# Bayesian Optimization for Automatic Tuning of Torque-Level Nonlinear Model Predictive Control

arXiv: https://arxiv.org/abs/2512.03772 · HTML: https://mlsanity.com/paper/2512.03772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspaces](https://mlsanity.com/paper/2103.00349/) (2021)
- [Scalable Constrained Bayesian Optimization](https://mlsanity.com/paper/2002.08526/) (2020)
- [Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control](https://mlsanity.com/paper/1909.04947/) (2019)
- [Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution](https://mlsanity.com/paper/1712.08048/) (2017)
- [Tuning Legged Locomotion Controllers via Safe Bayesian Optimization](https://mlsanity.com/paper/2306.07092/) (2023)
- [Performance-based Trajectory Optimization for Path Following Control Using Bayesian Optimization](https://mlsanity.com/paper/2103.15416/) (2021)
- [Performance-driven Constrained Optimal Auto-Tuner for MPC](https://mlsanity.com/paper/2503.07127/) (2025)
- [Differential Dynamic Programming for Multi-Phase Rigid Contact Dynamics](https://mlsanity.com/paper/1904.05072/) (2019)
- [Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty](https://mlsanity.com/paper/2203.00551/) (2022)
- [Guided Bayesian Optimization: Data-Efficient Controller Tuning with Digital Twin](https://mlsanity.com/paper/2403.16619/) (2024)

## Abstract (arXiv)

This paper presents an auto-tuning framework for torque-based Nonlinear Model Predictive Control (nMPC), where the MPC serves as a real-time controller for optimal joint torque commands. The MPC parameters, including cost function weights and low-level controller gains, are optimized using high-dimensional Bayesian Optimization (BO) techniques, specifically Sparse Axis-Aligned Subspace (SAASBO) with a digital twin (DT) to achieve precise end-effector trajectory real-time tracking on an UR10e robot arm. The simulation model allows efficient exploration of the high-dimensional parameter space, and it ensures safe transfer to hardware. Our simulation results demonstrate significant improvements in tracking performance (+41.9%) and reduction in solve times (-2.5%) compared to manually-tuned parameters. Moreover, experimental validation on the real robot follows the trend (with a +25.8% improvement), emphasizing the importance of digital twin-enabled automated parameter optimization for robotic operations.