical work domains and was recently published in Human Factors: The Journal of the Human Factors and Ergonomics Society. This research focuses on understanding the brain-behavior relationships regarding how an operator's trusting behaviors are influenced by both human and robot factors. Even Dr. Mehta has another publication in the journal Applied Ergonomics. That research investigates these human and robot factors.

He said, "While our focus so far was to understand how operator states of fatigue and stress impact how humans interact with robots, trust became an important construct to study. We found that as humans get tired, they let their guards down and become more trusting of automation than they should. However, why that is the case becomes an important question to address".

The main aim of this research was to track the trust of humans by monitoring their brain activities. Using the technique of near-infrared spectroscopy the researchers could capture functional brain activity through a collaboration of operators with robots on a manufacturing task. During the research, it was observed that faulty robot actions decreased the operator's trust in the robots. Along with distrust, researchers also observed that it was associated with increased activations of several regions in the brain which included frontal, motor, and visual cortices. This indicated increased workload and heightened situational awareness. The research also resulted that when the robots worked reliably, it led to the decoupling of these brain regions.  

Dr. Mehta said, " What we found most interesting was that the neural signatures differed when we compared brain activation data across reliability conditions (manipulated using normal and faulty robot behavior) versus operator's trust levels (collected via surveys) in the robot. This emphasized the importance of understanding and measuring brain-behavior relationships of trust in human-robot collaborations since perceptions of trust alone is not indicative of how operators' trusting behaviors shape up. This work is critical, and we are motivated to ensure that humans-in-the-loop robotics design, evaluation and integration into the workplace are supportive and empowering of human capabilities".

Dr. Sarah Hopko '19, lead author on both papers and a recent industrial engineering doctoral student said, " neural responses and perceptions of trust are both symptoms of trusting and distrusting behaviors and relay distinct information on how trust builds, breaches and repairs with different robot behaviors. She emphasized the strengths of multimodal trust metrics -- neural activity, eye tracking, behavioral analysis, etc. -- can reveal new perspectives that subjective responses alone cannot offer".

Thus this result gave an idea of how human behavior changes depending upon the work efficiency and reliability of the robots.