Weighted Maximum Likelihood for Controller Tuning

TL;DR

This paper introduces a probabilistic policy search method called Weighted Maximum Likelihood (WML) to automatically tune Model Predictive Contouring Control (MPCC) parameters for agile quadrotor flight, enabling zero-shot transfer from simulation to real-world scenarios.

Contribution

The paper presents a novel, data-efficient WML approach for automatic MPCC tuning that is capable of zero-shot transfer from simulation to real-world quadrotor flight.

Findings

WML outperforms manual tuning and auto-tuning baselines.

Achieves speeds of up to 75 km/h in real-world tests.

Enables zero-shot transfer from high-fidelity simulation.

Abstract

Recently, Model Predictive Contouring Control (MPCC) has arisen as the state-of-the-art approach for model-based agile flight. MPCC benefits from great flexibility in trading-off between progress maximization and path following at runtime without relying on globally optimized trajectories. However, finding the optimal set of tuning parameters for MPCC is challenging because (i) the full quadrotor dynamics are non-linear, (ii) the cost function is highly non-convex, and (iii) of the high dimensionality of the hyperparameter space. This paper leverages a probabilistic Policy Search method - Weighted Maximum Likelihood (WML)- to automatically learn the optimal objective for MPCC. WML is sample-efficient due to its closed-form solution for updating the learning parameters. Additionally, the data efficiency provided by the use of a model-based approach allows us to directly train in a high-fidelity simulator, which in turn makes our approach able to transfer zero-shot to the real world. We validate our approach in the real world, where we show that our method outperforms both the previous manually tuned controller and the state-of-the-art auto-tuning baseline reaching speeds of 75 km/h.