# Learning Long-Horizon Predictions for Quadrotor Dynamics

arXiv: https://arxiv.org/abs/2407.12964 · HTML: https://mlsanity.com/paper/2407.12964/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 26 of 26)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Lagrangian Neural Networks](https://mlsanity.com/paper/2003.04630/) (2020)
- [Learning Continuous Control Policies by Stochastic Value Gradients](https://mlsanity.com/paper/1510.09142/) (2015)
- [Benchmarking Model-Based Reinforcement Learning](https://mlsanity.com/paper/1907.02057/) (2019)
- [Learning-based Model Predictive Control for Safe Exploration](https://mlsanity.com/paper/1803.08287/) (2018)
- [Model-Based Reinforcement Learning via Meta-Policy Optimization](https://mlsanity.com/paper/1809.05214/) (2018)
- [Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds](https://mlsanity.com/paper/2205.06908/) (2022)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [Combating the Compounding-Error Problem with a Multi-step Model](https://mlsanity.com/paper/1905.13320/) (2019)
- [Investigating Compounding Prediction Errors in Learned Dynamics Models](https://mlsanity.com/paper/2203.09637/) (2022)
- [Learning to Combat Compounding-Error in Model-Based Reinforcement Learning](https://mlsanity.com/paper/1912.11206/) (2019)
- [NeuroBEM: Hybrid Aerodynamic Quadrotor Model](https://mlsanity.com/paper/2106.08015/) (2021)
- [Data-Driven MPC for Quadrotors](https://mlsanity.com/paper/2102.05773/) (2021)
- [Multi-Step Prediction of Dynamic Systems with Recurrent Neural Networks](https://mlsanity.com/paper/1806.00526/) (2018)
- [Structured Mechanical Models for Robot Learning and Control](https://mlsanity.com/paper/2004.10301/) (2020)
- [Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning](https://mlsanity.com/paper/2012.09156/) (2020)
- [Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking](https://mlsanity.com/paper/2206.03305/) (2022)
- [Learning Quadrotor Dynamics Using Neural Network for Flight Control](https://mlsanity.com/paper/1610.05863/) (2016)
- [Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control](https://mlsanity.com/paper/2210.12583/) (2022)
- [Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding](https://mlsanity.com/paper/2402.03947/) (2024)
- [Temporal Convolutions for Multi-Step Quadrotor Motion Prediction](https://mlsanity.com/paper/2110.04182/) (2021)
- [QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images](https://mlsanity.com/paper/2211.16988/) (2022)
- [GaPT: Gaussian Process Toolkit for Online Regression with Application to Learning Quadrotor Dynamics](https://mlsanity.com/paper/2303.08181/) (2023)

## Built on by (most cited first, 1 of 1)

- [SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors](https://mlsanity.com/paper/2606.23444/) (2026)

## Abstract (arXiv)

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.