OpenDR is a project that aims to achieve the development of the non-proprietary toolkit, in this case it refers to a set of deep learning software functions for core robotic functionality, harnessing deep learning to provide advanced perception and cognition abilities. This way, they will be able to apply the general requirements of robotic applications in areas of application such as healthcare, agri-food and agile production. This project will also demonstrate how to apply the robotics applications to software libraries and to link it to the operating environment (ROS).
Furthermore, the result of this work will focus on enabling cooperative human-robot interaction as well as the development of cognitive mechatronics, which contributes alongside the cognitive systems to two other core technologies beyond AI and Cognition.
PAL Robotics will participate in this project integrating DL algorithms, however, it will be mainly based on and applied in healthcare. The robot for this project will be TIAGo, and this robotic platform will serve as an end-user assistant by receiving visitors and taking an object and bringing it. To do all that, TIAGo needs to have incorporated human presence recognition, activities and vocal instructions as well as emotional states to enable a person-centric human interaction.