Do What I Want, Not What I Did: Imitation of Skills by Planning Sequences of Actions
This addresses the problem of robot adaptation to new environments for tasks like assembly, though it appears incremental as it builds on existing learning-from-demonstration and planning methods.
The paper tackles the problem of enabling robots to perform tasks in new environments by learning from demonstrations, proposing an approach that grounds actions from expert data and uses sampling-based motion planning to select sequences of high-level actions. The result is demonstrated in a magnetic structure assembly task, showing the robot can intelligently choose actions in different workspaces and with obstacles.
We propose a learning-from-demonstration approach for grounding actions from expert data and an algorithm for using these actions to perform a task in new environments. Our approach is based on an application of sampling-based motion planning to search through the tree of discrete, high-level actions constructed from a symbolic representation of a task. Recursive sampling-based planning is used to explore the space of possible continuous-space instantiations of these actions. We demonstrate the utility of our approach with a magnetic structure assembly task, showing that the robot can intelligently select a sequence of actions in different parts of the workspace and in the presence of obstacles. This approach can better adapt to new environments by selecting the correct high-level actions for the particular environment while taking human preferences into account.