Learning Dexterous Manipulation Policies from Experience and Imitation

Understand

We explore learning-based approaches for feedback control of a dexterous five-finger hand performing non-prehensile manipulation.

• First, we learn local controllers that are able to perform the task starting at a predefined initial state.
• These controllers are constructed using trajectory optimization with respect to locally-linear time-varying models learned directly from sensor data.
• In some cases, we initialize the optimizer with human demonstrations collected via teleoperation in a virtual environment.