Adaptation of Task Goal States from Prior Knowledge
This work addresses flexibility in robot task execution, but it appears incremental as it builds on existing task demonstration frameworks.
The paper tackles the problem of enabling robots to adapt task goal states from prior knowledge, allowing them to target easier-to-execute goals from a single demonstration, and presents experiments on creating environment variations and execution plans.
This paper presents a framework to define a task with freedom and variability in its goal state. A robot could use this to observe the execution of a task and target a different goal from the observed one; a goal that is still compatible with the task description but would be easier for the robot to execute. We define the model of an environment state and an environment variation, and present experiments on how to interactively create the variation from a single task demonstration and how to use this variation to create an execution plan for bringing any environment into the goal state.