CHAINS | SYNERGY | MEGALOPOLIS | UNBIAS
Computer Science and Automation together to create Techno-Human systems
Develop autonomous system according to user needs and preferences, enabling autonomous adaptation to characteristics, attributes, or features unique to individuals.
This project aims at contributing to these challenges by proposing new modelling and control strategies for autonomous systems considering users in the design and evaluation process. Our objectives are more specifically to:
Devise low-complexity learning and data-driven modeling strategies. Often, a large amount of data is available, and it is mandatory to extract only the information crucial to deriving a reliable model of reduced complexity for analysis or control purposes;
Develop safe reinforcement learning control strategies. The features of reinforcement learning make it a relevant candidate for controlling dynamical systems due to its ability to adapt control actions to system variations. However, endowing systems controlled by reinforcement learning with stability and robustness guarantees remains a largely open question;
Define a model-based solutions that, by estimation of unmeasurable variables, can enrich learning abilities;
Define procedures for the development and evaluation of autonomous systems, taking particular needs into account;
Develop a decision support architecture that accurately detects and efficiently responds to safety and security problems for autonomous systems; and
Develop appropriate sensor technology, exploit estimation techniques including unknown input observers, derive precise real-time physical and data-driven based dynamic models, and implement control strategies exploring artificial intelligence methods are key elements for achieving adaptive viable implementations. Strategies that can meet individual-specific requirements for assistive to autonomous systems are still an open research field.
Members
Adenilso da Silva Simão
André P.L.F. Carvalho
Antoine Gallais
Cássio Guimarães Lopes
Catherine Dezan
David Espes
Hamza Ouarnoughi
Jamal Daafouz
João Cavalcanti Santos
José Henrique de M. Goulart
Kalinka R.L. J. C. Branco
Kamila Rios Rodrigues
Márcia da Costa Peixoto
Marie Chabert
Oswaldo L. V. Costa
Phillip M. S. Burt
Romain Postoyan
Thierry-Marie Guerra
Youcef Imine
We welcome new research topics and axis for our project.