MA-SafeDiffuser：基于扩散概率模型的多智能体安全规划方法（AAMAS 2026 论文）
MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models
AI 导读
研究者提出 MA-SafeDiffuser，是 SafeDiffuser 的多智能体扩展，为基于扩散模型的轨迹规划器提供有限时间扩散不变性保证，满足联合智能体安全规范。
正文 · 原文
Abstract:We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of per-agent and pairwise barrier sets; (ii) derive centralized and decentralized (communication-aware) constrained denoising procedures with provable invariance under mild assumptions; (iii) address local-trap and deadlock phenomena via time-varying specifications and liveness CBFs; and (iv) develop a lightweight benchmarking suite including a multi-agent Maze2D domain. Empirically, MA-SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines, while retaining planning quality. We provide algorithms, proofs, and reference implementations.
| Comments: | Accepted at AAMAS 2026. 14 pages, including supplementary material |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.05524 [cs.AI] |
| (or arXiv:2611.05524v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05524 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.65109/PAPW1165
DOI(s) linking to related resources |
Submission history
From: Kiran Ravish [view email]
[v1]
Tue, 3 Nov 2026 19:20:32 UTC (3,466 KB)
来源：arXiv cs.AI · arxiv.org