Differentiable Object Pose Connectivity Metrics for Regrasp Sequence Optimization

arXiv cs.RO / 4/17/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses regrasp planning by optimizing intermediate object poses when a single pick-and-place cannot reach the goal while preserving grasp feasibility.
It introduces differentiable connectivity metrics for pose sequences by modeling grasp feasibility with an Energy-Based Model (EBM) and using energy additivity to create a continuous, optimizable energy landscape.
The method enables gradient-based optimization of intermediate poses, replacing brittle discrete search over intermediate states.
It proposes an adaptive iterative deepening strategy to automatically infer the minimum number of intermediate regrasp steps needed.
Experiments indicate smoother, more informative gradients, improved robustness over alternative formulations, and strong generalization—including unseen grasp poses and cross-end-effector transfer (e.g., suction-trained models guiding parallel gripper manipulation).

Abstract

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.