Monday, September 20, morning Autonomous robots that can assist humans in situations of daily life have been a long standing vision of artificial intelligence, robotics, and cognitive sciences. A first step towards this goal is to create robots that can learn tasks triggered by environmental context or higher level instruction. Hence, it is essential that more machine learning researchers dare to face the challenge of robot learning. To enable scientists an easier entry into this field, this tutorial will present an overview over the state of the art. It will cover both real-world problems and research opportunities for a machine learning researchers who are willing to enter the area of robot learning. Empirical evaluations on a several robot systems illustrate the effectiveness and applicability of the presented methods for anthropomorphic robots. |
