Every year, the Robocup@Home competition challenges teams and robots'\nabilities. In 2020, the RoboCup@Home Education challenge was organized online,\naltering the usual competition rules. In this paper, we present the latest\ndevelopments that lead the RoboBreizh team to win the contest. These\ndevelopments include several modules linked to each other allowing the Pepper\nrobot to understand, act and adapt itself to a local environment. Up-to-date\navailable technologies have been used for navigation and dialogue. First\ncontribution includes combining object detection and pose estimation techniques\nto detect user's intention. Second contribution involves using Learning by\nDemonstrations to easily learn new movements that improve the Pepper robot's\nskills. This proposal won the best performance award of the 2020 RoboCup@Home\nEducation challenge.\n