95 citations · 180 across the 12 of their papers we have counts for
12 papers
Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning
Hakan Aktas, Yigit Yildirim, Ahmet Firat Gamsiz +3
This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The archite…
Bidirectional Progressive Neural Networks with Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer
Suzan Ece Ada, Hanne Say, Emre Ugur +1
Human brain and behavior provide a rich venue that can inspire novel control and learning methods for robotics. In an attempt to exemplify such a development by inspiring how human…
Symbolic Manipulation Planning with Discovered Object and Relational Predicates
Alper Ahmetoglu, Erhan Oztop, Emre Ugur
Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a c…
Correspondence learning between morphologically different robots via task demonstrations
Hakan Aktas, Yukie Nagai, Minoru Asada +2
We observe a large variety of robots in terms of their bodies, sensors, and actuators. Given the commonalities in the skill sets, teaching each skill to each different robot indepe…
Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers
Alper Ahmetoglu, Batuhan Celik, Erhan Oztop +1
In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continu…
Developmental Scaffolding with Large Language Models
Batuhan Celik, Alper Ahmetoglu, Emre Ugur +1
Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowle…
Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning
Suzan Ece Ada, Erhan Oztop, Emre Ugur
Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges…
Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration
T. Baturhan Akbulut, G. Tuba C. Girgin, Arash Mehrabi +3
Learning from demonstration (LfD) provides a convenient means to equip robots with dexterous skills when demonstration can be obtained in robot intrinsic coordinates. However, the…
Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors
Alper Ahmetoglu, Erhan Oztop, Emre Ugur
In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is…
High-level Features for Resource Economy and Fast Learning in Skill Transfer
Alper Ahmetoglu, Emre Ugur, Minoru Asada +1
Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are pro…
Imitation and Mirror Systems in Robots through Deep Modality Blending Networks
M. Y. Seker, A. Ahmetoglu, Y. Nagai +3
Learning to interact with the environment not only empowers the agent with manipulation capability but also generates information to facilitate building of action understanding and…
Symbol Emergence in Cognitive Developmental Systems: a Survey
Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann +8
Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and a…