A study of reaching motions for collaborative human-robot interaction

Sara Sheikholeslami, Gilwoo Lee, Justin W. Hart, Siddhartha Srinivasa, Elizabeth A. Croft

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch


In human-human interactions, individuals naturally achieve fluency by anticipating the partner’s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.

Original languageEnglish
Title of host publicationProceedings of the 2018 International Symposium on Experimental Robotics
EditorsJing Xiao, Torsten Kröger, Oussama Khatib
Place of PublicationCham Switzerland
Number of pages11
ISBN (Electronic)9783030339500
ISBN (Print)9783030339494
Publication statusPublished - 2020
EventInternational Symposium on Experimental Robotics 2018 - Buenos Aires, Argentina
Duration: 5 Nov 20188 Nov 2018

Publication series

NameSpringer Proceedings in Advanced Robotics
ISSN (Print)2511-1256
ISSN (Electronic)2511-1264


ConferenceInternational Symposium on Experimental Robotics 2018
Abbreviated titleISER 2018
CityBuenos Aires
Internet address

Cite this