Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Volker Krueger"'
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2010 (2010)
We address the problem of unsupervised discovery of action classes in video data. Different from all existing methods thus far proposed for this task, we present a space-time link analysis approach which consistently matches or exceeds the performanc
Externí odkaz:
https://doaj.org/article/fab6c2ec0cb84403bad7a7bf0a6c4304
Publikováno v:
Image Analysis ISBN: 9783031314377
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a539d3291275d02c822b03f49f314940
https://doi.org/10.1007/978-3-031-31438-4_21
https://doi.org/10.1007/978-3-031-31438-4_21
Publikováno v:
Proceedings of the 12th International Conference on Operations Research and Enterprise Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5188ce23aa421c20721353e5faa482a
https://doi.org/10.5220/0011785100003396
https://doi.org/10.5220/0011785100003396
Publikováno v:
SN Computer Science. 4
Order Picking in warehouses is often optimized using a method known as Order Batching, which means that one vehicle can be assigned to pick a batch of several orders at a time. There exists a rich body of research on Order Batching Problem (OBP) opti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38f5ce7c8f0724b68b84fb5dba158428
https://doi.org/10.1007/s42979-022-01496-0
https://doi.org/10.1007/s42979-022-01496-0
Robot skills systems are meant to reduce robot setup time for new manufacturing tasks. Yet, for dexterous, contact-rich tasks, it is often difficult to find the right skill parameters. One strategy is to learn these parameters by allowing the robot s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc51bd002e1f0b208f17f93219a46852
http://arxiv.org/abs/2208.01605
http://arxiv.org/abs/2208.01605
Publikováno v:
Proceedings of the 3rd International Conference on Innovative Intelligent Industrial Production and Logistics.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::35447e3970183062eae3a7a357c81c76
https://doi.org/10.5220/0011378400003329
https://doi.org/10.5220/0011378400003329
Publikováno v:
Proceedings of the 11th International Conference on Operations Research and Enterprise Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4d79fede1f3fb4b54bebe6635016145
https://doi.org/10.5220/0010837700003117
https://doi.org/10.5220/0010837700003117
Publikováno v:
Bengtson, S H, Åström, H, Moeslund, T B, Topp, E A & Krüger, V 2021, Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering . in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) ., 9636839, IEEE, I E E E International Conference on Intelligent Robots and Systems. Proceedings, pp. 4618-4624, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems-IROS 2021, Prague, Czech Republic, 27/09/2021 . https://doi.org/10.1109/IROS51168.2021.9636839
We propose a novel multi-pose loss function to train a neural network for 6D pose estimation, using synthetic data and evaluating it on real images. Our loss is inspired by the VSD (Visible Surface Discrepancy) metric and relies on a differentiable r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ad3aaeb98f95a01e98933a4c49623fb
https://vbn.aau.dk/ws/files/458094775/IROS_2021_Pose_Estimation_from_RGB_Images_of_Highly_Symmetric_Objects_using_a_Novel_Multi_Pose_Loss_and_Differential_Rendering.pdf
https://vbn.aau.dk/ws/files/458094775/IROS_2021_Pose_Estimation_from_RGB_Images_of_Highly_Symmetric_Objects_using_a_Novel_Multi_Pose_Loss_and_Differential_Rendering.pdf
Publikováno v:
CASE
We address the problem of insufficient quality of robot simulators to produce precise sensor readings for joint positions, velocities and torques. Realistic simulations of sensor readings are particularly important for real time robot control laws an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02c412d7747a390650fbce706d6b5349
https://doi.org/10.1109/case49439.2021.9551626
https://doi.org/10.1109/case49439.2021.9551626
Reinforcement Learning (RL) is a powerful mathematical framework that allows robots to learn complex skills by trial-and-error. Despite numerous successes in many applications, RL algorithms still require thousands of trials to converge to high-perfo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1cc04e24169396113a8ba23bfde74fe