D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions
2026-07-12 • Robotics
Robotics
AI summaryⓘ
The authors address a problem where diffusion models used for robot planning often produce unsafe or unrealistic paths because they don't naturally follow safety rules. To fix this, they created D-SafeMPC, which mixes the diffusion model with control techniques that keep the robot safe and help it reach goals. Their method adjusts the robot's planned path step-by-step to make sure it avoids obstacles and stays feasible. Tests on both simulated and real robots showed that their approach plans safer and more successful movements than other methods.
diffusion modelsrobotic planningmodel predictive control (MPC)control barrier functions (CBFs)control Lyapunov functions (CLFs)trajectory planningsafe controlFranka manipulatorsim-to-real transferdenoising
Authors
Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan
Abstract
A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC