Zobrazeno 1 - 10
of 631
pro vyhledávání: '"P. Koert"'
Autor:
Maninis, Kevis-Kokitsi, Chen, Kaifeng, Ghosh, Soham, Karpur, Arjun, Chen, Koert, Xia, Ye, Cao, Bingyi, Salz, Daniel, Han, Guangxing, Dlabal, Jan, Gnanapragasam, Dan, Seyedhosseini, Mojtaba, Zhou, Howard, Araujo, Andre
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised image-only pretrain
Externí odkaz:
http://arxiv.org/abs/2410.16512
Autor:
Joung, Chankyu, van Koert, Otto
In this paper we propose a computational approach to proving the Birkhoff conjecture on the restricted three-body problem, which asserts the existence of a disk-like global surface of section. Birkhoff had conjectured this surface of section as a too
Externí odkaz:
http://arxiv.org/abs/2407.19159
Autor:
Prasad, Vignesh, Kshirsagar, Alap, Koert, Dorothea, Stock-Homburg, Ruth, Peters, Jan, Chalvatzaki, Georgia
Shared dynamics models are important for capturing the complexity and variability inherent in Human-Robot Interaction (HRI). Therefore, learning such shared dynamics models can enhance coordination and adaptability to enable successful reactive inter
Externí odkaz:
http://arxiv.org/abs/2407.07636
Autor:
Hahne, Fabian, Prasad, Vignesh, Kshirsagar, Alap, Koert, Dorothea, Stock-Homburg, Ruth Maria, Peters, Jan, Chalvatzaki, Georgia
Hidden Markov Models with an underlying Mixture of Gaussian structure have proven effective in learning Human-Robot Interactions from demonstrations for various interactive tasks via Gaussian Mixture Regression. However, a mismatch occurs when segmen
Externí odkaz:
http://arxiv.org/abs/2402.14548
Autor:
Göksu, Yasemin, Correia, Antonio De Almeida, Prasad, Vignesh, Kshirsagar, Alap, Koert, Dorothea, Peters, Jan, Chalvatzaki, Georgia
Bimanual handovers are crucial for transferring large, deformable or delicate objects. This paper proposes a framework for generating kinematically constrained human-like bimanual robot motions to ensure seamless and natural robot-to-human object han
Externí odkaz:
http://arxiv.org/abs/2402.14525
Using methods from symplectic geometry, the second and fifth authors have provided theoretical groundwork and tools aimed at analyzing periodic orbits, their stability and their bifurcations in families, for the purpose of space mission design. The B
Externí odkaz:
http://arxiv.org/abs/2308.03391
Learning priors on trajectory distributions can help accelerate robot motion planning optimization. Given previously successful plans, learning trajectory generative models as priors for a new planning problem is highly desirable. Prior works propose
Externí odkaz:
http://arxiv.org/abs/2308.01557
Autor:
Joung, Chankyu, Kim, Mijin, Paik, Taejin, Kong, Seong-Ho, Oh, Seung-Young, Jeon, Won Kyeong, Jeon, Jae-hu, Hong, Joong-Sik, Kim, Wan-Joong, Kook, Woong, Cha, Myung-Jin, van Koert, Otto
Publikováno v:
PLoS ONE 19(6): e0303178 (2024)
Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T wave
Externí odkaz:
http://arxiv.org/abs/2304.06237
Publikováno v:
BMC Medical Informatics and Decision Making, Vol 24, Iss 1, Pp 1-15 (2024)
Abstract Background BERT models have seen widespread use on unstructured text within the clinical domain. However, little to no research has been conducted into classifying unstructured clinical notes on the basis of patient lifestyle indicators, esp
Externí odkaz:
https://doaj.org/article/45d3e1bf4ce44831a340e72fdde72a58
Autor:
Paik, Taejin, van Koert, Otto
In this paper, we study the expectation values of topological invariants of the Vietoris-Rips complex and \v{C}ech complex for a finite set of sample points on a Riemannian manifold. We show that the Betti number and Euler characteristic of the compl
Externí odkaz:
http://arxiv.org/abs/2211.12058