Ozgur
@oskurovic.bsky.social
Roboticist, Perceptionist, Hacettepe University
Our work on Motion Planning with Dynamic Guidance is now available on arXiv, and it will be presented at ICRA Frontiers of Optimization for Robotics Workshop on Monday. arxiv.org/abs/2605.24690
May 30, 2026 at 5:27 PM
Our work on Motion Planning with Dynamic Guidance is now available on arXiv, and it will be presented at ICRA Frontiers of Optimization for Robotics Workshop on Monday. arxiv.org/abs/2605.24690
Our paper that fuses RGB&Thermal images for semantic segmentation by using frequency features in early stages is now available, accepted at Perception Beyond the Visible Spectrum workshop series (IEEE PBVS) CVPR, 2026. arxiv.org/abs/2605.26273, github.com/ismailemrecn... @cvprconference.bsky.social
Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation
Semantic segmentation in complex environments such as urban driving scenes remains challenging under adverse lighting conditions, where RGB images alone provide insufficient information. RGB-Thermal f...
arxiv.org
May 28, 2026 at 2:35 PM
Our paper that fuses RGB&Thermal images for semantic segmentation by using frequency features in early stages is now available, accepted at Perception Beyond the Visible Spectrum workshop series (IEEE PBVS) CVPR, 2026. arxiv.org/abs/2605.26273, github.com/ismailemrecn... @cvprconference.bsky.social
Our paper on Malfunction-Aware Robot Control by using VLA will be presented at VLA Pipelines Workshop at IEEE ICRA 2026.
In this study, we deal with adapting to robot's physical failures to VLA models. arxiv.org/abs/2605.16056, github.com/h-arslan/hea...
In this study, we deal with adapting to robot's physical failures to VLA models. arxiv.org/abs/2605.16056, github.com/h-arslan/hea...
Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control
Research on Vision Language Action (VLA) models has been increasing rapidly in recent years. Although some of them focus on detecting, preventing, and recovering from task failures, they usually don't...
arxiv.org
May 25, 2026 at 6:21 PM
Our paper on Malfunction-Aware Robot Control by using VLA will be presented at VLA Pipelines Workshop at IEEE ICRA 2026.
In this study, we deal with adapting to robot's physical failures to VLA models. arxiv.org/abs/2605.16056, github.com/h-arslan/hea...
In this study, we deal with adapting to robot's physical failures to VLA models. arxiv.org/abs/2605.16056, github.com/h-arslan/hea...
Imitation learning
April 20, 2025 at 4:32 PM
Imitation learning
Thanks for the interview. Also thanks to Nvidia and BTF (bridge to Turkey foundation) for their support in the project.
Learn more about Prof. Ozgur Erkent and his teaching activities at the Hacettepe University in Ankara using Duckiebots and Duckiedrones: t.co/NEOGY2V1Xv
🤖 Get your Duckiebot and Duckiedrone - t.co/kRq9hqXPFj
#Duckietown #Robotics #AI #SAR #Duckiedrones
🤖 Get your Duckiebot and Duckiedrone - t.co/kRq9hqXPFj
#Duckietown #Robotics #AI #SAR #Duckiedrones
April 4, 2025 at 6:32 PM
Thanks for the interview. Also thanks to Nvidia and BTF (bridge to Turkey foundation) for their support in the project.
Post a movie from your birth year
February 12, 2025 at 5:51 AM
Post a movie from your birth year
Reposted by Ozgur
Just another helpful reminder that a human being on a bicycle is the most efficient amongst all animals and machines in terms of energy consumed in moving a certain distance as a function of body weight.
Obvs.
Obvs.
December 8, 2024 at 6:15 AM
Just another helpful reminder that a human being on a bicycle is the most efficient amongst all animals and machines in terms of energy consumed in moving a certain distance as a function of body weight.
Obvs.
Obvs.