Inferring the Geometric Nullspace of Robot Skills from Human Demonstrations
This work addresses the challenge of transferring human skills to robots in a flexible and intuitive way, though it appears incremental as it builds on existing geometric constraint models.
The paper tackles the problem of learning robot skills from human demonstrations by modeling them as geometric nullspaces, enabling execution across different robots and dynamic environments. The result is a framework that successfully learns and executes these skills, demonstrated on a simulated industrial robot and the iCub humanoid robot.
In this paper we present a framework to learn skills from human demonstrations in the form of geometric nullspaces, which can be executed using a robot. We collect data of human demonstrations, fit geometric nullspaces to them, and also infer their corresponding geometric constraint models. These geometric constraints provide a powerful mathematical model as well as an intuitive representation of the skill in terms of the involved objects. To execute the skill using a robot, we combine this geometric skill description with the robot's kinematics and other environmental constraints, from which poses can be sampled for the robot's execution. The result of our framework is a system that takes the human demonstrations as input, learns the underlying skill model, and executes the learnt skill with different robots in different dynamic environments. We evaluate our approach on a simulated industrial robot, and execute the final task on the iCub humanoid robot.