Counterexample-Guided Repair for Symbolic-Geometric Action Abstractions
This addresses the difficulty for robotics experts in creating accurate symbolic abstractions, enabling more practical robot planning, though it is incremental as it builds on existing TMP methods.
The paper tackles the challenge of constructing symbolic abstractions for robot actions in integrated Task and Motion Planning by proposing an automatic abstraction repair approach that uses constrained polynomial zonotopes and symbolic edits to improve models from observations, demonstrating it can enhance realistic action abstractions with a handful of observations.
Integrated Task and Motion Planning (TMP) provides a promising class of approaches for solving robot planning problems with intricate symbolic and geometric constraints. However, the practical usefulness of TMP planners is limited by their need for symbolic abstractions of robot actions, which are difficult to construct even for experts. We propose an approach to automatically construct and continuously improve a symbolic abstraction of a robot action via observations of the robot performing the action. This approach, called automatic abstraction repair, allows symbolic abstractions to be initially incorrect or incomplete and converge toward a correct model over time. Abstraction repair uses constrained polynomial zonotopes (CPZs), an efficient non-convex set representation, to model predicates over joint symbolic and geometric state, and performs an optimizing search over symbolic edit operations to predicate formulae to improve the correspondence of a symbolic abstraction to the behavior of a physical robot controller. In this work, we describe the aforementioned predicate model, introduce the symbolic-geometric abstraction repair problem, and present an anytime algorithm for automatic abstraction repair. We then demonstrate that abstraction repair can improve realistic action abstractions for common mobile manipulation actions from a handful of observations.