# Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers

arXiv: https://arxiv.org/abs/2506.14855 · HTML: https://mlsanity.com/paper/2506.14855/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving](https://mlsanity.com/paper/1707.02342/) (2017)
- [Safe Reinforcement Learning Using Robust MPC](https://mlsanity.com/paper/1906.04005/) (2019)
- [Learning an Approximate Model Predictive Controller with Guarantees](https://mlsanity.com/paper/1806.04167/) (2018)
- [Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo](https://mlsanity.com/paper/2212.00541/) (2022)
- [Optimization-Based Control for Dynamic Legged Robots](https://mlsanity.com/paper/2211.11644/) (2022)
- [Feedback MPC for Torque-Controlled Legged Robots](https://mlsanity.com/paper/1905.06144/) (2019)
- [Automatic nonlinear MPC approximation with closed-loop guarantees](https://mlsanity.com/paper/2312.10199/) (2023)
- [TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers](https://mlsanity.com/paper/2310.16985/) (2023)
- [Cafe-Mpc: A Cascaded-Fidelity Model Predictive Control Framework with Tuning-Free Whole-Body Control](https://mlsanity.com/paper/2403.03995/) (2024)
- [MPCGPU: Real-Time Nonlinear Model Predictive Control through Preconditioned Conjugate Gradient on the GPU](https://mlsanity.com/paper/2309.08079/) (2023)
- [Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining](https://mlsanity.com/paper/2404.05835/) (2024)
- [Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation](https://mlsanity.com/paper/2306.00286/) (2023)
- [Accelerating Model Predictive Control for Legged Robots through Distributed Optimization](https://mlsanity.com/paper/2403.11742/) (2024)
- [Model Predictive Path Integral Control for Agile Unmanned Aerial Vehicles](https://mlsanity.com/paper/2407.09812/) (2024)
- [On the Benefits of GPU Sample-Based Stochastic Predictive Controllers for Legged Locomotion](https://mlsanity.com/paper/2403.11383/) (2024)
- [LP-MPPI: Low-Pass Filtering for Efficient Model Predictive Path Integral Control](https://mlsanity.com/paper/2503.11717/) (2025)

## Abstract (arXiv)

Model Predictive Path Integral control is a powerful sampling-based approach suitable for complex robotic tasks due to its flexibility in handling nonlinear dynamics and non-convex costs. However, its applicability in real-time, highfrequency robotic control scenarios is limited by computational demands. This paper introduces Feedback-MPPI (F-MPPI), a novel framework that augments standard MPPI by computing local linear feedback gains derived from sensitivity analysis inspired by Riccati-based feedback used in gradient-based MPC. These gains allow for rapid closed-loop corrections around the current state without requiring full re-optimization at each timestep. We demonstrate the effectiveness of F-MPPI through simulations and real-world experiments on two robotic platforms: a quadrupedal robot performing dynamic locomotion on uneven terrain and a quadrotor executing aggressive maneuvers with onboard computation. Results illustrate that incorporating local feedback significantly improves control performance and stability, enabling robust, high-frequency operation suitable for complex robotic systems.