Resumé
In this paper, we address the problem of finding replacements of missing objects, involved in the execution of manipulation tasks. Our approach is based on estimating functional affordances for the unknown objects in order to propose replacements. We use a vision-based affordance estimation system utilizing object-wise global features and a multi-label learning method. This method also associates confidence values to the estimated affordances. We evaluate our approach on kitchen-related manipulation affordances. The evaluation also includes testing different scenarios for training the system using large-scale datasets. The results indicate that the system is able to successfully predict the affordances of novel objects. We also implement our system on a humanoid robot and demonstrate the affordance estimation in a real scene.
| Originalsprog | Engelsk |
|---|---|
| Titel | Proceedings of the 47th International Symposium on Robotics |
| Forlag | VDE-Verlag |
| Publikationsdato | 2016 |
| Sider | 164-172 |
| ISBN (Trykt) | 978-3-8007-4231-8 |
| Status | Udgivet - 2016 |
| Begivenhed | 47th International Symposium on Robotics - Munich, Tyskland Varighed: 21. jun. 2016 → 22. jun. 2016 Konferencens nummer: 47 |
Konference
| Konference | 47th International Symposium on Robotics |
|---|---|
| Nummer | 47 |
| Land | Tyskland |
| By | Munich |
| Periode | 21/06/2016 → 22/06/2016 |
| Sponsor | ABB Robotics, FANUC Deutschland GmbH, KUKA Roboter GmbH, SCHUNK GmbH and Co. KG |
Fingeraftryk
Citer dette
}
Affordance estimation for vision-based object replacement on a humanoid robot. / Mustafa, Wail; Wächter, Mirko; Szedmak, Sandor; Agostini, Alejandro; Kraft, Dirk; Asfour, Tamim; Piater, Justus; Wörgötter, Florentin; Krüger, Norbert.
Proceedings of the 47th International Symposium on Robotics. VDE-Verlag, 2016. s. 164-172.Publikation: Bidrag til bog/antologi/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review
TY - GEN
T1 - Affordance estimation for vision-based object replacement on a humanoid robot
AU - Mustafa, Wail
AU - Wächter, Mirko
AU - Szedmak, Sandor
AU - Agostini, Alejandro
AU - Kraft, Dirk
AU - Asfour, Tamim
AU - Piater, Justus
AU - Wörgötter, Florentin
AU - Krüger, Norbert
PY - 2016
Y1 - 2016
N2 - In this paper, we address the problem of finding replacements of missing objects, involved in the execution of manipulation tasks. Our approach is based on estimating functional affordances for the unknown objects in order to propose replacements. We use a vision-based affordance estimation system utilizing object-wise global features and a multi-label learning method. This method also associates confidence values to the estimated affordances. We evaluate our approach on kitchen-related manipulation affordances. The evaluation also includes testing different scenarios for training the system using large-scale datasets. The results indicate that the system is able to successfully predict the affordances of novel objects. We also implement our system on a humanoid robot and demonstrate the affordance estimation in a real scene.
AB - In this paper, we address the problem of finding replacements of missing objects, involved in the execution of manipulation tasks. Our approach is based on estimating functional affordances for the unknown objects in order to propose replacements. We use a vision-based affordance estimation system utilizing object-wise global features and a multi-label learning method. This method also associates confidence values to the estimated affordances. We evaluate our approach on kitchen-related manipulation affordances. The evaluation also includes testing different scenarios for training the system using large-scale datasets. The results indicate that the system is able to successfully predict the affordances of novel objects. We also implement our system on a humanoid robot and demonstrate the affordance estimation in a real scene.
M3 - Article in proceedings
AN - SCOPUS:84983776379
SN - 978-3-8007-4231-8
SP - 164
EP - 172
BT - Proceedings of the 47th International Symposium on Robotics
PB - VDE-Verlag
ER -