Federico Rossi
Jet Propulsion Laboratory - California Institute of Technology
Seminar Information
Teams of autonomous driving, swimming, and flying robots hold promise to revolutionize planetary and Earth science.
Networks of gas sensors are uniquely well-positioned to localize the source of observed methane emissions on Mars, which may suggest or disprove the presence of bacterial life on the red planet. On Venus, teams of altitude-controlled aerobots can shed light on the planet's geology by detecting volcanic eruptions and observing them up close. On our own planet, under-ice autonomous underwater vehicles are critical to measure the melting rate of Antarctic glaciers, grounding climate models; and commercial spacecraft constellations, coordinating autonomously, can provide time-sensitive inputs to humanitarian relief organizations right after volcanic eruptions and flooding.
To realize this vision, new autonomy tools and techniques are needed to coordinate robotic teams faster than ground-based operators can do. Algorithms must adapt to infrequent communication, tight power and computation budgets, and likely hardware failures; they must be provably safe, to protect the high-value assets hosting them; they must handle heterogeneous systems with diverse sensors and actuators; and their decisions must be interpretable by scientists.
In this talk, we will discuss algorithmic tools developed at JPL to address each of these challenges; learn how several of these tools were infused in the upcoming CADRE mission to the Moon's Reiner Gamma region; and conclude by speculating about the future of multi-agent systems for space exploration.
Dr. Federico Rossi is a Robotics Technologist with the Multi-Agent Robotics Group (358P) within the Robotics section of NASA’s Jet Propulsion Laboratory. He received a Ph.D. in Aeronautics and Astronautics at Stanford University under the guidance of Prof. Marco Pavone in 2018 with a thesis On the Interaction between Autonomous Mobility-on-Demand Systems and the Built Environment: Models and Large Scale Coordination Algorithms. Prior to that, Federico received a dual M.Sc. in Space Engineering from Politecnico di Milano and Politecnico di Torino, Italy, in 2013. He is an alumn of the Alta Scuola Politecnica. At JPL, Federico leads the multi-agent autonomy team for NASA’ Coordinated Autonomous Distributed Robotics Explorers (CADRE) mission, which will deliver a team of three autonomous rovers to the Moon’s Reiner Gamma region. Federico’s research focuses on decision-making under uncertainty in multi-agent robotic systems and operations of autonomous agents, with applications to planetary exploration and Earth science. At JPL, he has developed autonomy technologies for cooperative robotic exploration, joint orbit and observation optimization for exploration of small bodies, and under-ice navigation in Antarctica.