1 code implementation • 4 Dec 2020 • Alper Ahmetoglu, M. Yunus Seker, Justus Piater, Erhan Oztop, Emre Ugur
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning.
1 code implementation • 9 Sep 2019 • Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Mert Imre, M. Yunus Seker, Emre Ugur
In this paper, we introduce Belief Regulated Dual Propagation Networks (BRDPN), a general purpose learnable physics engine, which enables a robot to predict the effects of its actions in scenes containing groups of articulated multi-part objects.
Robotics
1 code implementation • 9 Nov 2020 • M. Tuluhan Akbulut, Utku Bozdogan, Ahmet Tekden, Emre Ugur
For this, the experience of the robot, which can be bootstrapped from demonstrated trajectories, is used to train a novel Neural Processes-based deep network that samples from its latent space and generates the required trajectories given desired rewards.
no code implementations • 26 Jan 2018 • Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter
However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.
no code implementations • 3 Sep 2019 • Suzan Ece Ada, Emre Ugur, H. Levent Akin
Furthermore, we increase the generalization capacity in widely used transfer learning benchmarks by using maximum entropy regularization, different critic methods, and curriculum learning in an adversarial setup.
no code implementations • 25 Mar 2020 • M. Tuluhan Akbulut, Erhan Oztop, M. Yunus Seker, Honghu Xue, Ahmet E. Tekden, Emre Ugur
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).
no code implementations • 23 Jul 2020 • Hamit Basgol, Inci Ayhan, Emre Ugur
Firstly, we introduce a brief background from the psychology and neuroscience literature, covering the characteristics and models of time perception and related abilities.
no code implementations • 3 Feb 2021 • Ahmet E. Tekden, Aykut Erdem, Erkut Erdem, Tamim Asfour, Emre Ugur
Our approach enables the robot to predict and adapt the effect of a pushing action as it observes the scene.
no code implementations • 18 Jun 2021 • Alper Ahmetoglu, Emre Ugur, Minoru Asada, Erhan Oztop
To be concrete, in our simulation experiments, we either apply principal component analysis (PCA) or slow feature analysis (SFA) on the signals collected from the last hidden layer of a deep network while it performs a source task, and use these features for skill transfer in a new target task.
no code implementations • 7 Oct 2022 • Yigit Yildirim, Emre Ugur
Sociability is essential for modern robots to increase their acceptability in human environments.
no code implementations • 4 Oct 2022 • Hamit Basgol, Inci Ayhan, Emre Ugur
We compared event segmentation behaviors of participants and our model with this video in two hierarchical event segmentation levels.
no code implementations • 14 Jan 2023 • Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki, Dimitri Ognibene, Pablo Lanillos, Emre Ugur, Lorenzo Jamone, Tomoaki Nakamura, Alejandra Ciria, Bruno Lara, Giovanni Pezzulo
Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics.
no code implementations • 20 Feb 2023 • Suzan Ece Ada, Emre Ugur
To reduce the number of samples required at test time, we first obtain a latent representation of the transition dynamics from a single rollout from the test environment with hidden parameters.
no code implementations • 10 Jul 2023 • Suzan Ece Ada, Erhan Oztop, Emre Ugur
In contrast to behavior cloning, which assumes the data is collected from expert demonstrations, offline RL can work with non-expert data and multimodal behavior policies.
no code implementations • 2 Sep 2023 • Alper Ahmetoglu, Batuhan Celik, Erhan Oztop, Emre Ugur
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 observed effect successfully.
no code implementations • 19 Sep 2023 • Tuba Girgin, Emre Ugur
Learning object affordances is an effective tool in the field of robot learning.
no code implementations • 20 Oct 2023 • Hakan Aktas, Yukie Nagai, Minoru Asada, Erhan Oztop, Emre Ugur
To be specific, besides robots with similar morphologies with different degrees of freedom, we show that a fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework.
no code implementations • 31 Jan 2024 • Aydin Emre Utku, Suzan Ece Ada, Muhammet Hatipoglu, Mustafa Derman, Emre Ugur, Evren Samur
Accordingly, we design a model and a learning framework for a human-exoskeleton system with crutches.
1 code implementation • 13 Feb 2024 • Yigit Yildirim, Emre Ugur
Furthermore, we compare the performance of CNEP with another LfD framework, namely Conditional Neural Movement Primitives (CNMP), on a range of tasks, including experiments on a real robot.
no code implementations • 6 Mar 2024 • Suzan Ece Ada, Hanne Say, Emre Ugur, Erhan Oztop
In an attempt to exemplify such a development by inspiring how humans acquire knowledge and transfer skills among tasks, we introduce a novel multi-task reinforcement learning framework named Episodic Return Progress with Bidirectional Progressive Neural Networks (ERP-BPNN).
no code implementations • 24 Apr 2024 • Hakan Aktas, Yukie Nagai, Minoru Asada, Erhan Oztop, Emre Ugur
As a theoretical lens, affordances bridge the gap between effect and action, providing a nuanced understanding of the connections between agents' actions on entities and the effect of these actions.