Browsing Computer Science by Author "(ORCID 0000-0002-3051-6038 & YÖK ID 45227) Öztop, Erhan"
Now showing items 21-40 of 57
-
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 ... -
Guest editorial special issue on continual unsupervised sensorimotor learning
Navarro-Guerrero, N.; Nguyen, S. M.; Öztop, Erhan; Zhong, J. (IEEE, 2021-06)The pursuit of higher levels of autonomy and versatility in robotics is arguably led by two main factors. First, as we push robots out of the labs and production lines, it becomes increasingly challenging to design for all ... -
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 ... -
HMM bazlı 3 boyutlu insan hareketi tanıma ile insan ve robotun ortak çalışması
Pehlivan, Alp Burak; Öztop, Erhan (IEEE, 2014)We offer a system for a human-robot cooperation with natural communication in order to make using of robots in human-interactive tasks easier and more effective. This system includes a system with 3D motion capture cameras, ... -
Human adaptation to human–robot shared control
Amirshirzad, Negin; Kumru, Asiye; Öztop, Erhan (IEEE, 2019-04)Human-in-the-loop robot control systems naturally provide the means for synergistic human-robot collaboration through control sharing. The expectation in such a system is that the strengths of each partner are combined to ... -
Human motor adaptation in whole body motion
Babic, J.; Öztop, Erhan; Kawato, M. (2016)The main role of the sensorimotor system of an organism is to increase the survival of the species. Therefore, to understand the adaptation and optimality mechanisms of motor control, it is necessary to study the sensorimotor ... -
Human-in-the-loop control and task learning for pneumatically actuated muscle based robots
Teramae, T.; Ishihara, K.; Babič, J.; Morimoto, J.; Öztop, Erhan (Frontiers Media, 2018-11-06)Pneumatically actuated muscles (PAMs) provide a low cost, lightweight, and high power-To-weight ratio solution for many robotic applications. In addition, the antagonist pair configuration for robotic arms make it open to ... -
Imitation and mirror systems in robots through Deep Modality Blending Networks
Seker, M. Y.; Ahmetoglu, A.; Nagai, Y.; Asada, M.; Öztop, Erhan; Ugur, E. (Elsevier, 2022-02)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 imitation capabilities. This seems to be ... -
Inferring cost functions using reward parameter search and policy gradient reinforcement learning
Arditi, Emir; Kunavar, T.; Ugur, E.; Babic, J.; Öztop, Erhan (IEEE, 2021)This study focuses on inferring cost functions of obtained movement data using reward parameter search and policy gradient based Reinforcement Learning (RL). The behavior data for this task is obtained through a series of ... -
Interplay between neural computational energy and multimodal processing in robot-robot interaction
Kırtay, M.; Hafner, V. V.; Asada, M.; Öztop, Erhan (IEEE, 2023)Multimodal learning is an active research area that is gaining importance in human-robot interaction. Despite the obvious benefit of levering multiple sensors for perceiving the world, its neural computational cost has not ... -
Learning medical suturing primitives for autonomous suturing
Amirshirzad, Negin; Sunal, Begüm; Bebek, Özkan; Öztop, Erhan (IEEE, 2021)This paper focuses on a learning from demonstration approach for autonomous medical suturing. A conditional neural network is used to learn and generate suturing primitives trajectories which were conditioned on desired ... -
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 ... -
Learning to grasp with parental scaffolding
Ugur, E.; Celikkanat, H.; Şahin, E.; Nagai, Y.; Öztop, Erhan (IEEE, 2011)Parental scaffolding is an important mechanism utilized by infants during their development. Infants, for example, pay stronger attention to the features of objects highlighted by parents and learn the way of manipulating ... -
Minimal sign representation of boolean functions: algorithms and exact results for low dimensions
Sezener, Can Eren; Öztop, Erhan (MIT Press, 2015-08)Boolean functions (BFs) are central in many fields of engineering and mathematics, such as cryptography, circuit design, and combinatorics. Moreover, they provide a simple framework for studying neural computation mechanisms ... -
Mirror neurons: Functions, mechanisms and models
Öztop, Erhan; Kawato, M.; Arbib, M. A. (Elsevier, 2013-04-12)Mirror neurons for manipulation fire both when the animal manipulates an object in a specific way and when it sees another animal (or the experimenter) perform an action that is more or less similar. Such neurons were ... -
A model for cognitively valid lifelong learning
Say, H.; Öztop, Erhan (IEEE, 2023)In continual learning, usually a sequence of tasks are given to a learning agent and the performance of the agent after learning is measured in terms of resistance to catastrophic forgetting, efficacy of knowledge transfer ... -
Modeling robot trust based on emergent emotion in an interactive task
Kırtay, M.; Öztop, Erhan; Asada, M.; Hafner, V. V. (IEEE, 2021)Trust is an essential component in human-human and human-robot interactions. The factors that play potent roles in these interactions have been an attractive issue in robotics. However, the studies that aim at developing ... -
Modeling the development of infant imitation using inverse reinforcement learning
Tekden, A. E.; Ugur, E.; Nagai, Y.; Öztop, Erhan (IEEE, 2018-09)Little is known about the computational mechanisms of how imitation skills develop along with infant sensorimotor learning. In robotics, there are several well developed frameworks for imitation learning or so called ... -
Multimodal reinforcement learning for partner specific adaptation in robot-multi-robot interaction
Kırtay, M.; Hafner, V. V.; Asada, M.; Kuhlen, A. K.; Öztop, Erhan (IEEE, 2022)Successful and efficient teamwork requires knowledge of the individual team members' expertise. Such knowledge is typically acquired in social interaction and forms the basis for socially intelligent, partner-Adapted ... -
On the co-absence of input terms in higher order neuron representation of boolean functions
Yapar, O.; Öztop, Erhan (Springer International Publishin, 2017)Boolean functions (BFs) can be represented by using polynomial functions when −1 and +1 are used represent True and False respectively. The coefficients of the representing polynomial can be obtained by exact interpolation ...
Share this page