Getting on top of things : Towards intelligent robotic object stacking through image-schematic reasoning (bibtex)

by Dhanabalachandran, Kaviya, Hedblom, Maria M. and Beetz, Michael

Abstract:

In this extended abstract, we present initial work on intelligent object stacking by household robots using a symbolic approach grounded in image schema research. Image schemas represent spatiotemporal relationships that capture objects’ affordances and dispositions. Therefore, they offer the first step to ground semantic information in symbolic descriptions. We hypothesise that for a robot to successfully stack objects of different dispositions, these relationships can be used to more intelligently identify both task constraints and relevant event segments.

View PDF

Reference:

Dhanabalachandran, Kaviya, Hedblom, Maria M. and Beetz, Michael, "Getting on top of things : Towards intelligent robotic object stacking through image-schematic reasoning", In Proceedings of the Sixth Image Schema Day 2022 : Jönköping, Sweden, March 24-25th, 2022, CEUR-WS, no. 3140, 2022.

Bibtex Entry:

@inproceedings{Dhanabalachandran1662471,
   author = {Dhanabalachandran, Kaviya and Hedblom, Maria M. and Beetz, Michael},
   booktitle = {Proceedings of the Sixth Image Schema Day 2022 : Jönköping, Sweden, March 24-25th, 2022},
   institution = {Jönköping University, Jönköping AI Lab (JAIL)},
   institution = {Institute of Artificial Intelligence, University of Bremen, Germany},
   institution = {Institute of Artificial Intelligence, University of Bremen, Germany},
   publisher = {CEUR-WS},
   title = {Getting on top of things : Towards intelligent robotic object stacking through image-schematic reasoning},
   series = {CEUR Workshop Proceedings},
   number = {3140},
   keywords = {image schemas, object stacking, cognitive robotics, commonsense reasoning, embodied cognition},
   abstract = {In this extended abstract, we present initial work on intelligent object stacking by household robots using a symbolic approach grounded in image schema research. Image schemas represent spatiotemporal relationships that capture objects’ affordances and dispositions. Therefore, they offer the first step to ground semantic information in symbolic descriptions. We hypothesise that for a robot to successfully stack objects of different dispositions, these relationships can be used to more intelligently identify both task constraints and relevant event segments.},
   URL = {http://ceur-ws.org/Vol-3140/paper9.pdf},
   year = {2022}
}