Learning Long-Horizon Predictions for Quadrotor Dynamics

TL;DR

This paper investigates methods for improving long-horizon prediction accuracy in quadrotor dynamics modeling, emphasizing sequential architectures and a novel decoupled learning approach to reduce compounding errors.

Contribution

It introduces a decoupled dynamics learning method and analyzes key design choices, advancing long-term predictive modeling for quadrotor control.

Findings

Sequential models outperform other architectures in minimizing errors.

The proposed decoupled approach simplifies learning and improves modularity.

Experiments confirm enhanced long-term prediction accuracy on real data.

Abstract

Accurate modeling of system dynamics is crucial for achieving high-performance planning and control of robotic systems. Although existing data-driven approaches represent a promising approach for modeling dynamics, their accuracy is limited to a short prediction horizon, overlooking the impact of compounding prediction errors over longer prediction horizons. Strategies to mitigate these cumulative errors remain underexplored. To bridge this gap, in this paper, we study the key design choices for efficiently learning long-horizon prediction dynamics for quadrotors. Specifically, we analyze the impact of multiple architectures, historical data, and multi-step loss formulation. We show that sequential modeling techniques showcase their advantage in minimizing compounding errors compared to other types of solutions. Furthermore, we propose a novel decoupled dynamics learning approach, which further simplifies the learning process while also enhancing the approach modularity. Extensive experiments and ablation studies on real-world quadrotor data demonstrate the versatility and precision of the proposed approach. Our outcomes offer several insights and methodologies for enhancing long-term predictive accuracy of learned quadrotor dynamics for planning and control.