The improvements brought by this technique enables robots to perform difficult tasks such as grabbing or reaching targets . This way of learning is capital totransfer the task from simulation to the real world since the only externalsource of information for the robot in real life is video . In this paper, westudy how to limit the time taken for training a robotic arm with 6 Degrees OfFreedom (DOF) to reach a ball from scratch by assembling a pipeline asefficient as possible . The pipeline is divided into two parts: the first one is to capture the relevant information from the relevant video with a Computer Visionalgorithm . The second one studies how to train faster a Deep ReinforcementLearning algorithm in order to make the robotic arm reach the target in front of him . Follow this link to find videos and plots in higher resolution in a higher resolution. The

Author(s) : Maxence Mahe, Pierre Belamri, Jesus Bujalance Martin

Links : PDF - Abstract

Code :

Keywords : pipeline - reach - real - video - relevant -

Leave a Reply

Your email address will not be published. Required fields are marked *