Failure is Not an Option: Policy Learning for Adaptive Recovery in Space Operations
IEEE Robotics and Automation Letters, pp. 1639-1646, 2018.
This letter considers the problem of how robots in long-term space operations can learn to choose appropriate sources of assistance to recover from failures. Current assistant selection methods for failure handling are based on manually specified static lookup tables or policies, which are not responsive to dynamic environments or uncerta...More
Full Text (Upload PDF)
PPT (Upload PPT)