面向机器人基础模型的规格感知动作分布优化框架
Specification-Aware Distribution Shaping for Robotics Foundation Models
AI 导读
一项 arXiv 论文提出规格感知的动作分布优化框架，可在不修改预训练机器人基础模型参数的情况下，于执行时强制满足一大类 Signal Temporal Logic（STL）约束。该方法在每个决策步通过前向动力学传播推理剩余时域，计算满足硬 STL 可行性约束的最小改动动作分布，支持时限目标访问、顺序目标和持久安全条件等时空需求，并已在仿真中结合先进机器人基础模型完成多环境验证。
正文 · 原文
Abstract:Robotics foundation models have demonstrated strong capabilities in executing natural language instructions across diverse tasks and environments. However, they remain largely data-driven and lack formal guarantees on constraint satisfaction during deployment. In practice, robots often need to comply with operational constraints involving rich spatio-temporal requirements such as time-bounded goal visits, sequential objectives, and persistent safety conditions. In this work, we propose a specification-aware action distribution optimization framework that enforces a broad class of Signal Temporal Logic (STL) constraints during execution of a pretrained robotics foundation model without modifying its parameters. At each decision step, the method computes a minimally modified action distribution that satisfies a hard STL feasibility constraint by reasoning over the remaining horizon using forward dynamics propagation. We validate the proposed framework in simulation using state-of-the-art robotics foundation models across multiple environments and complex specifications.
| Comments: | 8 pages, 4 figures |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.17969 [cs.RO] |
| (or arXiv:2603.17969v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2603.17969 arXiv-issued DOI via DataCite |
Submission history
From: Sadık Bera Yüksel [view email]
[v1]
Wed, 18 Mar 2026 17:36:46 UTC (4,865 KB)
[v2]
Fri, 30 Oct 2026 15:28:37 UTC (3,294 KB)
来源：arXiv cs.AI · arxiv.org