跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25589 · v1

GraF-VTA: Neuro-Symbolic Trajectory Generation from Vision and Temporal Logic via Graph-Based Fusion

首次提交 2026-11-19 14:32
版本更新 2026-11-19 14:32
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

Robotic planning from visual observations and signal temporal logic (STL) requires grounding task requirements in scene evidence while adapting plans to execution feedback. We present GraF-VTA, a graph-based framework that extends Vision-TL-Action with structured task representations, causal observation history, and closed-loop trajectory generation. Bidirectional cross-attention fuses STL syntax tokens with visual features, while an optional frozen automaton embedding supplies complementary untimed task structure. A temporal pyramid preserves detailed current observations and compresses older frames to provide recent execution context. Conditioned on these features and robot state, a flow-matching model generates plans whose action prefixes are executed before replanning from refreshed observations. Across five simulation environments, the single-graph configuration achieves higher open-loop Success@KK than TeLoGraF and Vision-TL-Action on four environments at the reported budgets K≥16K\geq16. On Panda, matched-update ablations increase Success@256 from 53.91\% without observation history to 62.50\% with pyramid memory. In closed-loop Dubins evaluation, it reaches 64.06\% Success@1024, compared with 12.50\% for adapted S-MSP and 27.34\% for adapted Logic-VLA. These results support combining structured visual conditioning with observation history and replanning to improve coverage of STL-satisfying trajectories.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 14:32 · 最新观测版本

GraF-VTA: Neuro-Symbolic Trajectory Generation from Vision and Temporal Logic via Graph-Based Fusion

Robotic planning from visual observations and signal temporal logic (STL) requires grounding task requirements in scene evidence while adapting plans to execution feedback. We present GraF-VTA, a graph-based framework that extends Vision-TL-Action with structured task representations, causal observation history, and closed-loop trajectory generation. Bidirectional cross-attention fuses STL syntax tokens with visual features, while an optional frozen automaton embedding supplies complementary untimed task structure. A temporal pyramid preserves detailed current observations and compresses older frames to provide recent execution context. Conditioned on these features and robot state, a flow-matching model generates plans whose action prefixes are executed before replanning from refreshed observations. Across five simulation environments, the single-graph configuration achieves higher open-loop Success@KK than TeLoGraF and Vision-TL-Action on four environments at the reported budgets K≥16K\geq16. On Panda, matched-update ablations increase Success@256 from 53.91\% without observation history to 62.50\% with pyramid memory. In closed-loop Dubins evaluation, it reaches 64.06\% Success@1024, compared with 12.50\% for adapted S-MSP and 27.34\% for adapted Logic-VLA. These results support combining structured visual conditioning with observation history and replanning to improve coverage of STL-satisfying trajectories.

查看此版本解读 →查看此版本原文 ↗