Welcome!

I am currently pursuing my Ph.D. at the Agile Robotics and Perception Lab (ARPL) at New York University, under the guidance of Prof. Giuseppe Loianno. My research focuses on developing adaptive control systems for autonomous robots, integrating deep learning with control theory to solve real-world challenges. I hold Bachelor's and Master's degrees in Computer Engineering from the University of Padova, with research experience at the Robotics and Perception Group in Zurich and industry experience as a software engineer at Flexsight.

Research

Reactive Collision Avoidance

Quadrotor navigating through obstacles using real-time reactive collision avoidance framework

In dynamic environments, real-time collision avoidance is essential for safe robot navigation. Our framework integrates perception, planning, and control, using monocular depth estimation (MDE) to refine noisy RGB-D data in real-time. With nonlinear model predictive control (NMPC) and adaptive control barrier functions (CBFs), the system reacts to high-risk collision points in milliseconds, enabling agile navigation without prior tuning. Extensive tests show its ability to generalize across unknown environments, ensuring safe, real-time flight.

Dynamics Learning

By combining online learning with uncertainty-aware model predictive control, the learned dynamics actively adapt to multiple challenging operating conditions, enabling unprecedented flight control.

Model-based control needs an accurate system dynamics model to safely and precisely control robots in complex environments. This model should adapt to changing conditions. Our research introduces a self-supervised learning method that actively models nonlinear robotic systems' dynamics. We combine offline learning from past data and online learning from current interactions, making the process highly sample-efficient and adaptive. We also design an uncertainty-aware model predictive controller that considers data uncertainty to choose optimal control actions, improving both performance and learning efficiency.

Visual Tracking

Demonstrating our system's ability to detect, track, and navigate toward a running moving target in challenging outdoor environments.

Visual control allows quadrotors to navigate using real-time sensory data, but challenges like generalization, reliability, and real-time response remain. Our research addresses these issues with a new perception framework using foundation models for universal object detection and tracking. This framework, combined with a multi-layered tracker, ensures continuous target visibility despite motion blur, light changes, and occlusions. We also introduce a model-free visual controller for resilient tracking. Our system works efficiently with limited hardware, using only an onboard camera and an inertial measurement unit.

Perpetual Autonomy

AutoCharge, an autonomous charging system for quadrotors that is capable of universal, highly efficient, and robust charging.

Battery endurance is a major challenge for long-term autonomy and long-range aerial robot operations. Our solution, AutoCharge, addresses this with an autonomous charging system for quadrotors. AutoCharge combines a portable ground station with a lightweight, flexible charging tether for universal, efficient, and robust charging. We designed circular magnetic connectors for precise, orientation-agnostic connections between the ground station and tether. An electromagnet on the ground station increases tolerance to localization and control errors during docking, ensuring smooth undocking after charging.

Latest News

  • May, 2024. Will present in person at ICRA Agile Robotics workshop ✈️
  • May, 2024. Will present in person at ICRA Aerial Robotics workshop ✈️
  • May, 2024. Will present in person at ICRA 2024 conference in Yokohama ✈️
  • Jan, 2024. Paper article accepted at ICRA 2024 🦾
  • Nov, 2023. Journal article accepted at Transactions on Robotics 2023 🦾
  • Oct, 2023. Paper article featured on IEEE Spectrum 📺
  • Oct, 2023. Paper article accepted at ICAR 2023 🦾
  • Jun, 2023. AutoCharge featured on IEEE Spectrum 📺
  • May, 2023. Will present in person at ICRA Energy Efficient Aerial Robotics workshop ✈️
  • May, 2023. Will present in person at ICRA 2023 conference in London ✈️
  • May, 2023. Honored to have been awarded the Dr. Li Annual ECE Publication Award 🏆
  • Mar, 2023. Journal article accepted at Annual Reviews in Control 2023 🦾
  • Jan, 2023. AutoCharge and GaPT accepted at ICRA 2023 conference 🦾🦾
  • Oct, 2022. Will present virtually at IROS 2022 conference 📺
  • Jun, 2022. PI-TCN accepted at RAL+IROS 2022 🦾
  • May, 2022. Will present in person at ICRA 2022 conference in Philadelphia ✈️
  • Jan, 2022. AutoTune accepted at RAL+ICRA 2022 🦾
  • Aug, 2021. Joined Agile Robotics and Perception Lab 👨‍🎓