Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Erik Derner"'
Publikováno v:
IEEE Access, Vol 12, Pp 126176-126187 (2024)
As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disinformation to data breaches and
Externí odkaz:
https://doaj.org/article/029e0f9f89194bc0ab0325b01591f02b
Publikováno v:
IEEE Access, Vol 12, Pp 37840-37849 (2024)
Many real-world systems can be naturally described by mathematical formulas. The task of automatically constructing formulas to fit observed data is called symbolic regression. Evolutionary methods such as genetic programming have been commonly used
Externí odkaz:
https://doaj.org/article/b57444959ab9498ab345cd03d1513660
Publikováno v:
IEEE Access, Vol 11, Pp 61481-61501 (2023)
Many real-world systems can be described by mathematical models that are human-comprehensible, easy to analyze and help explain the system’s behavior. Symbolic regression is a method that can automatically generate such models from data. Historical
Externí odkaz:
https://doaj.org/article/637d94dcaf3d4a5695a4a383af736869
Publikováno v:
IEEE Access, Vol 9, Pp 14148-14158 (2021)
Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accu
Externí odkaz:
https://doaj.org/article/b18fcb26c2a74111a00272b8727a4578
Publikováno v:
IEEE Access, Vol 9, Pp 139697-139711 (2021)
Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function
Externí odkaz:
https://doaj.org/article/b4e237f7c70c40dfbea05c12d51a6c67
Publikováno v:
IEEE Access, Vol 9, Pp 14148-14158 (2021)
IEEE Access, 9
IEEE Access, 9
Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::776513e03447771cf4415632ea6499ba
https://ieeexplore.ieee.org/document/9326312/
https://ieeexplore.ieee.org/document/9326312/
Publikováno v:
IEEE Robotics and Automation Letters, 5(4)
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
instname
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
instname
Relying on static representations of the environment limits the use of mapping methods in most real-world tasks. Real-world environments are dynamic and undergo changes that need to be handled through map adaptation. In this work, an object-based pos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1660e02d43d25ec002106579f03339f
https://doi.org/10.1109/lra.2020.3007402
https://doi.org/10.1109/lra.2020.3007402
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197833
Novel view synthesis is a long-standing problem. In this work, we consider a variant of the problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene, which requir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c976dd4261a3f19f8d4db2168bd3f33
https://doi.org/10.1007/978-3-031-19784-0_12
https://doi.org/10.1007/978-3-031-19784-0_12
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::763ac51c4a84ed7b648d0f677bcc4673
https://doi.org/10.1109/iros51168.2021.9635831
https://doi.org/10.1109/iros51168.2021.9635831
Publikováno v:
Robotics and Autonomous Systems, 135
Autonomous mobile robots are becoming increasingly important in many industrial and domestic environments. Dealing with unforeseen situations is a difficult problem that must be tackled to achieve long-term robot autonomy. In vision-based localizatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7210d31a546ad82acb2fe33b064f0d6
https://hdl.handle.net/10016/34072
https://hdl.handle.net/10016/34072