Refine
Year of publication
- 2024 (55)
- 2023 (116)
- 2022 (146)
- 2021 (154)
- 2020 (172)
- 2019 (196)
- 2018 (173)
- 2017 (155)
- 2016 (161)
- 2015 (176)
- 2014 (167)
- 2013 (174)
- 2012 (164)
- 2011 (189)
- 2010 (187)
- 2009 (189)
- 2008 (157)
- 2007 (149)
- 2006 (160)
- 2005 (130)
- 2004 (161)
- 2003 (106)
- 2002 (130)
- 2001 (106)
- 2000 (108)
- 1999 (109)
- 1998 (99)
- 1997 (99)
- 1996 (81)
- 1995 (78)
- 1994 (87)
- 1993 (59)
- 1992 (54)
- 1991 (29)
- 1990 (39)
- 1989 (45)
- 1988 (57)
- 1987 (32)
- 1986 (19)
- 1985 (34)
- 1984 (22)
- 1983 (20)
- 1982 (29)
- 1981 (20)
- 1980 (36)
- 1979 (24)
- 1978 (34)
- 1977 (14)
- 1976 (13)
- 1975 (12)
- 1974 (3)
- 1973 (2)
- 1972 (2)
- 1971 (1)
- 1968 (1)
Institute
- Fachbereich Medizintechnik und Technomathematik (1693)
- Fachbereich Elektrotechnik und Informationstechnik (719)
- IfB - Institut für Bioengineering (624)
- Fachbereich Energietechnik (589)
- INB - Institut für Nano- und Biotechnologien (557)
- Fachbereich Chemie und Biotechnologie (552)
- Fachbereich Luft- und Raumfahrttechnik (497)
- Fachbereich Maschinenbau und Mechatronik (283)
- Fachbereich Wirtschaftswissenschaften (222)
- Solar-Institut Jülich (165)
Language
- English (4935) (remove)
Document Type
- Article (3285)
- Conference Proceeding (1170)
- Part of a Book (195)
- Book (146)
- Doctoral Thesis (32)
- Conference: Meeting Abstract (29)
- Patent (25)
- Other (10)
- Report (10)
- Conference Poster (6)
Keywords
- Biosensor (25)
- Finite-Elemente-Methode (12)
- Einspielen <Werkstoff> (10)
- CAD (8)
- civil engineering (8)
- Bauingenieurwesen (7)
- Blitzschutz (6)
- FEM (6)
- Gamification (6)
- Limit analysis (6)
In this paper, the use of reinforcement learning (RL) in control systems is investigated using a rotatory inverted pendulum as an example. The control behavior of an RL controller is compared to that of traditional LQR and MPC controllers. This is done by evaluating their behavior under optimal conditions, their disturbance behavior, their robustness and their development process. All the investigated controllers are developed using MATLAB and the Simulink simulation environment and later deployed to a real pendulum model powered by a Raspberry Pi. The RL algorithm used is Proximal Policy Optimization (PPO). The LQR controller exhibits an easy development process, an average to good control behavior and average to good robustness. A linear MPC controller could show excellent results under optimal operating conditions. However, when subjected to disturbances or deviations from the equilibrium point, it showed poor performance and sometimes instable behavior. Employing a nonlinear MPC Controller in real time was not possible due to the high computational effort involved. The RL controller exhibits by far the most versatile and robust control behavior. When operated in the simulation environment, it achieved a high control accuracy. When employed in the real system, however, it only shows average accuracy and a significantly greater performance loss compared to the simulation than the traditional controllers. With MATLAB, it is not yet possible to directly post-train the RL controller on the Raspberry Pi, which is an obstacle to the practical application of RL in a prototyping or teaching setting. Nevertheless, RL in general proves to be a flexible and powerful control method, which is well suited for complex or nonlinear systems where traditional controllers struggle.
Solidification of silver-germanium alloys in an amorphous matrix aboard the space station Mir
(1993)
High resolution temperature measurement technique for materials sciences experiments in space
(1998)
The use of transgenic animal models has transformed our knowledge of complex biochemical pathways in vivo. It has allowed disease processes to be modelled and used in the development of new disease prevention and treatment strategies. They can also be used to define cell- and tissue-specific pathways of gene regulation. A further major application is in the area of preclinical development where such models can be used to define pathways of chemical toxicity, and the pathways that regulate drug disposition. One major application of this approach is the humanisation of mice for the proteins that control drug metabolism and disposition. Such models can have numerous applications in the development of drugs and in their more sophisticated use in the clinic.
his report summarizes the results of a workshop on Groupware related task design which took place at the International Conference on Supporting Group Work Group'99, Arizona, from 14 th to 17 th November 1999.
The workshop was addressed to people from different
viewpoints, backgrounds, and domains:
- Researchers dealing with questions of task analysis
and task modeling for Groupware application from an
academic point of view. They may contribute modelbased design
approaches or theoretically oriented
work
- Practitioners with experience in the design and
everyday use of groupware systems. They might refer
to the practical side of the topic: "real" tasks, "real"
problems, "real" users, etc.