Steerable and Reactive Grasping Through Modular Design with a Three-Point Interface

2026-09-21

AI Summary

该研究通过三接触点接口设计，结合几何推理、模型控制和强化学习方法，解决了灵巧抓取中的定位、接近和稳定接触问题。

Abstract

Dexterous grasping requires deciding where to grasp, reaching the target, and maintaining stable contact. We connect these stages through a compact three-point interface that separates global geometric reasoning from local contact control. Given object geometry and optional language commands, our framework samples contact triples from a precomputed grasp-affordance heatmap. A model-based reactive controller tracks the object, avoids collisions, and guides the hand toward the selected contacts. In the final centimeters, a Reinforcement Learning (RL) policy uses proprioceptive feedback to refine and stabilize the grasp despite reaching and perception errors. It observes only finger joint states and its recent actions, with no target points, visual observations, or object geometry, so a single policy is shared across objects and grasp configurations. In simulation, we compare grasp-and-lift success against squeeze and end-to-end baselines, characterize reaching convergence, and demonstrate grasp steering; hardware demonstrations on two training objects and one unseen object illustrate the full pipeline. Our modular framework uses geometry to guide the reach and local feedback to secure the grasp.

Problem

• Grasping
• Reactive Control
• Modular Design

Innovation

• three-point interface
• grasp-affordance heatmap
• model-based reactive controller
• Reinforcement Learning policy
• proprioceptive feedback