cs.AINov 3, 2026

MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models

Authors: Kiran Ravish, Ankita Kushwaha, Preeti, Pawan Kumar

Organizations: IIIT Hyderabad, Hyderabad, India

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.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner

    Mar 11, 2026Eugene Ku, Yiwei LyuConstrained Motion PlanningTrajectory Generation

  2. Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning

    Aug 10, 2026Nakgyu Yang, KwangBin Lee, SooJean HanConstrained Motion PlanningTrajectory Generation

  3. D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

    Jul 12, 2026Erdi Sayar, Ersin Daş, Joel W. Burdick +2Constrained Motion PlanningDiffusion-Based Planning