Skip to content

论文arXiv 2611.1322711 天前

LBS框架解耦行为与路径安全,提升生成式规划到达率 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Latent Barrier Steering: Hierarchical Safety for Generative Planning(arXiv 2611.13227)

核心内容 ​

针对现有扩散或流匹配规划器中控制障碍函数(CBF)仅能局部修复样本、难以应对全局模式约束失效的问题,研究提出Latent Barrier Steering(LBS)分层语义到路径安全框架。该方法将行为选择与路径认证解耦,首先在潜空间引导生成器向高安全裕度轨迹演化,随后对解码路径施加CBF二次规划(QP)处理残余违规。实验表明,LBS在保留安全性的同时,相比纯路径级滤波器显著提高了目标到达成功率。

技术核心在于利用潜空间转向增加路径空间校正器的可用裕度,从而提供有限时间恢复保证并减少实时修正计算量。系统架构包含协同干预机制:先调整行为潜变量以规避模式级阻塞,再在物理路径空间执行精细化安全过滤。该方案已在机器人导航及末端执行器规划任务中验证,证实了其在复杂约束下平衡生成质量与安全合规的有效性,解决了传统方法在新约束阻断整体行为模式时的失效难题。

关键看点 ​

  • 分层解耦机制:将行为选择与路径认证分离,先引导潜变量增大安全裕度,再对解码路径应用CBF-QP修正残差
  • 理论安全保证:通过潜空间转向扩展校正器可用裕度,为生成式规划提供有限时间恢复保证,解决模式级约束失效
  • 性能实测验证:在导航与机械臂末端规划任务中,相比传统路径级安全滤波器,LBS在保障安全前提下提升目标到达率

工程与产业观察 ​

LBS为具身智能生成式规划提供了从“事后修补”转向“事前引导”的工程范式。通过潜空间与路径空间的分层协同,有效缓解了安全约束与生成多样性的冲突,对高动态环境下机器人端到端策略的安全部署具有直接参考价值,尤其适用于需兼顾长程语义理解与瞬时避障的复杂操作场景。

英文摘要 (Abstract) ​

We introduce Latent Barrier Steering (LBS), a hierarchical semantic-to-path framework for safe flow-matching-based generative planning. Existing control-barrier-function (CBF) safety filters for diffusion and flow-matching planners act locally on generated samples, either during sampling or after prediction. Such repair is effective for small violations, but can struggle when a new constraint blocks the whole selected behavior mode rather than merely perturbing it locally. LBS decouples behavior selection from path certification through two coordinated interventions: it first steers the generator's behavior latent toward rollouts with larger safety margin, then decodes the steered latent and applies a path-space CBF quadratic program (QP) only for residual violations. We show that latent steering increases the margin available to the path-space corrector, yielding finite-time recovery guarantees and reduced correction burden. Experiments across navigation and robot end-effector planning tasks show that LBS preserves safety while improving goal reaching and reducing correction burden compared with path-level safety filters.

作者:Renhao Zhang, Mingzhe Li, Bruno Castro da Silva

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.13227:Latent Barrier Steering: Hierarchical Safety for Generative Planning ↗访问 2026-11-11