Toward Single-Step MPPI via Differentiable Predictive Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914439328956416 |
|---|---|
| author | Le, Viet-Anh Tumu, Renukanandan Mangharam, Rahul |
| author_facet | Le, Viet-Anh Tumu, Renukanandan Mangharam, Rahul |
| contents | Model predictive path integral (MPPI) is a sampling-based method for solving complex model predictive control (MPC) problems, but its real-time implementation faces two key challenges: the computational cost and sample requirements grow with the prediction horizon, and manually tuning the sampling covariance requires balancing exploration and noise. To address these issues, we propose Step-MPPI, a framework that learns a sampling distribution for efficient single-step lookahead MPPI implementation. Specifically, we use a neural network to parameterize the MPPI proposal distribution at each time step, and train it in a self-supervised manner over a long horizon using the MPC cost, constraint penalties, and a maximum-entropy regularization term. By embedding long-horizon objectives into training the neural distribution policy, Step-MPPI achieves the foresight of a multi-step optimizer with the millisecond-level latency of single-step lookahead. We demonstrate the efficiency of Step-MPPI across multiple challenging tasks in which MPPI suffers from high dimensionality and/or long control horizons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01539 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Single-Step MPPI via Differentiable Predictive Control Le, Viet-Anh Tumu, Renukanandan Mangharam, Rahul Systems and Control Model predictive path integral (MPPI) is a sampling-based method for solving complex model predictive control (MPC) problems, but its real-time implementation faces two key challenges: the computational cost and sample requirements grow with the prediction horizon, and manually tuning the sampling covariance requires balancing exploration and noise. To address these issues, we propose Step-MPPI, a framework that learns a sampling distribution for efficient single-step lookahead MPPI implementation. Specifically, we use a neural network to parameterize the MPPI proposal distribution at each time step, and train it in a self-supervised manner over a long horizon using the MPC cost, constraint penalties, and a maximum-entropy regularization term. By embedding long-horizon objectives into training the neural distribution policy, Step-MPPI achieves the foresight of a multi-step optimizer with the millisecond-level latency of single-step lookahead. We demonstrate the efficiency of Step-MPPI across multiple challenging tasks in which MPPI suffers from high dimensionality and/or long control horizons. |
| title | Toward Single-Step MPPI via Differentiable Predictive Control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2604.01539 |