Michael Bosello

Michael Bosello

Senior Researcher, Ph.D. Student

Technology Innovation Institute

University of Bologna

Biography

Michael Bosello is a Ph.D. student at the University of Bologna - Department of Computer Science and Engineering (DISI), and a senior researcher at the Technology Innovation Institute - Autonomous Robotics Research Center (ARRC) in Abu Dhabi. Previously, he has been a research fellow at the University of Bologna.

Mr. Bosello holds the Master’s in Computer Science and Engineering granted by the University of Bologna with Honours. He was awarded multiple funding among research grants and scholarships.

Mr. Bosello’s core research interests are Reinforcement Learning, Deep Learning, and Robotics as the main application domain. He authored several peer-reviewed papers in the field and contributed to international journals and conferences. He also served as a reviewer and TPC member for international journals and conferences. He designed a framework to integrate Reinforcement Learning with BDI agent reasoning. More recently, he worked on autonomous driving, autonomous car racing, and autonomous drone racing.

Interests
  • Reinforcement Learning
  • Deep Learning
  • Autonomous Robotics
Education

  • PhD in Automotive Engineering for Intelligent Mobility, ongoing

    University of Bologna

  • MEng in Computer Science and Engineering, 2020

    University of Bologna

  • BSc in Computer Science and Engineering, 2017

    University of Bologna

Experience

 
 
 
 
 
Technology Innovation InstituteAutonomous Robotics Research Center
Senior Researcher
Technology Innovation Institute
Autonomous Robotics Research Center
April 2024 – Present Abu Dhabi, UAE
Autonomous Drone Racing
 
 
 
 
 
Technology Innovation InstituteAutonomous Robotics Research Center
Researcher
Technology Innovation Institute
Autonomous Robotics Research Center
November 2022 – March 2024 Abu Dhabi, UAE
 
 
 
 
 
Technology Innovation InstituteAutonomous Robotics Research Center
Intern
Technology Innovation Institute
Autonomous Robotics Research Center
July 2022 – October 2022 Abu Dhabi, UAE
 
 
 
 
 
University of BolognaDepartment of Computer Science and Engineering
Research Fellow
University of Bologna
Department of Computer Science and Engineering
November 2020 – October 2021 Cesena, Italy
  • Using machine learning techniques to estimate and predict the status of batteries
  • Leading a small team that works on autonomous driving with both simulated and real 1/10 scale cars, aiming to win the f1tenth competition

Projects

.js-id-autonomous-robotics
All RL DL Robotics
Autonomous Drone Racing
Development of a software stack based on ROS2 for autonomous drone racing, and deployment on custom quadrotors. The stack implements the pipeline for motion capture-based and vision-based autonomous high-speed flight on complex tracks. More info here.
PDF Code Video
Autonomous Drone Racing
F1tenth-RL
LIDAR data are used as input of a Deep Q-Network on a realistic 1/10 scale car prototype controlled by ROS. The robot-driver learns how to run in race tracks by exploiting the experience gained through a mechanism of rewards that allow the agent to learn without human supervision
PDF Code Slides Video DOI
F1tenth-RL
Battery State Estimation
Using deep LSTMs and Autoencoders to estimate the State of Charge and the Remaining Useful Life of batteries.
SoC PDF SoC Code SoC DOI RUL PDF RUL Code RUL DOI
Battery State Estimation
Jason-RL
Integrating Belief-Desire-Intention agents and RL, i.e., integrating planning and learning. The framework has been tested on a simulated urban scenario based on f1tenth, where BDI plans are used for high-level path planning and RL for low-level control.
PDF Code Slides DOI Seminar F1tenth-RL-BDI PDF F1tenth-RL-BDI Code F1tenth-RL-BDI Slides F1tenth-RL-BDI Video
Jason-RL

Selected Publications

See all publications here.

Race Against the Machine: A Fully-Annotated, Open-Design Dataset of Autonomous and Piloted High-Speed Flight
IEEE Robotics and Automation Letters
Michael Bosello, Davide Aguiari, Yvo Keuter, Enrico Pallotta, Sara Kiade, Gyordan Caminati, Flavio Pinzarrone, Junaid Halepota, Jacopo Panerati, Giovanni Pau
PDF Cite Code Dataset Project Slides Video DOI
Race Against the Machine: A Fully-Annotated, Open-Design Dataset of Autonomous and Piloted High-Speed Flight
To Charge or to Sell? EV Pack Useful Life Estimation via LSTMs, CNNs, and Autoencoders
Energies
Michael Bosello, Carlo Falcomer, Claudio Rossi, Giovanni Pau
PDF Cite Code Project DOI
To Charge or to Sell? EV Pack Useful Life Estimation via LSTMs, CNNs, and Autoencoders
Train in Austria, Race in Montecarlo: Generalized RL for Cross-Track F1tenth LIDAR-Based Races
IEEE, 19th Annual Consumer Communications & Networking Conference (CCNC 2022)
Michael Bosello, Rita Tse, Giovanni Pau
PDF Cite Code Project Slides Video DOI
Train in Austria, Race in Montecarlo: Generalized RL for Cross-Track F1tenth LIDAR-Based Races
From Programming Agents to Educating Agents – A Jason-Based Framework for Integrating Learning in the Development of Cognitive Agents
Springer, 7th International Workshop on Engineering Multi-Agent Systems (EMAS 2019)
Michael Bosello, Alessandro Ricci
PDF Cite Code Project Slides DOI
From Programming Agents to Educating Agents – A Jason-Based Framework for Integrating Learning in the Development of Cognitive Agents

Media

See all media here.

Oct 23, 2024
Our Autonomous Drone Project on CNN International
Our Autonomous Drone Project on CNN International

Dr. Najwa A. CEO of TII, joined CNN’s Becky Anderson to explore AI-powered autonomous systems and the game-changing impact of AI in every aspect of our lives. These innovations are reshaping industries and everyday experiences. The UAE is at the forefront, harnessing AI to drive the next wave of fast mobility autonomous systems and smart solutions.

Project Video
Oct 18, 2024
Human vs AI Drone Racing at IROS 2024
Human vs AI Drone Racing at IROS 2024

Honored to go head-to-head against a professional drone racing champion in a live drone racing demo at @IROS2024. Congratulations to the Technology Innovation Institute Drone Racing Team for this incredible achievement. Red=Human; Purple=Autonomous

Project Video
Oct 1, 2024
2024 Achievements Recap - From Human vs AI to Dodging Obstacles
2024 Achievements Recap - From Human vs AI to Dodging Obstacles

TII’s autonomous drones blend AI-driven vision, and reinforcement learning, pushing the boundaries of speed without external localization systems, and with no external localization systems used for training. This is more than advanced flight – it’s a redefinition of how we move with drones. Where limits are meant to be broken, that’s where you’ll find us. Join us as we redefine flight.

Project Video
Jul 30, 2024
Meet Michael Bosello PhD Student - Autonomous Drone Racing
Meet Michael Bosello PhD Student - Autonomous Drone Racing

In the series of interviews “Meet UniBo PhD Students”. At Abu Dhabi’s Autonomous Robotics Research Center, Michael’s team is bringing innovations to the field of drone racing. Their goal? Developing a drone capable of autonomous flight, matching human pilot skills.

Project Video
Oct 23, 2021
F1tenth-RL Project in the National Italian TV
F1tenth-RL Project in the National Italian TV

Coverage of the F1tenth-RL project in the RAI 1 TV show “Linea Verde”.

Project Video

Teaching

See all teaching and seminars here.

Smart Vehicular Systems 2021 (Master’s)
Smart Vehicular Systems (SVS) lab: Autonomous Driving Intro, ROS, rospy
Michael Bosello
Jan 1, 2021
Slides SVS01 Slides SVS02 Slides SVS03 Slides CarFi Slides SVS-projects
Autonomous Driving and Reinforcement Learning – an Introduction
Introduction to Reinforcement Learning for Autonomous Driving
Michael Bosello
Jan 1, 2020
Slides

News

  • TII Racing qualified for the A2RL Drone Challenge Finale
  • TII Racing showcased incredible autonomous drone racing at the F1 Fanzone
  • Drone racing demonstration and paper presentation at IROS 2024, Abu Dhabi, UAE
  • The A2RL Autonomous Drone Race has been announced
  • The first race of the Abu Dhabi Autonomous Racing League (A2RL) has been an historical moment for autonomous racing. Proud to have been a witness of the race and its organization. Yas Marina Circuit, Abu Dhabi, UAE
  • In the backstage of The Stig vs AI
  • Presenting our WIP paper at CDC 2023, online
  • See you at IROS 2023, Detroit, US
  • Competing at ICRA 2022 DodgeDrone Challenge: Vision-based Agile Drone Flight
  • See you at ICRA 2022, Philadelphia, US
  • See you at PerCom 2022, online
  • Presenting our paper at IEEE CCNC 2022, online
  • See you at NeurIPS 2021, online
  • Presenting our paper at GoodIT 2021, Rome, Italy
  • Presenting our paper at GoodTechs 2020, online
  • Presenting our paper at IEEE MSN 2019, Shenzhen, China
  • Presenting our paper at EMAS 2019, Montreal, Canada
  • See you at AAMAS 2019, Montreal, Canada

Professional Activities

  • [2024] Reviewer – Conference

    IEEE International Conference on Robotics and Automation (ICRA 2025)

  • [2024] Reviewer – Journal

    International Journal of Dynamics and Control

  • [2023–2024] Reviewer – Conference

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023, 2024)

  • [2023-2024] Reviewer – Journal

    IEEE Robotics and Automation Letters (RA-L)

  • [2021–2023] TPC Member and Reviewer – Conference

    IEEE Consumer Communications and Networking Conference (CCNC 2022, 2023, 2024)

  • [2021-2022] Reviewer – Journal

    Network Modeling Analysis in Health Informatics and Bioinformatics (NetMAHIB)

Scholarships

  • [2022] Grant for abroad research, Marco Polo program, University of Bologna
  • [2021–2024] PhD Scholarship, CEMI Mobility Technology Holding Limited
  • [2020–2021] Research grant, University of Bologna

Contact

  • michael.bosello (at) tii (dot) ae