Constraint-based movement representation grounded in geometric features

Robots that are to master everyday manipulation tasks need both: The ability to reason about actions, objects and action effects, and the ability to perform sophisticated movement control. To bridge the gap between these two worlds, we consider the problem of connecting symbolic action representation with strategies from motion control engineering. We present a system using the task function approach [1] to define a common symbolic movement description language which defines motions as sets of symbolic constraints. We define these constraints using geometric features, like points, lines, and planes, grounding the description in the visual percepts of the robot. Additionally, we propose to assemble task functions by stacking 1-D feature functions, which leads to a modular movement specification. We evaluate and validate our approach on the task of flipping pancakes with a robot, showcasing the robustness and flexibility of the proposed movement representation.