FP2: Equipping Robotic Foundation Models with Force Control

2026-09-29

AI Summary

This study addresses the limited force control capabilities of robot foundation models in contact-rich scenarios by proposing FP2, a lightweight interface. The method employs an action modulation decomposition architecture that decouples task-level generation from high-frequency force control. It introduces a novel structured force control parameter generation mechanism combining context representation compression with physical feedback prediction, and integrates multimodal historical data to achieve explicit force control. Experimental results demonstrate that FP2 significantly enhances manipulation performance and force control quality across four real-world contact tasks. It outperforms mainstream baseline methods while exhibiting superior generalization capabilities.

Abstract

Robotic foundation models (RFMs) are increasingly capable of general-purpose manipulation, yet reliable physical interaction remains challenging in contact-rich settings. We present FP2, a lightweight downstream interface that equips task-adapted RFMs with explicit force control while preserving their action-generation capability. FP2 adopts an action-regulation decomposition: the task-adapted RFM serves as a foundation policy responsible for task-level action generation, while a high-frequency force control policy focuses solely on interaction regulation. To condition force regulation on the ongoing manipulation, FP2 compresses foundation-policy contextual representations and combines them with wrench and proprioceptive histories to predict structured force-control parameters. We evaluate FP2 with four RFM backbones across four real-world contact-rich manipulation tasks. FP2 consistently improves task performance and force regulation quality over the corresponding foundation policies, while comparing favorably with representative force-aware and force-control baselines. Ablations further show that foundation-policy context and physical feedback are complementary for effective force regulation, while preserving foundation-policy action generation improves both efficiency and novel-object generalization. Project website: http://force-policy.github.io/fp2

Problem

• Robotic Foundation Models
• Force Control
• Contact-rich Manipulation
• Physical Interaction

Innovation

• Robotic Foundation Models
• Force Control
• Action-Regulation Decomposition
• Contact-rich Manipulation
• Contextual Representations