measuring-trust-in-robots-with-likert-scales | episodes

listen on castbox.fmlisten on google podcastslisten on player.fmlisten on pocketcastslisten on podcast addictlisten on tuninlisten on Amazon Musiclisten on Stitcher


Measuring User’s Perception

Today, Mariah Schrum and Matthew Gombolay join us. Maria is a Ph.D. student in the CORE Robotics Lab at Georgia Institute of Technology. Matthew is an Assistant Professor in the School of Interactive Computing at Georgia Institute of Technology. He is also the Director of the CORE Robotics Lab. They discuss best practices for measuring a respondent’s perception in a survey.

Matthew began by giving some insight into the kind of work done at his laboratory. Putting it simply, they build robots with a core focus on their interaction with humans. Matthew explained how robots differ from LLMs such as ChatGPT. He also discussed how robots’ performance can be measured. It was more complicated than conventional machine learning models. Mariah spoke about the Likert scale, a metric to measure respondents’ attitudes.

Mariah extensively discussed how researchers and HR practitioners can use the scale to measure one’s perception of a robot. She also discussed the recent problems of employing different scales that are not thoroughly validated.

Matthew discussed the process of validation, starting with measuring humans’ trust in robots. Mariah then outlined some best practices when developing good scales. She also shared some of the dangers of not following these best practices. She explained how researchers can convert complex distributional data from the survey to tangible insights using the Likert scale. They both discussed techniques to help check the quality of responses on a survey.

They also shared some common mistakes they found in research paper surveys. Rounding up, Matthew discussed the trends of robot adoption for the coming years and some new research they are working on. You can learn more about Matthew’s work by visiting CORE Robotics Lab’s official website. You can follow Mariah on Twitter @mariah17schrum.

Mariah Schrum

Mariah Schrum is a fifth-year Robotics PhD student in the CORE Robotics Lab at Georgia Tech and is also an NSF Accessibility, Rehabilitation, and Movement Science (ARMS) fellow. In her research, Mariah explores techniques for algorithmic human-robot interaction and data-driven personalization. Her research spans diverse domains, including learning from demonstration, autonomous vehicles, and healthcare. Prior to her PhD, Mariah graduated from the Johns Hopkins University with a BS in Biomedical Engineering and minors in Robotics and Mathematics in 2018. She additionally received a Master’s in Computer Science from Georgia Tech in 2020. Her publication record includes papers at the Conference on Robot Learning (CoRL), the International Conference on Robotics and Automation (ICRA), and a best technical paper award at the International Conference on Human-Robot Interaction (HRI).

Matthew Gombolay

Professor Matthew Gombolay is an Assistant Professor of Interactive Computing at the Georgia Institute of Technology and was named the Anne and Alan Taetle Early-career Assistant Professor in 2018. Dr. Gombolay is the director of the Cognitive Optimization and Relational (CORE) Robotics Lab, which seeks to place the power of robots in the hands of everyone by developing new computational methods and human factors insights that enable robots to learn from interaction with diverse, non-expert end-users to perform assistive tasks and coordinate in human-robot teams in applications from healthcare to manufacturing. Dr. Gombolay has authored has produced over 60 peer-reviewed papers, including best paper awards at the ACM/IEEE International Conference on Human-Robot Interaction, a best paper finalist at the 2020 Conference on Robot Learning (CoRL), and a best student paper finalist at the 2020 American Controls Conference (ACC). Dr. Gombolay is a NASA Early Career Fellow and a DARPA Riser, and he is an Associate Editor of Autonomous Robots and the ACM Transactions on Human-Robot Interaction.