# Multirotor Ensemble Model Predictive Control I: Simulation Experiments

arXiv: https://arxiv.org/abs/2305.12625 · HTML: https://mlsanity.com/paper/2305.12625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 9 of 9)

- [Informative Neural Ensemble Kalman Learning](https://mlsanity.com/paper/2008.09915/) (2020)
- [Neural Integration of Continuous Dynamics](https://mlsanity.com/paper/1911.10309/) (2019)
- [Neural Networks as Geometric Chaotic Maps](https://mlsanity.com/paper/1912.05081/) (2019)
- [Experimental Implementation of an Adaptive Digital Autopilot](https://mlsanity.com/paper/2012.02896/) (2020)
- [An Adaptive PID Autotuner for Multicopters with Experimental Results](https://mlsanity.com/paper/2109.12797/) (2021)
- [GPU-Based Parallel Integration of Large Numbers of Independent ODE Systems](https://mlsanity.com/paper/1611.02274/) (2016)
- [Iterative Sequential Action Control for Stable, Model-Based Control of Nonlinear Systems](https://mlsanity.com/paper/1706.08932/) (2017)
- [Learn Like The Pro: Norms from Theory to Size Neural Computation](https://mlsanity.com/paper/2106.11409/) (2021)
- [An Adaptive Digital Autopilot for Fixed-Wing Aircraft with Actuator Faults](https://mlsanity.com/paper/2110.11390/) (2021)

## Abstract (arXiv)

Nonlinear receding horizon model predictive control is a powerful approach to controlling nonlinear dynamical systems. However, typical approaches that use the Jacobian, adjoint, and forward-backward passes may lose fidelity and efficacy for highly nonlinear problems. Here, we develop an Ensemble Model Predictive Control (EMPC) approach wherein the forward model remains fully nonlinear, and an ensemble-represented Gaussian process performs the backward calculations to determine optimal gains for the initial time. EMPC admits black box, possible non-differentiable models, simulations are executable in parallel over long horizons, and control is uncertainty quantifying and applicable to stochastic settings. We construct the EMPC for terminal control and regulation problems and apply it to the control of a quadrotor in a simulated, identical-twin study. Results suggest that the easily implemented approach is promising and amenable to controlling autonomous robotic systems with added state/parameter estimation and parallel computing.