Enhancing collaborative human-robot interaction through physiological-signal based communication

In order to develop a friendly and safe interaction between humans and robots, it is essential for the robot to evaluate users’ affective states and respond accordingly. This paper investigates the use of physiological signals to estimate human affective states during a Human-Robot Interaction (HRI) task. We focus on characterizing physiological responses and understanding how affective states evolve in a collaborative human-robot task. We propose to both design a model that maps physiological signals to affective states in real time and design a methodology for the robot to exhibit an appropriate behavior during the task in response to estimated changes in affective states.

[1]  A. Mehrabian,et al.  Inference of attitudes from nonverbal communication in two channels. , 1967, Journal of consulting psychology.

[2]  Changchun Liu,et al.  Physiology-based affect recognition for computer-assisted intervention of children with Autism Spectrum Disorder , 2008, Int. J. Hum. Comput. Stud..

[3]  Nilanjan Sarkar,et al.  Anxiety-based affective communication for implicit human–machine interaction , 2022 .

[4]  Jennifer Healey,et al.  Toward Machine Emotional Intelligence: Analysis of Affective Physiological State , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Antonio Bicchi,et al.  Measuring intent in human-robot cooperative manipulation , 2009, 2009 IEEE International Workshop on Haptic Audio visual Environments and Games.

[6]  Dana Kulic,et al.  Estimating Robot Induced Affective State using Hidden Markov Models , 2006, ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication.

[7]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

[8]  Nils J. Nilsson,et al.  Artificial Intelligence , 1974, IFIP Congress.

[9]  Nilanjan Sarkar,et al.  Anxiety detecting robotic system – towards implicit human-robot collaboration , 2004, Robotica.