Evaluation of affective state estimations using an on-line reporting device during human-robot interactions

Abstract

Abstract-In order to develop a friendly and safe interaction between humans and robots, it is essential for the robot to evaluate user's affective states and respond accordingly. However, affective states are typically assessed using offline questionnaires and user reports. In this paper we investigate the use of an online-device for collecting real-time user reports of affective state during interaction with a robot. These reports are compared to both previous survey reports taken after the interaction, and the affective states estimated by an inference system. The aim is to evaluate and characterize the physiological signal-based inference system and determine which factors significantly influence its performance. This analysis will be used in future work, to fine tune the affective estimations by identifying what kind of variations in physiological signals precede or accompany the variations in reported affective states.

An Investigation of Responses to Robot-Initiated Touch in a Nursing Context

“…Several researchers have employed GSR to characterize people's responses during HRI or to enable a robot to respond to a human's affective state [21,28,35,39,45].…”

Perceived Safety in Physical Human Robot Interaction -- A Survey

“…The last category includes devices aimed at providing direct feedback during the experiment: these, as for questionnaires, provide a subjective measure of perceived safety, which however can be acquired in "real-time" rather than at the end of the experiment. The first device, used by Zoghbi et al in [25], was named Affective-State Reporting Device (ASRD), and was "an in-house developed modified joystick [...] to record affective states expressed by each user" [25]. The second, used by Koay and coauthors in [46,47,49,73,77] was the so-called Comfort Level Device (CLD), i.e., "a handheld comfort level monitoring device that would allow subjects to indicate their internal comfort level during the experiment" [46].…”

“…Industrial manipulators constitute the type of robot on which the largest number of papers were written on perceived safety in pHRI. Earlier works used standard industrial manipulators, and precisely CRS A460 [20,21,[23][24][25], Mitsubishi Movemaster RM-501 [18,19,22], ABB IRB-120 [29,31], Comau SMART SiX [27], Yaskawa MOTOMAN-K10S and SONY SRX-410 [28]. More recent papers, instead, started using collaborative robots: KUKA LBR iiwa [35,38,43], Kinova MICO [33], UR3 [44], UR5 [39], UR10, [30], Sawyer [45], and Franka Emika Panda [42].…”

“…In addition to the previous categorization, papers [17, 20, 21, 23-26, 28, 29, 31-33, 35, 36, 38-40] focused on finding a connection between perceived safety, robot speed, and relative distance between human and robot, with [27,30,40] having an explicit focus on motion prediction. The human attitude toward robot position and approach direction was studied in [18,25]. Finally, the effect of visibility/audibility of the robot by the human subjects were analyzed in [18,22].…”

Mitigating User Frustration through Adaptive Feedback based on Human-Automation Etiquette Strategies

“…It is the basis of many sensor techniques, including electrodermal response, psychogalvanic reflex, skin conductance response, and skin conductance level (Conesa, 1995). Studies have found that skin response is positively correlated with body arousal (Meisner, Isler, & Trinkle, 2008;Swangnetr, Zhu, Kaber, & Taylor, 2010;Zoghbi, Croft, Kulic, & Van der Loos, 2009;Rosenthal-von, Krämer, Hoffmann, Sobieraj, & Eimler, 2013;Chen, King, Thomaz, & Kemp, 2014). For instance, Bradley and Lang (2000) found a significant correlation between emotional stimuli and skin conductance.…”