Research map / Image generation / Fast diffusion sampling
Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning
Jinhao Liang, Sven Koenig, Ferdinando Fioretto
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| decompose MRMP into convex-region subproblems guided by MAPF schedule (DGD) versus global projection-based diffusion (SMD) | diffusion-based MRMP · MRMP Dense map, 6 robots | running time (s): 287.3 -> 12.3 at 100% success | Improved |
| use priority-based convex decomposition instead of Visibility Clique Cover | DGD · MRMP benchmark scenarios | number of convex regions: reduces region count by over 50% | Improved |
| scale DGD to 100 robots and 104 obstacles | DGD · large-scale map | feasible solutions: 2.5x robot count over prior diffusion MRMP (40 robots) | Improved |
| unguided single-robot diffusion extended to multiple robots (MPD) | MPD · complex maps with more than three robots | success rate | Hurt |
| MAPF-guided diffusion without explicit coordination (MMD) on narrow-passage maps | MMD · Room and Shelf maps, 12+ robots | success rate | Hurt |
| initialize reverse diffusion from MAPF solution instead of Gaussian noise | DGD · MRMP | sampling efficiency and quality | Improved |
Closest papers by meaning
- Multi-Robot Motion Planning with Diffusion Models (ICLR 2025 · similarity 0.92)
- Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models (ICML 2025 · similarity 0.91)
- Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning (NeurIPS 2026 · similarity 0.90)
- Multi-Agent Motion Planning for Differential Drive Robots Through Stationary State Search (AAAI 2025 · similarity 0.89)
- Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding (AAAI 2024 · similarity 0.88)
- Model-based Diffusion for Trajectory Optimization (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
