Inverse Manipulation through Symbolic Planning and Residual Operator Learning
For robotic manipulation tasks, this work addresses the challenge of inverting continuous interaction dynamics by integrating symbolic and learning-based approaches.
The paper presents a hybrid framework for inverse manipulation that combines symbolic planning with residual operator learning, achieving physically grounded inverse skills from approximate symbolic inverses. On the ManiSkill3 PushCube task, the method refines cube pose to satisfy inverse predicates.
Inverting a robotic task requires more than reversing symbolic state transitions or rewinding motor trajectories. In robot manipulation tasks, symbolic inverse plans often fail to fully restore the effects of forward executions under continuous interaction dynamics. We present a hybrid framework for inverse manipulation that derives inverse-skill objectives from STRIPS-like operators automatically extracted from demonstrations through soft geometric predicates. For each extracted operator, we construct an inverse restoration objective that preserves preconditions, restores delete effects, and negates add effects. A task planner first attempts to satisfy this objective using available action primitives. Unresolved symbolic predicates then induce a residual operator learning problem solved through Reinforcement Learning (RL). We evaluate the framework on the ManiSkill3 PushCube task. For a forward pushing skill, the symbolic inverse performs a coarse pick-and-place restoration, while a residual Soft Actor-Critic policy refines the cube pose to satisfy the remaining inverse predicates. Our results show that predicate-derived residual control can turn an approximate symbolic inverse into a physically grounded inverse skill.