Differentiable Object Pose Connectivity Metrics for Regrasp Sequence Optimization
For robotic manipulation, this work provides a novel method to optimize regrasp sequences, addressing a key bottleneck in discrete search for grasp feasibility.
This paper tackles regrasp planning for object transfer when a single pick-and-place is insufficient. It proposes a differentiable pose connectivity metric using an Energy-Based Model to enable gradient-based optimization of intermediate poses, achieving improved planning robustness and generalization to unseen grasps and cross-end-effector transfer.
Regrasp planning is often required when one pick-and-place cannot transfer an object from an initial pose to a goal pose while maintaining grasp feasibility. The main challenge is to reason about shared-grasp connectivity across intermediate poses, where discrete search becomes brittle. We propose an implicit multi-step regrasp planning framework based on differentiable pose sequence connectivity metrics. We model grasp feasibility under an object pose using an Energy-Based Model (EBM) and leverage energy additivity to construct a continuous energy landscape that measures pose-pair connectivity, enabling gradient-based optimization of intermediate object poses. An adaptive iterative deepening strategy is introduced to determine the minimum number of intermediate steps automatically. Experiments show that the proposed cost formulation provides smooth and informative gradients, improving planning robustness over other alternatives. They also demonstrate generalization to unseen grasp poses and cross-end-effector transfer, where a model trained with suction constraints can guide parallel gripper grasp manipulation. The multi-step planning results further highlight the effectiveness of adaptive deepening and minimum-step search.