Rapid and Safe Trajectory Planning over Diverse Scenes through Diffusion Composition

Anonymous Authors
Anonymous Institution

Teaser

Diffusion Composition Enables Efficient, Safe Planning with Practical Real-world Performance. An individual diffusion model cannot ensure safe trajectory planning in out-of-distribution scenarios, whereas composing multiple diffusion models can achieve safety during generalization. Dashed boxes indicate obstacles that do not exist during training. Validation on the F1TENTH platform demonstrates that trajectories planned by the composed diffusion model offer excellent safety while maintaining computational efficiency, indicating that the proposed method is suitable for real-world applications.

Abstract

Safe trajectory planning remains a significant challenge in complex environments, where traditional methods often trade off computational efficiency for safety. Comprehensive obstacle modeling improves safety but is computationally expensive, while approximate methods are more efficient but may compromise safety. To address this issue, this paper introduces a rapid and safe trajectory planning framework based on state-based diffusion models. Leveraging only low-dimensional vehicle states, the diffusion models achieve notable inference efficiency while ensuring sufficient collision-free characteristics. By composing diffusion models, the proposed framework can safely generalize across diverse scenarios, planning collision-free trajectories even in unseen scenes. To further ensure the safety of the generated trajectories, an efficient, rule-based safety filter is proposed, which selects optimal trajectories that satisfy both sufficient safety and control feasibility from among candidate trajectories. Both in seen and unseen scenarios, the proposed method achieves efficient inference time while maintaining high safety and stability. Evaluations on the F1TENTH vehicle further demonstrate that the proposed method is practical in real-world applications.

Real-World Validation of Individual Static Model

replay

replay
replay

replay

replay
replay
This paper introduces a fast trajectory‐synthesis framework that seamlessly fuses real‐time perception with diffusion‐based generative models. By distilling rich sensor inputs into compact vehicle‐state embeddings, our approach dramatically accelerates the iterative denoising process while fully preserving the diffusion model's capacity to produce precise, high‐fidelity trajectories.

Real-World Validation of Composition for UNSEEN Scenes

Static Diffusion Model replay

Dynamic Diffusion Model replay
Composed Result replay
This model composition approach ensures collision-free trajectory planning in unseen scenes for safety. The proposed method can make optimal test-time decisions to generate safe behaviors, such as accelerating to bypass or decelerating to avoid obstacles , thus allowing trajecoty planning for diverse scenes without retraining.

Composed Scene 1 - view 1:

Initial Pose: [0.86, 0.03] replay

Initial Pose: [2.73, 0.32] replay
Initial Pose: [3.03, -0.07] replay

Composed Scene 1 - view 2:

Initial Pose: [0.86, 0.03] replay

Initial Pose: [2.73, 0.32] replay
Initial Pose: [3.03, -0.07] replay

Composed Scene 2 - view 1:

Initial Pose: [0.82, 0.07] replay

Initial Pose: [2.76, 0.47] replay
Initial Pose: [2.79, -0.11] replay

Composed Scene 2 - view 2:

Initial Pose: [0.82, 0.07] replay

Initial Pose: [2.76, 0.47] replay
Initial Pose: [2.79, -0.11] replay

The Performance of Model Composition in Simulation

Weights of composition - [Dynamic Model, Static Model]:  
Static Model

Dynamic Model

Composed Result
Effectiveness of Models Composition and Sensitivity of Compositional Weights. The composed model can safely generalize to unseen scenes when appropriate compositional weights are selected, achieving collision-free trajectory planning.