TY - CHAP AU - Károly, István Artúr AU - Nádas, Imre AU - Galambos, Péter ED - IEEE, Publ. TI - Synthetic Multimodal Video Benchmark (SMVB): Utilizing Blender for rich dataset generation T2 - IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics : SAMI 2024 : Proceedings PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Danvers (MA) SN - 9798350317206 PY - 2024 SP - 65 EP - 70 PG - 6 DO - 10.1109/SAMI60510.2024.10432848 UR - https://m2.mtmt.hu/api/publication/34532023 ID - 34532023 LA - English DB - MTMT ER - TY - JOUR AU - Károly, István Artúr AU - Tirczka, Sebestyén AU - Gao, Huijun AU - Rudas, Imre AU - Galambos, Péter TI - Increasing the Robustness of Deep Learning Models for Object Segmentation: A Framework for Blending Automatically Annotated Real and Synthetic Data JF - IEEE TRANSACTIONS ON CYBERNETICS J2 - IEEE T CYBERNETICS VL - 54 PY - 2024 IS - 1 SP - 25 EP - 38 PG - 14 SN - 2168-2267 DO - 10.1109/TCYB.2023.3276485 UR - https://m2.mtmt.hu/api/publication/34027020 ID - 34027020 LA - English DB - MTMT ER - TY - THES AU - Károly, István Artúr TI - New Deep Neural Network Applications in Robot Control and System Supervision PB - Óbudai Egyetem PY - 2023 SP - 132 UR - https://m2.mtmt.hu/api/publication/34729097 ID - 34729097 LA - English DB - MTMT ER - TY - PAT AU - Felix, Wolf Hans Erich von Drigalski AU - Ryo, Yonetani AU - Károly, István Artúr TI - Movement planning device, movement planning method, and non-transitory computer readable medium PY - 2023 UR - https://m2.mtmt.hu/api/publication/34415088 ID - 34415088 LA - English DB - MTMT ER - TY - JOUR AU - Károly, István Artúr AU - Galambos, Péter TI - Task-Specific Grasp Planning for Robotic Assembly by Fine-Tuning GQCNNs on Automatically Generated Synthetic Data JF - APPLIED SCIENCES-BASEL J2 - APPL SCI-BASEL VL - 13 PY - 2022 IS - 1 PG - 10 SN - 2076-3417 DO - 10.3390/app13010525 UR - https://m2.mtmt.hu/api/publication/33557664 ID - 33557664 AB - In modern robot applications, there is often a need to manipulate previously unknown objects in an unstructured environment. The field of grasp-planning deals with the task of finding grasps for a given object that can be successfully executed with a robot. The predicted grasps can be evaluated according to certain criteria, such as analytical metrics, similarity to human-provided grasps, or the success rate of physical trials. The quality of a grasp also depends on the task which will be carried out after the grasping is completed. Current task-specific grasp planning approaches mostly use probabilistic methods, which utilize categorical task encoding. We argue that categorical task encoding may not be suitable for complex assembly tasks. This paper proposes a transfer-learning-based approach for task-specific grasp planning for robotic assembly. The proposed method is based on an automated pipeline that quickly and automatically generates a small-scale task-specific synthetic grasp dataset using Graspit! and Blender. This dataset is utilized to fine-tune pre-trained grasp quality convolutional neural networks (GQCNNs). The aim is to train GQCNNs that can predict grasps which do not result in a collision when placing the objects. Consequently, this paper focuses on the geometric feasibility of the predicted grasps and does not consider the dynamic effects. The fine-tuned GQCNNs are evaluated using the Moveit! Task Constructor motion planning framework, which enables the automated inspection of whether the motion planning for a task is feasible given a predicted grasp and, if not, which part of the task is responsible for the failure. Our results suggest that fine-tuning GQCNN models can result in superior grasp-planning performance (0.9 success rate compared to 0.65) in the context of an assembly task. Our method can be used to rapidly attain new task-specific grasp policies for flexible robotic assembly applications. LA - English DB - MTMT ER - TY - CHAP AU - Károly, István Artúr AU - Sebestyén, Tirczka AU - Piricz, Tamás AU - Galambos, Péter ED - Szakál, Anikó TI - Robotic Manipulation of Pathological Slides Powered by Deep Learning and Classical Image Processing T2 - IEEE Joint 22nd International Symposium on COMPUTATIONAL INTELLIGENCE and INFORMATICS and 8th International Conference on Recent Achievements in Mechatronics, Automation, Computer Science and Robotics (CINTI-MACRo 2022) PB - IEEE Hungary Section CY - Budapest SN - 9798350398823 PY - 2022 SP - 387 EP - 392 PG - 6 DO - 10.1109/CINTI-MACRo57952.2022.10029564 UR - https://m2.mtmt.hu/api/publication/33262785 ID - 33262785 LA - English DB - MTMT ER - TY - CHAP AU - Tarsoly, Sándor AU - Károly, István Artúr AU - Galambos, Péter ED - Szakál, Anikó TI - Lessons Learnt with Traditional Image Processing Techniques for Mushroom Detection T2 - IEEE 10th Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems ICCC 2022 PB - IEEE Hungary Section CY - Budapest SN - 9781665481762 PY - 2022 SP - 1 EP - 8 PG - 8 UR - https://m2.mtmt.hu/api/publication/32886757 ID - 32886757 LA - English DB - MTMT ER - TY - CHAP AU - Károly, István Artúr AU - Károly, Ármin AU - Galambos, Péter ED - Szakál, Anikó TI - Automatic Generation and Annotation of Object Segmentation Datasets Using Robotic Arm T2 - IEEE 10th Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems ICCC 2022 PB - IEEE Hungary Section CY - Budapest SN - 9781665481762 PY - 2022 SP - 63 EP - 68 PG - 6 DO - 10.1109/ICCC202255925.2022.9922852 UR - https://m2.mtmt.hu/api/publication/32886749 ID - 32886749 LA - English DB - MTMT ER - TY - CHAP AU - Károly, István Artúr AU - Galambos, Péter TI - Automated Dataset Generation with Blender for Deep Learning-based Object Segmentation T2 - IEEE 20th Jubilee World Symposium on Applied Machine Intelligence and Informatics SAMI (2022) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Poprad SN - 9781665497039 PY - 2022 SP - 329 EP - 333 PG - 5 DO - 10.1109/SAMI54271.2022.9780790 UR - https://m2.mtmt.hu/api/publication/32596965 ID - 32596965 LA - English DB - MTMT ER - TY - CHAP AU - Károly, István Artúr AU - Levendovics, Renáta AU - Haidegger, Tamás AU - Galambos, Péter ED - IEEE, , TI - Moving Obstacle Segmentation with an Optical Flow-based DNN: an Implementation Case Study T2 - 2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - New York, New York SN - 9781665444996 PY - 2021 SP - 000189 EP - 000194 PG - 6 DO - 10.1109/INES52918.2021.9512898 UR - https://m2.mtmt.hu/api/publication/32154559 ID - 32154559 LA - English DB - MTMT ER -