Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking

Alessandro Saviolo, Guanrui Li, Giuseppe Loianno

Research output: Contribution to journalArticlepeer-review


Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. The model needs to capture the system behavior in multiple flight regimes and operating conditions, including those producing highly nonlinear effects such as aerodynamic forces and torques, rotor interactions, or possible system configuration modifications. Classical approaches rely on handcrafted models and struggle to generalize and scale to capture these effects. In this letter, we present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions. In addition, physics constraints are embedded in the training process to facilitate the network's generalization capabilities to data outside the training distribution. Finally, we design a model predictive control approach that incorporates the learned dynamics for accurate closed-loop trajectory tracking fully exploiting the learned model predictions in a receding horizon fashion. Experimental results demonstrate that our approach accurately extracts the structure of the quadrotor's dynamics from data, capturing effects that would remain hidden to classical approaches. To the best of our knowledge, this is the first time physics-inspired deep learning is successfully applied to temporal convolutional networks and to the system identification task, while concurrently enabling predictive control.

Original languageEnglish (US)
Pages (from-to)10256-10263
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number4
StatePublished - Oct 1 2022


  • Aerial Systems
  • Aerodynamics
  • Mathematical models
  • Model Learning for Control
  • Neural networks
  • Optimization and Optimal Control
  • Predictive models
  • Robot Learning
  • System dynamics
  • Training
  • Vehicle dynamics
  • optimization and optimal control
  • model learning for control
  • robot learning
  • Aerial systems

ASJC Scopus subject areas

  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Computer Science Applications


Dive into the research topics of 'Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking'. Together they form a unique fingerprint.

Cite this