外观
论文arXiv 2609.3743329 天前
FP2框架赋予机器人基础模型显式力控能力
本文由 AI 根据公开内容整理，可能有误，请以原文为准：FP2: Equipping Robotic Foundation Models with Force Control（arXiv 2609.37433）
核心内容
针对机器人基础模型（RFMs）在接触密集场景中物理交互可靠性不足的瓶颈，研究团队提出FP2轻量级下游接口。该方法在不破坏RFM原有动作生成能力的前提下，为其注入显式力控制能力。实验覆盖4种RFM骨干网络及4项真实世界接触丰富操作任务，结果表明FP2在任务成功率与力调节精度上均优于原始基础策略，且性能对标甚至超越现有的力感知与力控制基线方案。
FP2核心采用动作-调节解耦架构：任务适配RFM作为基础策略负责高层动作生成，高频力控策略专注交互调节。系统通过压缩基础策略上下文表征，融合力矩（wrench）与本体感知历史数据，预测结构化力控参数以条件化调节力输出。消融实验证实，基础策略上下文与物理反馈具有互补性，保留基础策略动作生成机制不仅提升了样本效率，还显著增强了模型对未见物体的泛化能力。
关键看点
- 解耦架构：将任务级动作生成与高频力调节分离，RFM负责规划，独立力控策略基于上下文与传感器历史执行交互调节
- 多模态融合：压缩基础策略上下文表征并结合wrench及本体感知历史，预测结构化力控参数实现自适应物理交互
- 实证性能：在4种RFM骨干与4项真实接触任务中验证，力调节质量与任务表现优于基础策略及代表性力控基线
- 泛化优势：保留基础策略动作生成能力，消融实验证明其与物理反馈互补，有效提升样本效率与新物体泛化水平
工程与产业观察
FP2为具身大模型落地接触密集场景提供了工程化解法。其动作-调节解耦范式解决了端到端模型力控不稳的痛点，无需重训即可复用现有RFM。这种轻量化插件式设计降低了力觉集成门槛，对精密装配、柔性抓取等需精确力交互的工业与服务机器人应用具有重要参考价值。
英文摘要 (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
作者：Hongjie Fang, Shirun Tang, Junjian Hu, Shidong Zhang, Derek Zhang, Linhao Chen, Dehai Li, Mingyu Mei, Wanxi Liu, Cewu Lu, Shiquan Wang
来源
本页事实对应的公开页面，以原文为准。