# Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning

arXiv: https://arxiv.org/abs/2508.20095 · HTML: https://mlsanity.com/paper/2508.20095/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations](https://mlsanity.com/paper/2410.10792/) (2024)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [Constrained Synthesis with Projected Diffusion Models](https://mlsanity.com/paper/2402.03559/) (2024)
- [EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding](https://mlsanity.com/paper/2010.01367/) (2020)
- [Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey](https://mlsanity.com/paper/2011.13112/) (2020)
- [Informed RRT*: Optimal Sampling-based Path Planning Focused via Direct Sampling of an Admissible Ellipsoidal Heuristic](https://mlsanity.com/paper/1404.2334/) (2014)
- [Potential Based Diffusion Motion Planning](https://mlsanity.com/paper/2407.06169/) (2024)
- [Multi-Robot Motion Planning with Diffusion Models](https://mlsanity.com/paper/2410.03072/) (2024)
- [Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models](https://mlsanity.com/paper/2502.03607/) (2025)
- [Motion Planning around Obstacles with Convex Optimization](https://mlsanity.com/paper/2205.04422/) (2022)
- [dRRT*: Scalable and Informed Asymptotically-Optimal Multi-Robot Motion Planning](https://mlsanity.com/paper/1903.00994/) (2019)
- [Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation](https://mlsanity.com/paper/2506.01121/) (2025)
- [Constrained Generative Modeling with Manually Bridged Diffusion Models](https://mlsanity.com/paper/2502.20371/) (2025)
- [GCS*: Forward Heuristic Search on Implicit Graphs of Convex Sets](https://mlsanity.com/paper/2407.08848/) (2024)
- [Efficient Multi-Agent Trajectory Planning with Feasibility Guarantee using Relative Bernstein Polynomial](https://mlsanity.com/paper/1909.10219/) (2019)
- [Approximating Robot Configuration Spaces with few Convex Sets using Clique Covers of Visibility Graphs](https://mlsanity.com/paper/2310.02875/) (2023)
- [Faster Algorithms for Growing Collision-Free Convex Polytopes in Robot Configuration Space](https://mlsanity.com/paper/2410.12649/) (2024)
- [SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion Transformer](https://mlsanity.com/paper/2505.15679/) (2025)

## Built on by (most cited first, 10 of 10)

- [Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation](https://mlsanity.com/paper/2509.25157/) (2025)
- [Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning](https://mlsanity.com/paper/2605.27697/) (2026)
- [Scalable Multi Agent Diffusion Policies for Coverage Control](https://mlsanity.com/paper/2509.17244/) (2025)
- [Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention](https://mlsanity.com/paper/2605.13296/) (2026)
- [Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning](https://mlsanity.com/paper/2604.06598/) (2026)
- [Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning](https://mlsanity.com/paper/2605.16863/) (2026)
- [Robots as Tokens: Unified Diffusion Transformer for Coordinated Multi-Robot Trajectory Generation](https://mlsanity.com/paper/2606.15550/) (2026)
- [Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion](https://mlsanity.com/paper/2608.29507/) (2026)
- [Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding](https://mlsanity.com/paper/2609.32019/) (2026)
- [Training-Free Diffusion Planning with Analytical Local Scores](https://mlsanity.com/paper/2610.01959/) (2026)

## Abstract (arXiv)

Multi-Robot Motion Planning (MRMP) involves generating collision-free trajectories for multiple robots operating in a shared continuous workspace. While discrete multi-agent path finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization severely limits trajectory quality. In contrast, continuous optimization-based planners offer higher-quality paths but suffer from the curse of dimensionality, resulting in poor scalability with respect to the number of robots. This paper tackles the limitations of these two approaches by introducing a novel framework that integrates discrete MAPF solvers with constrained generative diffusion models. The resulting framework, called Discrete-Guided Diffusion (DGD), has three key characteristics: (1) it decomposes the original nonconvex MRMP problem into tractable subproblems with convex configuration spaces, (2) it combines discrete MAPF solutions with constrained optimization techniques to guide diffusion models capture complex spatiotemporal dependencies among robots, and (3) it incorporates a lightweight constraint repair mechanism to ensure trajectory feasibility. The proposed method sets a new state-of-the-art performance in large-scale, complex environments, scaling to 100 robots while achieving planning efficiency and high success rates.