Davide Celestini

Davide Celestini

Auto-generated profile, based on publicly available information

Davide Celestini

Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Torino, Italy

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 September 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
DCDavide Celestini
Davide Celestini
DGDaniele Gammelli
Daniele Gammelli
TGTommaso Guffanti
Tommaso Guffanti
SDSimone D'Amico
Simone D'Amico
Elisa CapelloElisa Capello
Elisa Capello
MPMarco Pavone
Marco Pavone
Model predictive control (MPC) has established itself as the primary methodology for constrained control, enabling general-purpose robot autonomy in diverse real-world scenarios. However, for most problems of interest, MPC relies on the recursive solution of highly non-convex trajectory optimization problems, leading to high computational complexity and strong dependency on initialization. In this work, we present a unified framework to combine the main strengths of optimization-based and learning-based methods for MPC. Our approach entails embedding high-capacity, transformer-based neural network models within the optimization process for trajectory generation, whereby the transformer provides a near-optimal initial guess, or target plan, to a non-convex optimization problem. Our experiments, performed in simulation and the real world onboard a free flyer platform, demonstrate the capabilities of our framework to improve MPC convergence and runtime. Compared to purely optimization-based approaches, results show that our approach can improve trajectory generation performance by up to 75%, reduce the number of solver iterations by up to 45%, and improve overall MPC runtime by 7x without loss in performance.

18 July 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
DCDavide Celestini
Davide Celestini
SPStefano Primatesta
Stefano Primatesta
Elisa CapelloElisa Capello
Elisa Capello
In this paper, a 3D trajectory planner for Unmanned Aerial Vehicles (UAVs) based on Interfered Fluid Dynamical System (IFDS) and Bézier curves is introduced. The proposed strategy joints the potentialities of IFDS with the use of Bézier curves to obtain optimized trajectories with continuous curvature. While IFDS computes an initial trajectory to safely avoid fixed and dynamic obstacles, Bézier curve optimization generates a trajectory satisfying kinematic constraints. This combination is computationally efficient for online applications with limited hardware and a smoothed path is obtained, for safe and flyable trajectories. Simulations are performed for a fixed-wing UAV in a complex and dynamic environment.