让机器人导航模型生成安全动作，无需重训练即可保证行为合规。
Constrained Decoding for Safe Robot Navigation Foundation Models
- 用信号时序逻辑约束解码过程，实时保障动作安全
- 在数百个随机生成场景中验证，显著减少不安全行为
- 适用于主流导航模型，适合关注安全落地的开发者
近期机器人基础模型的发展推动了端到端、通用型机器人的进步。这些模型通过大量模拟与真实轨迹数据训练，直接将多模态观测映射为可执行的动作序列。尽管具备出色的现实表现，但其仍依赖数据驱动，缺乏对行为正确性的显式定义。本文提出SafeDec，一种针对自回归Transformer架构的机器人导航基础模型的约束解码框架，通过信号时序逻辑（STL）公式表达安全规范，在运行时假设动态模型下，无需重训练即可保证生成动作严格满足STL约束。该方法对底层策略完全透明。我们在CHORES基准上对最先进的具身导航策略进行了评估，涵盖数百个程序生成环境，结果表明，解码阶段的干预不仅有效过滤不安全动作，还能实现条件化动作生成。视频展示见constrained-robot-fms.github.io。
原文摘要 · Abstract (English)
Recent advances in the development of robotic foundation models have led to promising end-to-end and general-purpose capabilities in robotic systems. Trained on vast datasets of simulated and real-world trajectories, these policies map multimodal observations directly to action sequences for physical execution. Despite promising real-world capabilities, these models are still data-driven and, therefore, lack explicit notions of behavioral correctness. We address this gap by introducing SafeDec, a constrained decoding framework for autoregressive, transformer-based robot navigation foundation models that enforces safety specifications expressed as Signal Temporal Logic (STL) formulas. Our method ensures that generated actions provably satisfy STL specifications under assumed dynamics at runtime without retraining while remaining agnostic of the underlying policy. We evaluate SafeDec on tasks from the CHORES benchmark for state-of-the-art embodied navigation policies across hundreds of procedurally generated environments and show that our decoding-time interventions are useful not only for filtering unsafe actions but also for conditional action generation. Videos are available at constrained-robot-fms.github.io
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。