Safe Model Predictive Diffusion with Shielding

TL;DR

Safe Model Predictive Diffusion (Safe MPD) is a novel, training-free diffusion-based planning method that ensures kinodynamically feasible and safe trajectories for complex robotic systems by integrating safety constraints directly into the denoising process.

Contribution

This paper introduces Safe MPD, a new diffusion planning framework that unifies safety and feasibility enforcement during trajectory generation without requiring training.

Findings

Outperforms existing safety strategies in success rate and safety.

Achieves sub-second computation times.

Validated on complex non-convex planning problems.

Abstract

Generating safe, kinodynamically feasible, and optimal trajectories for complex robotic systems is a central challenge in robotics. This paper presents Safe Model Predictive Diffusion (Safe MPD), a training-free diffusion planner that unifies a model-based diffusion framework with a safety shield to generate trajectories that are both kinodynamically feasible and safe by construction. By enforcing feasibility and safety on all samples during the denoising process, our method avoids the common pitfalls of post-processing corrections, such as computational intractability and loss of feasibility. We validate our approach on challenging non-convex planning problems, including kinematic and acceleration-controlled tractor-trailer systems. The results show that it substantially outperforms existing safety strategies in success rate and safety, while achieving sub-second computation times.