跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20929 · v1

Transferable Neural CBFs via Generalized Closure

首次提交 2026-11-16 19:38
版本更新 2026-11-16 19:38
雷达观测 2026-11-17 17:11
arXiv ↗PDF ↗

摘要

Classical control barrier functions (CBFs) provide safety constraints for controllers, but designing them by hand is difficult for underactuated vehicles and the resulting safe sets can be overly conservative. Neural CBFs can learn more informative barriers from data, yet a learned barrier is usually verified only for one fixed obstacle configuration. We study whether one neural barrier can be reused across environments by expressing the state relative to each obstacle. The key gap is that these relative coordinates may discard information needed to predict their own evolution. We give a generalized closure condition that represents this missing information as a residual and a lifting theorem that transfers a verified relative-coordinate barrier to every obstacle in a family. A rank test also identifies when symmetry alone cannot justify the transfer. We validate the conditions on a double integrator, a planar aircraft, and a 12-state quadrotor. Coordinates that fail the test lead to obstacle penetration or to a barrier condition that fails near hover, whereas body-frame coordinates close exactly for the quadrotor. The resulting barrier transfers to new maps without retraining and is effective in the reported deployment and fast-start experiments.

作者备注:8 pages, 1 figure, 5 tables. Submitted to the 2027 American Control Conference (ACC 2027)

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 · 2026-11-16 19:38 · 最新观测版本

Transferable Neural CBFs via Generalized Closure

Classical control barrier functions (CBFs) provide safety constraints for controllers, but designing them by hand is difficult for underactuated vehicles and the resulting safe sets can be overly conservative. Neural CBFs can learn more informative barriers from data, yet a learned barrier is usually verified only for one fixed obstacle configuration. We study whether one neural barrier can be reused across environments by expressing the state relative to each obstacle. The key gap is that these relative coordinates may discard information needed to predict their own evolution. We give a generalized closure condition that represents this missing information as a residual and a lifting theorem that transfers a verified relative-coordinate barrier to every obstacle in a family. A rank test also identifies when symmetry alone cannot justify the transfer. We validate the conditions on a double integrator, a planar aircraft, and a 12-state quadrotor. Coordinates that fail the test lead to obstacle penetration or to a barrier condition that fails near hover, whereas body-frame coordinates close exactly for the quadrotor. The resulting barrier transfers to new maps without retraining and is effective in the reported deployment and fast-start experiments.

查看此版本解读 →查看此版本原文 ↗