Skip to Main content Skip to Navigation
New interface

Programmation de cobots : de l'apprentissage de trajectoires à leur acceptabilité

Abstract : Robots, new machines in our daily lives, diversify. Recent progress has made the rising of cobots possible. Cobots are robots which collaborate with human beings. Contrary to traditional robots, this new type of robot requires the expertise of an operator to run. The Learning from Demonstration creates an original way of programming. The operator can manipulate the robot’s arm in order to teach it the movement to realize. The present thesis proposes an improvement of this learning through these three axes: the data processing, the learning, and the acceptability. Before being used by the learning, data is retrieved during the kinesthetic demonstration, then temporally aligned, and filtered to improve its quality. A novel learning algorithm with weighted data is proposed with generic software architecture allowing it to run on multiple robotics platforms. Finally, the acceptability of the Programming by Demonstration is evaluated with an experiment whose participants are potentially future users of cobots. The impact of the anthropomorphism is also considered. The different outcomes permit to consider the introduction of cobots in the industry of the future: from the data acquisition to the learning while evaluating the acceptability as well as the understanding of this type of programming by users.
Document type :
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Thursday, September 22, 2022 - 12:12:50 PM
Last modification on : Saturday, September 24, 2022 - 3:07:47 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03783711, version 1


Amélie Legeleux. Programmation de cobots : de l'apprentissage de trajectoires à leur acceptabilité. Automatique / Robotique. Université de Bretagne Sud, 2022. Français. ⟨NNT : 2022LORIS629⟩. ⟨tel-03783711⟩



Record views


Files downloads