Learning Large-scale Multi-agent Control with Safety Certificates
Name
Qin-qinzy-SM-AeroAstro-2022-thesis.pdf
Description
Thesis PDF
Size
3.95 MB
Format
Adobe PDF
Checksum (MD5)
f586e6eafe719c4170bff73054c51d00
Author(s)
Qin, Zengyi
Advisor(s)
How, Jonathan P.
Date Issued
September 2022
Publisher
Massachusetts Institute of Technology
Abstract
Multi-agent intelligence in autonomous systems has been fascinating roboticists for decades. The recent advances in machine learning has created unprecedented opportunities for achieving ultimate multi-agent intelligence and full autonomy in a data-driven way. However, a fundamental bottleneck of machine learning-based methods is their safety and reliability in controlling the autonomous system at large scale, due to the lack of formal safety guarantee. In addressing these challenges, we develop: (1) An machine learning-based large-scale multi-agent control framework with safety certificates, which simultaneously enjoys the versatility of machine learning and the assurance of safety. (2) A multi-agent trajectory tracking framework with convergence and safety guarantees. (3) A general method to learn safe controllers for black-box systems with unknown dynamics. Comprehensive experiments have shown that the proposed methods have notable performance in terms of safety rate, task completion rate, computational efficiency and large-scale scalability.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
