Risk-Constrained MPPI Tuning with Update-Aware MA-ES Racing
Abstract
We formulate offline tuning of Model Predictive Path Integral (MPPI) controllers as a chance-constrained black-box optimization problem and develop an update-aware framework based on Matrix Adaptation Evolution Strategy (MA-ES). We use statistical information from noisy controller evaluations to determine when the evolutionary update is sufficiently reliable. When the recombination direction is certified, a derivative-free nonmonotone line search (NMLS) is used to refine the candidate solution, and a separate validation stage assesses the final frozen controller. We establish a worst-case arithmetic-complexity bound for both online MPPI control and offline tuning. Numerical experiments on TurtleBot 4, Jackal-like, and Ackermann models show that the proposed NMLS refinement is competitive with standard MA-ES, transfers across the three vehicle models without model-specific retuning, and improves several cost and validation measures. Both MA-ES variants also compare favorably with the tested randomized derivative-free line search (VRBBO) configuration. The results support the practical applicability and transferability of the proposed framework, while not claiming universal superiority or hardware-level safety.
Related
- Risk-Aware Unit Commitment in District Heating Networks: Chance-Constrained and CVaR Optimization Under Demand Uncertainty
- Regularity-Aware Stochastic MGDA with Adaptive Per-Iterate Conflict-Avoidant Update
- UQ-ACE: Stability-Aware Counterfactual Controller Tuning via Bayesian SINDy
- Tuning-Free Covariance-Aware Sequential Shrinkage for Multi-Source Estimation
- Feedback-Aware Tuning of Recursive Q-Learning
BibTeX
@misc{kimiaei2026riskconstrained,
title = {{Risk-Constrained MPPI Tuning with Update-Aware MA-ES Racing}},
author = {Morteza Kimiaei and Roya Khalili-Amirabadi and Mohsen Jalaeian-Farimani},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14965},
eprint = {2610.14965},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14965},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Risk-Constrained MPPI Tuning with Update-Aware MA-ES Racing
AU - Morteza Kimiaei
AU - Roya Khalili-Amirabadi
AU - Mohsen Jalaeian-Farimani
PY - 2026
DA - 2026/10/10
PB - arXiv
DO - 10.48550/arxiv.2610.14965
UR - https://arxiv.org/abs/2610.14965
AB - We formulate offline tuning of Model Predictive Path Integral (MPPI) controllers as a chance-constrained black-box optimization problem and develop an update-aware framework based on Matrix Adaptation Evolution Strategy (MA-ES). We use statistical information from noisy controller evaluations to determine when the evolutionary update is sufficiently reliable. When the recombination direction is certified, a derivative-free nonmonotone line search (NMLS) is used to refine the candidate solution, and a separate validation stage assesses the final frozen controller. We establish a worst-case arithmetic-complexity bound for both online MPPI control and offline tuning. Numerical experiments on TurtleBot 4, Jackal-like, and Ackermann models show that the proposed NMLS refinement is competitive with standard MA-ES, transfers across the three vehicle models without model-specific retuning, and improves several cost and validation measures. Both MA-ES variants also compare favorably with the tested randomized derivative-free line search (VRBBO) configuration. The results support the practical applicability and transferability of the proposed framework, while not claiming universal superiority or hardware-level safety.
ER -