具身开发者社区

外观

论文arXiv 2610.1811815 天前

ForeTac：用于生成式机器人策略的预测性接触引导 ​

ForeTac通过预测并评估候选动作的触觉后果来引导生成式策略，并在四个真机接触操作任务上验证。

AI 整理
  • 本体 SDK 与控制
  • 数据与采集
  • 具身模型

原文链接：ForeTac: Predictive Contact Guidance for Generative Robot Policies（arXiv 2610.18118 · 发布日期：2026-10-13）

ForeTac: Predictive Contact Guidance for Generative Robot Policies

ForeTac通过预测并评估候选动作的触觉后果来引导生成式策略，并在四个真机接触操作任务上验证。

核心要点 ​

  • 视觉相似动作可能导致失触、卡滞、滑移或损伤，触觉反馈可能来得过晚。
  • 框架采用表示-预测-评估-引导循环，先编码当前触觉再预测动作后果。
  • 相较视觉Diffusion Policy，任务成功率36.3%升至71.3%，CSR 20.0%升至66.3%。
  • 组件分析支持触觉表示和动作条件前瞻，并显示预测触觉保持接触质量排序。

验证范围与局限：验证范围为四个真机任务：平面和曲面擦拭、刷卡、易碎物体抓取。

英文摘要 (Abstract) ​

Visually similar actions can produce contact loss, jamming, slippage, or irreversible damage, while tactile feedback may arrive after a critical transition. Contact-rich manipulation therefore requires generative policies to anticipate and evaluate whether candidate actions will produce desirable contact outcomes, then adjust action generation before execution. We present ForeTac, a predictive contact-guidance framework organized as a represent-predict-evaluate-guide loop. ForeTac encodes the current tactile state, predicts the tactile consequences of a candidate action sequence, and evaluates the predicted trajectory using a contact-quality objective learned from successful and failed physical interactions. At deployment, its gradient propagates through the tactile predictor to guide action generation while the pretrained model parameters remain frozen. We evaluate ForeTac on four real-robot tasks (planar and curved-surface wiping, card swiping, and fragile-object grasping) with diffusion and flow-matching policies. Across these tasks, ForeTac raises the average task success rate from 36.3% to 71.3% and the average contact success rate (CSR) from 20.0% to 66.3% compared with vision-only Diffusion Policy. Component analyses support the tactile representation and action-conditioned foresight, and show that predicted touch preserves contact-quality ordering. Project page: https://foretac.github.io/.

作者：Zhiyuan Chen, Shuai Chen, Haoran Zhou, Yizhe Zhao, Kaiyuan Yang, Zhixiang Duan, Shaoqing Xu, Ran Cao, Diyun Xiang, Yangwei You

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.18118：ForeTac: Predictive Contact Guidance for Generative Robot Policies访问 2026-10-21