Embedded Files
Creating future aviation systems with safe, trustworthy machine learning in the loop
Creating future aviation systems with safe, trustworthy machine learning in the loop
We are a multi-institution team from Stanford, UC Berkeley, MIT, Georgia Tech, University of New Mexico, Raytheon, Hampton University, and MIT Lincoln Laboratory selected by NASA's University Leadership Initiative to build safe, efficient autonomous aviation systems.
We are a multi-institution team from Stanford, UC Berkeley, MIT, Georgia Tech, University of New Mexico, Raytheon, Hampton University, and MIT Lincoln Laboratory selected by NASA's University Leadership Initiative to build safe, efficient autonomous aviation systems.
Research Thrusts
Research Thrusts
Future autonomous aviation systems, such as cyber-taxis, are expected to complete millions of flights per day. These systems have the potential to significantly benefit from machine-learning-enabled components for enhanced perception, decision-making, and control that outperform their traditional, non-learning based counterparts. Despite the promise of deploying machine learning (ML) in future aviation systems, today's ML methods remain poor at generalizing to unseen conditions and lack formal safety guarantees. Our goal is to develop safe, trustworthy, and robust ML methods that will usher in a new level of autonomy in the national airspace.
Future autonomous aviation systems, such as cyber-taxis, are expected to complete millions of flights per day. These systems have the potential to significantly benefit from machine-learning-enabled components for enhanced perception, decision-making, and control that outperform their traditional, non-learning based counterparts. Despite the promise of deploying machine learning (ML) in future aviation systems, today's ML methods remain poor at generalizing to unseen conditions and lack formal safety guarantees. Our goal is to develop safe, trustworthy, and robust ML methods that will usher in a new level of autonomy in the national airspace.
Safety Assurances for Aviation Systems
Safety Assurances for Aviation Systems
We are building algorithms to verify deep neural network perception and planning modules for robust generalization in real-world flight conditions.
We are building algorithms to verify deep neural network perception and planning modules for robust generalization in real-world flight conditions.
Run-Time Fault Detection, Isolation, and Recovery
Run-Time Fault Detection, Isolation, and Recovery
We will build algorithms that continuously monitor when machine learning-enabled components (LECs) are uncertain, and seamlessly transfer control to trusted software.
We will build algorithms that continuously monitor when machine learning-enabled components (LECs) are uncertain, and seamlessly transfer control to trusted software.
Airspace Management
Airspace Management
We will develop tools and methods to extend vehicle-centric assurances to fleets of vehicles in the national airspace.
We will develop tools and methods to extend vehicle-centric assurances to fleets of vehicles in the national airspace.
Team Members
Team Members
Our team comprises a diverse set of researchers from Stanford, UC Berkeley, MIT, Georgia Tech, University of New Mexico, Raytheon, Hampton University, and MIT Lincoln Laboratory.
Our team comprises a diverse set of researchers from Stanford, UC Berkeley, MIT, Georgia Tech, University of New Mexico, Raytheon, Hampton University, and MIT Lincoln Laboratory.
Investigators
Investigators
Marco Pavone (PI)
Marco Pavone (PI)
Associate Professor, Stanford Aeronautics and Astronautics
Associate Professor, Stanford Aeronautics and Astronautics
Mykel Kochenderfer
Mykel Kochenderfer
Associate Professor, Stanford Aeronautics and Astronautics
Associate Professor, Stanford Aeronautics and Astronautics
Mac Schwager
Mac Schwager
Assistant Professor, Stanford Aeronautics and Astronautics
Assistant Professor, Stanford Aeronautics and Astronautics
Hamsa Balakrishnan
Hamsa Balakrishnan
Professor, MIT Aeronautics and Astronautics
Professor, MIT Aeronautics and Astronautics
Chuchu Fan
Chuchu Fan
Assistant Professor, MIT Aeronautics and Astronautics
Assistant Professor, MIT Aeronautics and Astronautics
Kevin Leahy
Kevin Leahy
Member of Technical Staff, MIT Lincoln Lab
Member of Technical Staff, MIT Lincoln Lab
Meeko Oishi
Meeko Oishi
Professor, University of New Mexico ECE
Professor, University of New Mexico ECE
Zhao Sun
Zhao Sun
Assistant Professor, Hampton University
Assistant Professor, Hampton University
Frank Dellaert
Frank Dellaert
Professor, Georgia Tech School of Interactive Computing
Professor, Georgia Tech School of Interactive Computing
Panagiotis Tsiotras
Panagiotis Tsiotras
Professor, Georgia Tech Aerospace Engineering
Professor, Georgia Tech Aerospace Engineering
Claire Tomlin
Claire Tomlin
Professor, UC Berkeley EECS
Professor, UC Berkeley EECS
Alessandro Pinto
Alessandro Pinto
Technical Fellow, Embedded AI, Raytheon Technologies
Technical Fellow, Embedded AI, Raytheon Technologies
Join Our Team!
Join Our Team!
We welcome applications from prospective postdoctoral scholars, graduate students, and undergraduate research interns. Please contact any principal investigator for openings.
We welcome applications from prospective postdoctoral scholars, graduate students, and undergraduate research interns. Please contact any principal investigator for openings.
Page updated
Google Sites
Report abuse