SID is a decentralized planner that reuses a constraint-aware diffusion model to simulate neighbors' trajectories and then generate collision-free own paths, enabling minimal communication and scaling to 108 robots.
Potential based diffusion motion planning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
MADP uses diffusion models to generate interdependent actions for decentralized robot swarms in coverage control, trained via imitation from a clairvoyant expert and shown to generalize and outperform baselines across varying agent densities and importance densities.
Optimization-guided diffusion replaces sampling perturbations with constrained corrections to enforce physical feasibility in generative robot policies at inference time.
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.
citing papers explorer
-
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
SID is a decentralized planner that reuses a constraint-aware diffusion model to simulate neighbors' trajectories and then generate collision-free own paths, enabling minimal communication and scaling to 108 robots.
-
Muninn: Your Trajectory Diffusion Model But Faster
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
-
Scalable Multi Agent Diffusion Policies for Coverage Control
MADP uses diffusion models to generate interdependent actions for decentralized robot swarms in coverage control, trained via imitation from a clairvoyant expert and shown to generalize and outperform baselines across varying agent densities and importance densities.
-
Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control
Optimization-guided diffusion replaces sampling perturbations with constrained corrections to enforce physical feasibility in generative robot policies at inference time.
-
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.