ECHORD: Fidelio Experiment
Responsible:
EU Research FP7
DEIB Role: Partner
Start date: 2009-01-01
Length: 60 months
Project abstract
FIDELIO is one of the experiments founded by the FP7 project ECHORD, which aims to investigate the feasibility and the related advantages of an innovative approach to autonomously generate a robot program “learning from observation”.
In this new paradigm, the information coming from a variety of observations is transformed into an abstract representation of the task. By using such information, and exploiting the abstraction capabilities of a suitable cognitive system, the robot is able to autonomously generate a program to reproduce the task, even in an environment which is different from the one observed during the learning phase. The approach is applied to an industrial application scenario, exemplified by a fixtureless wheel deburring task.
In this new paradigm, the information coming from a variety of observations is transformed into an abstract representation of the task. By using such information, and exploiting the abstraction capabilities of a suitable cognitive system, the robot is able to autonomously generate a program to reproduce the task, even in an environment which is different from the one observed during the learning phase. The approach is applied to an industrial application scenario, exemplified by a fixtureless wheel deburring task.
Project results
Scientific publications:
- L. Bascetta, G. Ferretti, G. Magnani, P. Rocco. Walk-through programming for robotic manipulators based on admittance control, Robotica, United Kingdom, Vol. 31, No. 7, October 2013, pp. 1143-1153.
- A.M. Ghalamzan E., L. Bascetta, M. Restelli, P. Rocco. Estimating a mean-path from a set of 2-D curves. IEEE International Conference on Robotics and Automation ICRA 2015. Seattle, USA, Maj 2015.
- L. Bascetta, G. Ferretti, A. Ghalamzan, G. Magnani, M. Pirotta, M. Restelli, P. Rocco. Sistema autonomo di sbavatura robotizzata, Motion Control 2013, Milan, Italy, November 2013, pp. 1-10.
