Abstract
The affective motion of humans conveys messages that other humans perceive and understand without conventional linguistic processing. This ability to classify human movement into meaningful gestures or segments plays also a critical role in creating social interaction between humans and robots. In the research presented here, grasping and social gesture recognition by humans and four machine learning techniques (k-Nearest Neighbor, Locality-Sensitive Hashing Forest, Random Forest and Support Vector Machine) is assessed by using human classification data as a reference for evaluating the classification performance of machine learning techniques for thirty hand/arm gestures. The gestures are rated according to the extent of grasping motion on one task and the extent to which the same gestures are perceived as social according to another task. The results indicate that humans clearly rate differently according to the two different tasks. The machine learning techniques provide a similar classification of the actions according to grasping kinematics and social quality. Furthermore, there is a strong association between gesture kinematics and judgments of grasping and the social quality of the hand/arm gestures. Our results support previous research on intention-from-movement understanding that demonstrates the reliance on kinematic information for perceiving the social aspects and intentions in different grasping actions as well as communicative point-light actions.
Highlights
Social competence relies on successful human-human interaction where people have the ability to recognize and understand human social gestures and transitive gestures that convey intentions when interacting with objects (e.g., McNeill, 1992)
One important issue in our results concerns the more specific information that contributes to the classification distinction between social and non-social gestures given by the kinematic patterns of hand and arm movement
It is an open question as to what specific information humans are using in their classification behavior
Summary
Social competence relies on successful human-human interaction where people have the ability to recognize and understand human social gestures (hand/arm actions) and transitive gestures that convey intentions when interacting with objects (e.g., McNeill, 1992). Within the area of human-robot interaction (HRI), there is a continuing development of robots to demonstrate relevant social behavior understanding (Breazeal, 2004; Carter et al, 2014; Yang, et al, 2007; Dautenhahn, 2007; Dautenhahn and Saunders, 2011; Kanda and Ishiguro, 2013). This appears to be the case even in industrial settings (Gleeson et al, 2013; Liu and Wang, 2018) as well as in the assisting services and healthcare areas (Cao et al, 2019). Previous results from (Hemeren and Thill, 2011) demonstrated an association between the contextual activation of an action representation due to previous experience and the kinematics of the specific grasping action
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call