Refine
Departments, institutes and facilities
- Fachbereich Informatik (80)
- Fachbereich Wirtschaftswissenschaften (69)
- Fachbereich Ingenieurwissenschaften und Kommunikation (65)
- Fachbereich Angewandte Naturwissenschaften (64)
- Fachbereich Sozialpolitik und Soziale Sicherung (59)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (53)
- Institut für funktionale Gen-Analytik (IFGA) (36)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (27)
- Institut für Cyber Security & Privacy (ICSP) (23)
- Institut für Verbraucherinformatik (IVI) (23)
Document Type
- Article (150)
- Conference Object (112)
- Part of a Book (45)
- Book (monograph, edited volume) (25)
- Preprint (15)
- Working Paper (13)
- Contribution to a Periodical (11)
- Report (9)
- Video (8)
- Research Data (6)
Year of publication
- 2021 (416) (remove)
Keywords
- Lehrbuch (7)
- DGQ (6)
- Melcher (6)
- Augmented Reality (4)
- Machine Learning (4)
- Usable Security (4)
- Big Data Analysis (3)
- Digitalisierung (3)
- Grundwerkzeug des Qualitätsmanagements (3)
- Kenya (3)
Representation and Experience-Based Learning of Explainable Models for Robot Action Execution
(2021)
For robots acting in human-centered environments, the ability to improve based on experience is essential for reliable and adaptive operation; however, particularly in the context of robot failure analysis, experience-based improvement is only useful if robots are also able to reason about and explain the decisions they make during execution. In this paper, we describe and analyse a representation of execution-specific knowledge that combines (i) a relational model in the form of qualitative attributes that describe the conditions under which actions can be executed successfully and (ii) a continuous model in the form of a Gaussian process that can be used for generating parameters for action execution, but also for evaluating the expected execution success given a particular action parameterisation. The proposed representation is based on prior, modelled knowledge about actions and is combined with a learning process that is supervised by a teacher. We analyse the benefits of this representation in the context of two actions – grasping handles and pulling an object on a table – such that the experiments demonstrate that the joint relational-continuous model allows a robot to improve its execution based on experience, while reducing the severity of failures experienced during execution.
İnsanlar yeryüzünün doğal kaynaklarını onun bunları yenileyebileceğinden daha hızlı tüketmektedirler. İnsanların bu tutumlarının bedelini gelecek kuşaklar ödeyeceklerdir. Gelecek kuşaklara bu bedeli ödetmemek için artık parasal kârları ençoklamak, niceliksel olarak büyümek ve bolluk yaratmak doğrultusunda işleyen şimdiki ekonomik faaliyetleri bir başka biçime dönüştürmek kaçınılmazdır. Peren Teoremi göstermektedir ki Dünya örneğinde de olduğu gibi kapalı bir sistem doğal kaynak tüketimi eş düzeyde bir doğal kaynak üretimi ile yaşayabilir. Üretim ile tüketim arasındaki denge çok uzun bir süre bozulursa gezegen doğal bir ölüm ile karşılaşır. Bunu sağlamak üzere Dünya üzerinde yaşayan ve/veya dünya sayesinde yaşayan tüm insanların kişi başına doğal kaynak tüketimlerini artan küresel nüfusla orantılı bir biçimde azaltmak gerekir.
In recent years, there has been an increasing interest in psychological need satisfaction and its role in promoting optimal functioning. The DRAMMA model integrates existing need and recovery models to explain why leisure is connected to optimal functioning (i.e., high well-being and low ill-being). It encompasses six psychological needs: detachment, relaxation, autonomy, mastery, meaning, and affiliation (DRAMMA). While the individual needs of the DRAMMA model have been previously shown to relate to different aspects of optimal functioning, a longitudinal study examining the entire model has not been conducted before. In this longitudinal field study covering leisure and work episodes, we tested the within-person reliability and (construct and criterion) validity of the operationalization of the DRAMMA model in a sample of 279 German employees. Participants filled out measures of DRAMMA need satisfaction and optimal functioning at five measurement times before, during, and after vacation periods in 2016 and 2017. The six-factor model showed good fit to the data. In the multilevel models, relaxation, detachment, autonomy, and mastery had the most consistent within-person effects on optimal functioning, while the relationships between optimal functioning, meaning, and affiliation were considerably weaker. In conclusion, DRAMMA need satisfaction can aid and nurture employees’ optimal functioning.