Browsing Faculty of Engineering by Author "Uğur, E."
Now showing items 1-11 of 11
-
ACNMP: skill transfer and task extrapolation through learning from demonstration and reinforcement learning via representation sharing
Akbulut, M. T.; Öztop, Erhan; Xue, H.; Tekden, A. E.; Şeker, M. Y.; Uğur, E. (ML Research Press, 2020)To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). ... -
Adaptive shared control with human intention estimation for human agent collaboration
Amirshirzad, Negin; Uğur, E.; Bebek, Özkan; Öztop, Erhan (IEEE, 2022)In this paper an adaptive shared control frame-work for human agent collaboration is introduced. In this framework the agent predicts the human intention with a confidence factor that also serves as the control blending ... -
Deep multi-object symbol learning with self-attention based predictors
Ahmetoğlu, A.; Öztop, Erhan; Uğur, E. (IEEE, 2023)This paper proposes an architecture that can learn symbolic representations from the continuous sensorimotor experience of a robot interacting with a varying number of objects. Unlike previous works, this work aims to ... -
Discovering predictive relational object symbols with symbolic attentive layers
Ahmetoglu, A.; Celik, B.; Öztop, Erhan; Uğur, E. (IEEE, 2024-02-01)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 ... -
An ecologically valid reference frame for perspective invariant action recognition
Bayram, Berkay; Uğur, E.; Asada, M.; Öztop, Erhan (IEEE, 2021)In robotics, objects and body parts can be represented in various coordinate frames to ease computation. In biological systems, body or body part centered coordinate frames have been proposed as possible reference frames ... -
Exploration with intrinsic motivation using object–action–outcome latent space
Sener, M. İ.; Nagai, Y.; Öztop, Erhan; Uğur, E. (IEEE, 2023-06)One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration ... -
High-level features for resource economy and fast learning in skill transfer
Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective and efficient decision making. Although, deep neural networks are proven to be effective learning ... -
High-level representations through unconstrained sensorimotor learning
Öztürkçü, Özgür Baran; Uğur, E.; Öztop, E. (IEEE, 2020-10-26)How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming ... -
Learning system dynamics via deep recurrent and conditional neural systems
Pekmezci, Mehmet; Uğur, E.; Öztop, Erhan (IEEE, 2021)Although there are various mathematical methods for modeling system dynamics, more general solutions can be achieved using deep learning based on data. Alternative deep learning methods are presented in parallel with the ... -
Self-discovery of motor primitives and learning grasp affordances
Uğur, E.; Şahin, E.; Öztop, Erhan (IEEE, 2012)Human infants practice their initial, seemingly random arm movements for transforming them into voluntary reaching and grasping actions. With the developing perceptual abilities, infants further explore their environment ... -
Symbol emergence in cognitive developmental systems: A survey
Taniguchi, T.; Uğur, E.; Hoffmann, M.; Jamone, L.; Nagai, T.; Rosman, B.; Matsuka, T.; Iwahashi, N.; Öztop, Erhan; Piater, J.; Worgotter, F. (IEEE, 2019-12)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 adaptation to our real-world environment. ...
Share this page