Our recent work about "Interest-Based Exploration toward Versatile Cognitive Robots" by Rania Rayyes and Jochen Steil will be presented at Robotics: Science and Systems (RSS): Women in Robotics (WiR) workshop. More complex robots are getting involved in our daily life e.g., robotic applications for household. These robots in an open-ended environment should be able to adapt to the time dependent changes, learn new skills, handle tasks flexibly and explore new areas. Hence, online intrinsically motivated goal-directed learning methods are the most convenient option as per-programmed robots and traditional control schemes do not solve anymore handling daily tasks flexibility and adaptability. In such high dimensional open-ended environments, it is important to learn the robots limits as well as to determine what to learn since sampling the full workspace in lifelong time is not feasible. Here our recent work tackles these challenges. We propose “Associative Goal Babbling Interest-Based Exploration” inspired by the versatility of human learning. The proposed learning scheme is able to learn forward and inverse kinematics simultaneously, the robot is driven by intrinsic motivation to choose where to explore based on its interests and its acquired knowledge.