Visual predictive control of robotic arms with overlapping workspace

Emile Le Flecher (1) , Adrien Durand-Petiteville (2) , Viviane Cadenat (1) , Thierry Sentenac (3)

1 LAAS-RAP - Équipe Robotique, Action et Perception
2 UFPE - Universidade Federal de Pernambuco [Recife]
3 ICA - Institut Clément Ader

This paper deals with multi-arms fruits picking in orchards. More specifically, the goal is to control the arms to approach the fruits position. To achieve this task a VPC strategy has been designed to take into account the dynamic of the environment as well as the various constraints inherent to the mechanical system, visual servoing manipulation and shared workspace. Our solution has been evaluated in simulation using on PR2 arms model. Different models of visual features prediction have been tested and the entire VPC strategy has been run on various cases. The obtained results show the interest and the efficiency of this strategy to perform a fruit picking task.

Mots clés: Agricultural robotics; multi-arms; Non-linear Model Predictive Control; Image Based Visual Servoing

Domaines: Automatique / Robotique

Emile Le Flecher, Adrien Durand-Petiteville, Viviane Cadenat, Thierry Sentenac. Visual predictive control of robotic arms with overlapping workspace. ICINCO 2019 - 16th International Conference on Informatics in Control, Automation and Robotics, Jul 2019, Prague, Czech Republic. pp.130-137, ⟨10.5220/0008119001300137⟩. ⟨hal-03193387⟩