Yigit YILDIRIM

Dr. Yigit YILDIRIM

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 February 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
FDFatih Doğangün
Fatih Doğangün
SBSerdar Bahar
Serdar Bahar
YYYigit YILDIRIM
Yigit YILDIRIM
BTBora Toprak Temir
Bora Toprak Temir
EUEmre Ugur
Emre Ugur
MDMustafa Doga Dogan
Mustafa Doga Dogan
This paper introduces Robotic Augmented Reality for Machine Programming by Demonstration (Rampa), the first ML-integrated, XR-driven end-to-end robotic system, allowing training and deployment of ML models such as ProMPs on the fly, and utilizing the capabilities of state-of-the-art and commercially available AR headsets, e.g., Meta Quest 3, to facilitate the application of Programming by Demonstration (PbD) approaches on industrial robotic arms, e.g., Universal Robots UR10. Our approach enables in-situ data recording, visualization, and fine-tuning of skill demonstrations directly within the user's physical environment. Rampa addresses critical challenges of PbD, such as safety concerns, programming barriers, and the inefficiency of collecting demonstrations on the actual hardware. The performance of our system is evaluated against the traditional method of kinesthetic control in teaching three different robotic manipulation tasks and analyzed with quantitative metrics, measuring task performance and completion time, trajectory smoothness, system usability, user experience, and task load using standardized surveys. Our findings indicate a substantial advancement in how robotic tasks are taught and refined, promising improvements in operational safety, efficiency, and user engagement in robotic programming.

9 October 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YYYigit YILDIRIM
Yigit YILDIRIM
EUEmre Ugur
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 learning systems may attempt to acquire different means of the same skill simultaneously, making it challenging to encode these motions into movement primitives. To address these challenges, we propose an LfD framework, namely the Conditional Neural Expert Processes (CNEP), that learns to assign demonstrations from different modes to distinct expert networks utilizing the inherent information within the latent space to match experts with the encoded representations. CNEP does not require supervision on which mode the trajectories belong to. We compare the performance of CNEP against widely used and powerful LfD methods such as Gaussian Mixture Models, Probabilistic Movement Primitives, and Stable Movement Primitives and show that our method outperforms these baselines on multimodal trajectory datasets. The results reveal enhanced modeling performance for movement primitives, leading to the synthesis of trajectories that more accurately reflect those demonstrated by experts, particularly when the skill demonstrations include intersection points from various trajectories. We evaluated the CNEP model on two real-robot tasks, namely obstacle avoidance and pick-and-place tasks, that require the robot to learn multi-modal motion trajectories and execute the correct primitives given target environment conditions. We also showed that our system is capable of on-the-fly adaptation to environmental changes via an online conditioning mechanism. Lastly, we believe that CNEP offers improved explainability and interpretability by autonomously finding discrete behavior primitives and providing probability values about its expert selection decisions.

Verified
Journal Article
Open access
PDF file
OLOscar Escallada Lopez
Oscar Escallada Lopez
NANagore Osa Arzuaga
Nagore Osa Arzuaga
GLGanix Lasa
Ganix Lasa
MEMaitane Mazmela Etxabe
Maitane Mazmela Etxabe
FDFatih Doğangün
Fatih Doğangün
EUEmre Ugur
Emre Ugur
Extended reality (XR) and collaborative robots are reshaping human–robot interaction (HRI) by introducing novel control methods that enhance user experience (UX). However, human factors such as cognitive workload, usability, trust, and task performance are often underexplored. This study evaluated UX during robotic manipulation tasks under three interaction modalities: manual control, XR-based control at real-time speed (RS), and XR-based control at reduced safety speed (SS). Twenty-one participants performed a series of tasks across three scenarios, where we measured usability, workload, flow state, trust, and agency using a subjective questionnaire adapted from SUS, NASA-TLX, FSS, SoAS, and Trust in Industrial Human–Robot Collaboration Questionnaire, and objective task metrics (completion time, errors, and attempts). Our results reveal that RS-based control modes significantly reduced physical workload and improved usability compared to manual control. RS control at real-time speed enhanced task efficiency but increased error rates during complex tasks, while SS mode mitigated errors at the cost of prolonged completion times. Trust and agency remained stable across all modalities, indicating extended reality technologies do not undermine user confidence. These findings contribute to the field of human–robot collaboration by offering insights regarding efficiency, accuracy, and UX. The results are particularly relevant for industries seeking to optimize safety, productivity, and human-centric robotic systems.