TY - GEN
T1 - Effect of grasping uniformity on estimation of grasping region from gaze data
AU - Witchawanitchanun, Pimwalun
AU - Yucel, Zeynep
AU - Monden, Akito
AU - Leelaprute, Pattara
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number J18K18168.
Publisher Copyright:
© 2019 ACM.
PY - 2019/9/25
Y1 - 2019/9/25
N2 - This study explores estimation of grasping region of objects from gaze data. Our study distinguishes from previous works by accounting for "grasping uniformity" of the objects. In particular, we consider three types of graspable objects: (i) with a well-defined graspable part (e.g. handle), (ii) without a grip but with an intuitive grasping region, (iii) without any grip or intuitive grasping region. We assume that these types define how "uniform" grasping region is across different graspers. In experiments, we use "Learning to grasp" data set and apply the method of [5] for estimating grasping region from gaze data. We compute similarity of estimations and ground truth annotations for the three types of objects regarding subjects (a) who perform free viewing and (b) who view the images with the intention of grasping. In line with many previous studies, similarity is found to be higher for non-graspers. An interesting finding is that the difference in similarity (between free viewing and motivated to grasp) is higher for type-iii objects; and comparable for type-i and ii objects. Based on this, we believe that estimation of grasping region from gaze data offers a larger potential to "learn" particularly grasping of type-iii objects.
AB - This study explores estimation of grasping region of objects from gaze data. Our study distinguishes from previous works by accounting for "grasping uniformity" of the objects. In particular, we consider three types of graspable objects: (i) with a well-defined graspable part (e.g. handle), (ii) without a grip but with an intuitive grasping region, (iii) without any grip or intuitive grasping region. We assume that these types define how "uniform" grasping region is across different graspers. In experiments, we use "Learning to grasp" data set and apply the method of [5] for estimating grasping region from gaze data. We compute similarity of estimations and ground truth annotations for the three types of objects regarding subjects (a) who perform free viewing and (b) who view the images with the intention of grasping. In line with many previous studies, similarity is found to be higher for non-graspers. An interesting finding is that the difference in similarity (between free viewing and motivated to grasp) is higher for type-iii objects; and comparable for type-i and ii objects. Based on this, we believe that estimation of grasping region from gaze data offers a larger potential to "learn" particularly grasping of type-iii objects.
KW - Human-robot collaboration
KW - Joint attention
KW - Social robotics
UR - http://www.scopus.com/inward/record.url?scp=85077118005&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077118005&partnerID=8YFLogxK
U2 - 10.1145/3349537.3352787
DO - 10.1145/3349537.3352787
M3 - Conference contribution
AN - SCOPUS:85077118005
T3 - HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction
SP - 265
EP - 267
BT - HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction
PB - Association for Computing Machinery, Inc
T2 - 7th International Conference on Human-Agent Interaction, HAI 2019
Y2 - 6 October 2019 through 10 October 2019
ER -