Tese de doutoramento em Engenharia Electrotécnica e de Computadores, no ramo de especialização Automação e Robótica, apresentada ao Departamento de Engenharia Electrotécnica e de Computadores da Faculdade de Ciências e Tecnologia da Universidade de Coimbra ; The development of intelligent and autonomous robots is envisioned as a breakthrough in science and is expected to have significant impact in the future of our society. Scientists estimate that in the future, robots will be able to coexist in society with humans. A wave of intelligent robots will be capable to autonomously perceive the environment, follow a set of contextual social rules, and make their own decisions into fulfilling several tasks, relieving them from humans. Moreover, a set of cognitive capabilities will allow them to reconfigure themselves to new tasks, learn new actions, reason about unknown reactions and learn new social rules. The challenge is that robots have to cope with a limited prior knowledge about themselves and the environment, while operating without supervision in an uncertain world. To address these challenges, currently robotic system as developed towards specific scenarios, within well defined environments and properties. This fact, makes it difficult for them to deal with unknown situations, where its perception is subject to uncertainty and noise. In our thesis, we present a set of novel methodologies and concepts that enable robots to comprehensively interpret human motion and extend such knowledge via hierarchical analysis of different types of information. The proposed methods in this thesis address the following main three topics: (1) Defining a model which can robustly infer different types of information from human motion, using a generalizable grounding language; (2) Encoding the unique expressive properties of each person’s motion, so as to develop action invariant motion signatures towards a person recognition framework; (3) Develop a system’s action memory, which can store and retrieve action generalized ...
Laban Movement Analysis: A Bayesian Computational Approach to Hierarchical Motion Analysis and Learning
04.04.2014
101320442
Hochschulschrift
Elektronische Ressource
Englisch
DDC: | 629 |
Laban movement analysis to classify emotions from motion [10696-9]
British Library Conference Proceedings | 2018
DataCite | 1911
|Robot Choreography: The Use of the Kinetography Laban System to Notate Robot Action and Motion
BASE | 2017
|Hierarchical segmentation-based approach to motion analysis
British Library Online Contents | 1993
|Risk analysis of animal–vehicle crashes: a hierarchical Bayesian approach to spatial modelling
Taylor & Francis Verlag | 2016
|