跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 01:29 — 2026-11-23 01:29(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
版本更新 · v2arXiv:2610.14335

PILOT: Guiding Long-Horizon World-Model Planning for Robot Manipulation with Imagined Subgoals and Policy Priors

Yang Liu, Hanchen Cui, Karthik Desingh

原文摘要

Latent world-model planning has shown promising results in goal-conditioned robotic manipulation, but remains challenging for long-horizon planning due to limited temporal guidance and inefficient action search. A distant goal image offers little guidance for preparatory actions, capturing intermediate subgoal images by hand is impractical, and uninformed sampling makes action search inefficient. We propose PILOT (Policy-Initialized Local Optimization with Temporal subgoals), which brings two foundation models into latent world-model planning: a video model turns a language instruction into visual subgoals, and a vision-language-action policy initializes the cross-entropy method (CEM). CEM refines action sequences toward each subgoal with an action-conditioned world model, and no goal image is needed at test time. With both models fine-tuned on 40 demonstrations, PILOT achieves 68.8% success on four real UR5e tasks, compared with 55.0% without policy initialization, 13.8% for policy-only execution, and 0.0% for direct final-goal planning. In simulation, PILOT exceeds direct execution of the same policy by 30 percentage points on long Push-T tasks and by 22 percentage points on LIBERO-10. Subgoals and the policy prior are complementary: better subgoals and stronger priors each raise success, and even a weak policy that succeeds alone on only 3.3% of medium Push-T tasks is an effective prior.

cs.RO