The document describes a study where a robot learns social affordances through interactions with humans and objects, and uses the learned affordances to make multi-step plans. The robot is equipped with sensors to perceive its environment and humans within it. It interacts with objects and humans, and learns affordances represented as relationships between perceptual features, behaviors, and effects. The learned affordances are used by the robot to plan sequences of behaviors to achieve demonstrated goals by getting assistance from humans when needed. The study shows that robots can learn social affordances in the same way as physical affordances, and use this to plan interactions with humans.