95 citations · 260 across the 32 of their papers we have counts for
32 papers
Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning
Suzan Ece Ada, Emre Ugur
We introduce Unsupervised Meta-Testing with Conditional Neural Processes (UMCNP), a novel hybrid few-shot meta-reinforcement learning (meta-RL) method that uniquely combines, yet d…
Bidirectional Human Interactive AI Framework for Social Robot Navigation
Tuba Girgin, Emre Girgin, Yigit Yildirim +2
Trustworthiness is a crucial concept in the context of human-robot interaction. Cooperative robots must be transparent regarding their decision-making process, especially when oper…
Learning Early Social Maneuvers for Enhanced Social Navigation
Yigit Yildirim, Mehmet Suzer, Emre Ugur
Socially compliant navigation is an integral part of safety features in Human-Robot Interaction. Traditional approaches to mobile navigation prioritize physical aspects, such as ef…
Learning Social Navigation from Demonstrations with Deep Neural Networks
Yigit Yildirim, Emre Ugur
Traditional path-planning techniques treat humans as obstacles. This has changed since robots started to enter human environments. On modern robots, social navigation has become an…
Cross-Embodied Affordance Transfer through Learning Affordance Equivalences
Hakan Aktas, Yukie Nagai, Minoru Asada +3
Affordances represent the inherent effect and action possibilities that objects offer to the agents within a given context. From a theoretical viewpoint, affordances bridge the gap…
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…
Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration
Yigit Yildirim, Emre Ugur
Learning from Demonstration (LfD) is a widely used technique for skill acquisition in robotics. However, demonstrations of the same skill may exhibit significant variances, or lear…
A Reinforcement Learning Based Controller to Minimize Forces on the Crutches of a Lower-Limb Exoskeleton
Aydin Emre Utku, Suzan Ece Ada, Muhammet Hatipoglu +3
Metabolic energy consumption of a powered lower-limb exoskeleton user mainly comes from the upper body effort since the lower body is considered to be passive. However, the upper b…
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…
Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances
Tuba Girgin, Emre Ugur
Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in…
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…
Multi-step planning with learned effects of partial action executions
Hakan Aktas, Utku Bozdogan, Emre Ugur
In this paper, we propose a novel affordance model, which combines object, action, and effect information in the latent space of a predictive neural network architecture that is bu…
Meta-World Conditional Neural Processes
Suzan Ece Ada, Emre Ugur
We propose Meta-World Conditional Neural Processes (MW-CNP), a conditional world model generator that leverages sample efficiency and scalability of Conditional Neural Processes to…
Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experiments
Hamit Basgol, Inci Ayhan, Emre Ugur
People segment complex, ever-changing and continuous experience into basic, stable and discrete spatio-temporal experience units, called events. Event segmentation literature inves…
Learning Social Navigation from Demonstrations with Conditional Neural Processes
Yigit Yildirim, Emre Ugur
Sociability is essential for modern robots to increase their acceptability in human environments. Traditional techniques use manually engineered utility functions inspired by obser…
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…
Object and Relation Centric Representations for Push Effect Prediction
Ahmet E. Tekden, Aykut Erdem, Erkut Erdem +2
Pushing is an essential non-prehensile manipulation skill used for tasks ranging from pre-grasp manipulation to scene rearrangement, reasoning about object relations in the scene,…
Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization
M. Tuluhan Akbulut, Utku Bozdogan, Ahmet Tekden +1
The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challengi…