# Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees

## TL;DR

DiTree introduces a diffusion policy-guided kinodynamic motion planning framework that combines learning-based sampling with classical search algorithms, achieving higher success rates and robustness in complex, out-of-distribution scenarios.

## Contribution

The paper proposes Diffusion Tree (DiTree), a novel framework that integrates diffusion policies with sampling-based planners to ensure provably-safe, efficient kinodynamic motion planning with generalization capabilities.

## Key findings

- 30% higher success rate in OOD scenarios
- Effective in complex dynamical systems like car and ant robot
- Demonstrated robustness and superior trajectory quality in real-world experiments

## Abstract

Kinodynamic motion planning is concerned with computing collision-free trajectories while abiding by the robot's dynamic constraints. This critical problem is often tackled using sampling-based planners (SBPs) that explore the robot's high-dimensional state space by constructing a search tree via action propagations. Although SBPs can offer global guarantees on completeness and solution quality, their performance is often hindered by slow exploration due to uninformed action sampling. Learning-based approaches can yield significantly faster runtimes, yet they fail to generalize to out-of-distribution (OOD) scenarios and lack critical guarantees, e.g., safety, thus limiting their deployment on physical robots. We present Diffusion Tree (DiTree): a provably-generalizable framework leveraging diffusion policies (DPs) as informed samplers to efficiently guide state-space search within SBPs. DiTree combines DP's ability to model complex distributions of expert trajectories, conditioned on local observations, with the completeness of SBPs to yield provably-safe solutions within a few action propagation iterations for complex dynamical systems. We demonstrate DiTree's power with an implementation combining the popular RRT planner with a DP action sampler trained on a single environment. In comprehensive evaluations on OOD scenarios, DiTree achieves on average a 30% higher success rate compared to standalone DP or SBPs, on a dynamic car and Mujoco's ant robot settings (for the latter, SBPs fail completely). Beyond simulation, real-world car experiments confirm DiTree's applicability, demonstrating superior trajectory quality and robustness even under severe sim-to-real gaps. Project webpage: https://sites.google.com/view/ditree.