Discovering predictive relational object symbols with symbolic attentive layers

Name: Discovering predictive relational object symbols with symbolic attentive layers
Author: Ahmetoglu, A., Celik, B., Öztop, Erhan, Uğur, E.

İsim	Discovering predictive relational object symbols with symbolic attentive layers
Yazar	Ahmetoglu, A., Celik, B., Öztop, Erhan, Uğur, E.
Basım Tarihi:	2024-02-01
Basım Yeri	- IEEE
Konu	Deep learning methods, Developmental robotics, Learning categories and concepts
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2377-3766
Kayıt Numarası	ed092be6-34cb-447e-bd18-fa8da5781e34
Lokasyon	Computer Science
Tarih	2024-02-01
Notlar	TÜBİTAK ; European Commission ; New Energy and Industrial Technology Development Organization ; Japan Science and Technology Agency ; Core Research for Evolutional Science and Technology
Örnek Metin	In this letter, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects in a tabletop environment. The key feature of the model is that it can take a changing number of objects as input and map the object-object relations into symbolic domain explicitly. In the model, we employ a self-attention layer that computes discrete attention weights from object features, which are treated as relational symbols between objects. These relational symbols are then used to aggregate the learned object symbols and predict the effects of executed actions on each object. The result is a pipeline that allows the formation of object symbols and relational symbols from a dataset of object features, actions, and effects in an end-to-end manner. We compare the performance of our proposed architecture with state-of-the-art symbol discovery methods in a simulated tabletop environment where the robot needs to discover symbols related to the relative positions of objects to predict the action's result. Our experiments show that the proposed architecture performs better than other baselines in effect prediction while forming not only object symbols but also relational symbols.
DOI	10.1109/LRA.2024.3350994
Cilt	9

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Discovering predictive relational object symbols with symbolic attentive layers

Yazar Ahmetoglu, A., Celik, B., Öztop, Erhan, Uğur, E.

Basım Tarihi 2024-02-01

Basım Yeri - IEEE

Konu Deep learning methods, Developmental robotics, Learning categories and concepts

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2377-3766

Kayıt Numarası ed092be6-34cb-447e-bd18-fa8da5781e34

Lokasyon Computer Science

Tarih 2024-02-01

Notlar TÜBİTAK ; European Commission ; New Energy and Industrial Technology Development Organization ; Japan Science and Technology Agency ; Core Research for Evolutional Science and Technology

Örnek Metin In this letter, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects in a tabletop environment. The key feature of the model is that it can take a changing number of objects as input and map the object-object relations into symbolic domain explicitly. In the model, we employ a self-attention layer that computes discrete attention weights from object features, which are treated as relational symbols between objects. These relational symbols are then used to aggregate the learned object symbols and predict the effects of executed actions on each object. The result is a pipeline that allows the formation of object symbols and relational symbols from a dataset of object features, actions, and effects in an end-to-end manner. We compare the performance of our proposed architecture with state-of-the-art symbol discovery methods in a simulated tabletop environment where the robot needs to discover symbols related to the relative positions of objects to predict the action's result. Our experiments show that the proposed architecture performs better than other baselines in effect prediction while forming not only object symbols but also relational symbols.

DOI 10.1109/LRA.2024.3350994

Cilt 9