Dario Pasquali
Alexander Mois Aroyo
ABSTRACT
Detecting lies in a real-world scenario is an important skill for a humanoid robot that aims to act as a teacher, a therapist, or a caregiver. In these contexts, it is essential to detect lies while preserving the pleasantness of the social interaction and the informality of the relation. This study investigates whether pupil dilation related to an increase in cognitive load can be used to swiftly identify a lie in an entertaining scenario. The iCub humanoid robot plays the role of a magician in a card game, telling which card the human partner is lying about. The results show a greater pupil dilation in presence of a false statement even if in front of a robot and without the need of a strictly controlled scenario. We developed a heuristic method (accuracy of 71.4% against 16.6% chance level) and a random forest classifier (precision and recall of 83.3%) to detect the false statement. Additionally, the current work suggests a potential method to assess the lying strategy of the partner.
- A. Westbrook and T. S. Braver, "Cognitive effort: A neuroeconomic approach," Cognitive, Affective and Behavioral Neuroscience, vol. 15, no. 2. Springer New York LLC, pp. 395--415, 22-Jun-2015.Google Scholar
- J. Beatty, "Task-Evoked Pupillary Responses, Processing Load, and the Structure of Processing Resources," 1982.Google Scholar
- A. Koenig et al., "Real-time closed-loop control of cognitive load in neurological patients during robot-assisted gait training.," IEEE Trans. Neural Syst. Rehabil. Eng., vol. 19, no. 4, pp. 453--64, Aug. 2011.Google ScholarCross Ref
- J. A. Stern, L. C. Walrath, and R. Goldstein, "The endogenous eyeblink.," Psy-chophysiology, vol. 21, no. 1, pp. 22--33, Jan. 1984.Google ScholarCross Ref
- J. Fallon, "Box of Lies." [Online]. Available: https://www.youtube.com/watch?v=Md4QnipNYqM.Google Scholar
- C. R. Honts, D. C. Raskin, and J. C. Kircher, "Mental and physical countermeas-ures reduce the accuracy of polygraph tests.," J. Appl. Psychol., vol. 79, no. 2, pp. 252--9, Apr. 1994.Google ScholarCross Ref
- B. M. DePaulo, J. J. Lindsay, B. E. Malone, L. Muhlenbruck, K. Charlton, and H. Cooper, "Cues to deception.," Psychol. Bull., vol. 129, no. 1, pp. 74--118, 2003.Google ScholarCross Ref
- D. P. Dionisio, E. Granholm, W. A. Hillix, and W. F. Perrine, "Differentiation of deception using pupillary responses as an index of cognitive processing.," Psy-chophysiology, vol. 38, no. 2, pp. 205--11, Mar. 2001.Google ScholarCross Ref
- S. M. Kassin, "On the Psychology of Confessions: Does Innocence Put Innocents at Risk?," Am. Psychol., vol. 60, no. 3, pp. 215--228, Apr. 2005.Google ScholarCross Ref
- J. G. May, R. S. Kennedy, M. C. Williams, W. P. Dunlap, and J. R. Brannan, "Eye movement indices of mental workload," Acta Psychol. (Amst)., vol. 75, no. 1, pp. 75--89, 1990.Google ScholarCross Ref
- M. Nakayama and Y. Shimizu, "Frequency analysis of task evoked pupillary response and eye-movement," in Proceedings of the Eye tracking research & applications symposium on Eye tracking research & applications - ETRA'2004, 2004, pp. 71--76.Google Scholar
- K. F. Van Orden, W. Limbert, S. Makeig, and T. P. Jung, "Eye activity correlates of workload during a visuospatial memory task.," Hum. Factors, vol. 43, no. 1, pp. 111--21, 2001.Google ScholarCross Ref
- B. C. Goldwater, "Psychological significance of pupillary movements," Psychol. Bull., vol. 77, no. 5, pp. 340--355, May 1972.Google ScholarCross Ref
- A. Szulewski, N. Roth, and D. Howes, "The Use of Task-Evoked Pupillary Re-sponse as an Objective Measure of Cognitive Load in Novices and Trained Physi-cians: A New Tool for the Assessment of Expertise," Acad. Med., vol. 90, no. 7, pp. 981--987, Jul. 2015.Google ScholarCross Ref
- M. Ahmad, B. Jasmin, L. Katrin, and F. Eyssel, "Trust and Cognitive Load During Human-Robot Interaction," 2019.Google Scholar
- J. Klingner, "Measuring Cognitive Load During Visual Task by Combining Pupil-lometry and Eye Tracking," Ph.D. Diss., no. May, 2010.Google Scholar
- G. Hossain and M. Yeasin, "Understanding effects of cognitive load from pupil-lary responses using hilbert analytic phase," IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., pp. 381--386, 2014.Google Scholar
- A. Gaggioli, "Beyond the Truth Machine: Emerging Technologies for Lie Detec-tion," Cyberpsychology, Behav. Soc. Netw., vol. 21, no. 2, pp. 144--144, Feb. 2018.Google ScholarCross Ref
- M. Gamer, "Detecting of deception and concealed information using neuroimag-ing techniques," in Memory Detection, B. Verschuere, G. Ben-Shakhar, and E. Meijer, Eds. Cambridge: Cambridge University Press, 2011, pp. 90--113.Google Scholar
- J. Gonzalez-Billandon et al., "Can a Robot Catch You Lying? A Machine Learn-ing System to Detect Lies During Interactions," Front. Robot. AI, vol. 6, Jul. 2019.Google Scholar
- K. Kobayashi and S. Yamada, "Human-robot interaction design for low cognitive load in cooperative work," in RO-MAN 2004. 13th IEEE International Work-shop on Robot and Human Interactive Communication (IEEE Catalog No.04TH8759), pp. 569--574.Google Scholar
- S. M. Al Mahi, M. Atkins, and C. Crick, "Learning to assess the cognitive capacity of human partners," ACM/IEEE Int. Conf. Human-Robot Interact., pp. 63--64, 2017.Google Scholar
- A. M. Aroyo et al., "Can a Humanoid Robot Spot a Liar?," IEEE-RAS 18th Int. Conf. Humanoid Robot., 2018.Google Scholar
- C. Wangwiwattana, X. Ding, and E. C. Larson, "PupilNet, Measuring Task Evoked Pupillary Response using Commodity RGB Tablet Cameras," Proc. ACM Interactive, Mobile, Wearable Ubiquitous Technol., vol. 1, no. 4, pp. 1--26, Jan. 2018.Google ScholarDigital Library
- G. Metta, G. Sandini, D. Vernon, L. Natale, and F. Nori, "The iCub humanoid robot," in Proceedings of the 8th Workshop on Performance Metrics for Intelli-gent Systems - PerMIS '08, 2008, p. 50.Google Scholar
- L. Riek, "Wizard of Oz Studies in HRI: A Systematic Review and New Reporting Guidelines," J. Human-Robot Interact., vol. 1, no. 1, pp. 119--136, 2012.Google ScholarDigital Library
- S. Mathôt, J. Fabius, E. Van Heusden, and S. Van der Stigchel, "Safe and sensible preprocessing and baseline correction of pupil-size data," Behav. Res. Methods, vol. 50, no. 1, pp. 94--106, 2018.Google ScholarCross Ref
- S. Shapiro and M. Wilk, "An analysis of variance test for normality (complete samples)," Z. Bibliothekswes. Bibliogr., vol. 52, no. 6, pp. 311--319, 2005.Google Scholar
- R. B. D'Agostino, A. Belanger, and R. B. D'Agostino, "A Suggestion for Using Powerful and Informative Tests of Normality," Am. Stat., vol. 44, no. 4, p. 316, Nov. 1990.Google Scholar
- F. Wilcoxon, "Individual Comparisons by Ranking Methods," Biometrics Bull., vol. 1, no. 6, p. 80, Dec. 1945.Google ScholarCross Ref
- S. G. K. Patro and K. K. sahu, "Normalization: A Preprocessing Stage," Iarjset, no. April, pp. 20--22, 2015.Google Scholar
- Nitesh V. Chawla, K. W. Bowyer, and L. O. Hall, "SMOTE: Synthetic Minority Over-sampling Technique Nitesh," J. Artif. Intell. Res., 2006.Google Scholar
Index Terms
- Your Eyes Never Lie: A Robot Magician Can Tell if You Are Lying
Recommendations
Magic iCub: A Humanoid Robot Autonomously Catching your Lies in a Card Game
HRI '21: Proceedings of the 2021 ACM/IEEE International Conference on Human-Robot InteractionGames are often used to foster human partners' engagement and natural behavior, even when they are played with or against robots. Therefore, beyond their entertainment value, games represent ideal interaction paradigms where to investigate natural human-...
Lying through the eyes: detecting lies through eye movements
GazeIn '13: Proceedings of the 6th workshop on Eye gaze in intelligent human machine interaction: gaze in multimodal interactionIn this pilot study, we investigated if it is possible to detect lies through eye gaze behavior. Earlier research suggests that lying increases the cognitive load, resulting in less eye -movements and shorter saccade amplitudes. To investigate these ...
Human vs Robot Lie Detector: Better Working as a Team?
Social RoboticsAbstractHuman interaction often entails lies. Understanding when a partner is being deceitful is an important social skill, that also robots will need, to properly navigate social exchanges. In this work, we investigate how good are human observers at ...
Comments