Expressing Robot Personality through Talking Body Language

Abstract

Social robots must master the nuances of human communication as a mean to convey an effective message and generate trust. It is well-known that non-verbal cues are very important in human interactions, and therefore a social robot should produce a body language coherent with its discourse. In this work, we report on a system that endows a humanoid robot with the ability to adapt its body language according to the sentiment of its speech. A combination of talking beat gestures with emotional cues such as eye lightings, body posture of voice intonation and volume permits a rich variety of behaviors. The developed approach is not purely reactive, and it easily allows to assign a kind of personality to the robot. We present several videos with the robot in two different scenarios, and showing discrete and histrionic personalities.

Creating Expressive Social Robots That Convey Symbolic and Spontaneous Communication

“…Based on these gestures’ affective state and meaning in the context of the sentence, a gesture ranker selects one gesture to be generated. Zabala et al [ 29 ] presented a method for adapting beat gestures, lights in the eyes, body posture, and vocal intonation and volume to the sentiment of a humanoid robot’s speech. The system first retrieves the valence score for each word in the script using the VADER sentiment analyser.…”

“…Another interface that is present in multiple robots is coloured LEDs, usually combined with other modalities. This can be seen in the approaches of Gomez et al [ 39 ], Hong et al [ 40 ], or Zabala et al [ 29 ].…”

“…A gesture ranker then selects one expression per sentence, among all of the ones generated. Zabala et al [ 29 ] also extracted the sentiment of the robot’s speech. This value is simultaneously passed as an input to the GAN-based gesture-generation method, converted into RGB values for the LED in the robot’s eyes, and used to control the volume, speed, and pitch of the robot’s voice.…”

Towards a Personality AI for Robots: Potential Colony Capacity of a Goal-Shaped Generative Personality Model When Used for Expressing Personalities via Non-Verbal Behaviour of Humanoid Robots

“…Many human activities involve “effort”—albeit defined differently in different contexts—and therefore the idea may apply to a range of human behaviour other than body motion. Zabala et al (2021) proposed an affect-based system that generates non-verbal behaviour consistent with the robot’s speech. Their system does not have components to encode inter- and intra-individual differences of personalities by traits but works by generating non-verbal behaviour from the emotions expressed in the robot’s speech.…”

Closing the loop in minimally supervised human–robot interaction: formative and summative feedback

“…Although there is extensive research on the detection of user gestures 5 , robot-generated gestures are only rarely studied in human–robot interaction (HRI) and are frequently combined with speech 6 . In particular, gesture-based interactions have mainly been studied for story-telling robots 7 , 8 , social interactions 9 , 10 , and educational activities for children 11 . However, nonverbal cues have not yet been thoroughly investigated for helping autonomous robots guide humans to perform physical tasks.…”