This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
research:projects [2019/10/29 12:29] Justus Piater |
research:projects [2020/03/05 11:52] Alejandro Agostini |
||
---|---|---|---|
Line 2: | Line 2: | ||
===== Current Projects ===== | ===== Current Projects ===== | ||
+ | |||
+ | **SEAMLESS LEVELS OF ABSTRACTION FOR ROBOT COGNITION** - (FWF Lise Meitner Project, 2019-2021): The project seeks to develop a robotic cognitive architecture that overcomes the difficulties to integrate different levels of abstraction (e.g. AI and robotic techniques) for task plan and execution in unstructured scenarios. The project hinges on a unified approach that permits searching for feasible solutions at all the levels of abstractions simultaneously, where symbolic descriptions are only evaluated from physical parameters to generate feasible solutions for new task execution. | ||
**OLIVER** - Open-Ended Learning for Interactive Robots (EUREGIO IPN, 2019-2022): We would like to be able to teach robots to perform a great variety of tasks, including collaborative tasks, and tasks not specifically foreseen by its designers. Thus, the space of potentially-important aspects of perception and action is by necessity extremely large, since every aspect may become important at some point in time. Conventional machine learning methods cannot be directly applied in such unconstrained circumstances, as the training demands increase with the sizes of the input and output spaces. | **OLIVER** - Open-Ended Learning for Interactive Robots (EUREGIO IPN, 2019-2022): We would like to be able to teach robots to perform a great variety of tasks, including collaborative tasks, and tasks not specifically foreseen by its designers. Thus, the space of potentially-important aspects of perception and action is by necessity extremely large, since every aspect may become important at some point in time. Conventional machine learning methods cannot be directly applied in such unconstrained circumstances, as the training demands increase with the sizes of the input and output spaces. |