CaltechTHESIS
  A Caltech Library Service

Reliable Learning and Control in Dynamic Environments: Towards Unified Theory and Learned Robotic Agility

Citation

Shi, Guanya (2023) Reliable Learning and Control in Dynamic Environments: Towards Unified Theory and Learned Robotic Agility. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/8rz4-7b35. https://resolver.caltech.edu/CaltechTHESIS:08052022-231458463

Abstract

Recent breathtaking advances in machine learning beckon to their applications in a wide range of real-world autonomous systems. However, for safety-critical settings such as agile robotic control in hazardous environments, we must confront several key challenges before widespread deployment. Most importantly, the learning system must interact with the rest of the autonomous system (e.g., highly nonlinear and non-stationary dynamics) in a way that safeguards against catastrophic failures with formal guarantees. In addition, from both computational and statistical standpoints, the learning system must incorporate prior knowledge for efficiency and generalizability.

This thesis presents progress towards establishing a unified framework that fundamentally connects learning and control. First, Part I motivates the benefit and necessity of such a unified framework by the Neural-Control Family, a family of nonlinear deep-learning-based control methods with not only stability and robustness guarantees but also new capabilities in agile robotic control. Then Part II discusses three unifying interfaces between learning and control: (1) online meta-adaptive control, (2) competitive online optimization and control, and (3) online learning perspectives on model predictive control. All interfaces yield settings that jointly admit both learning-theoretic and control-theoretic guarantees.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Machine Learning, Control Theory, Robotics
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Control and Dynamical Systems
Awards:Ben P.C. Chou Doctoral Prize in IST, 2022. Simoudis Discovery Prize, 2020/2021. Rising Stars in Data Science, Autumn 2021 cohort.
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Chung, Soon-Jo (co-advisor)
  • Yue, Yisong (co-advisor)
Thesis Committee:
  • Burdick, Joel Wakeman (chair)
  • Wierman, Adam C.
  • Chung, Soon-Jo
  • Yue, Yisong
Defense Date:21 July 2022
Funders:
Funding AgencyGrant Number
DARPAUNSPECIFIED
RaytheonUNSPECIFIED
Center for Autonomous Systems and Technologies at CaltechUNSPECIFIED
Record Number:CaltechTHESIS:08052022-231458463
Persistent URL:https://resolver.caltech.edu/CaltechTHESIS:08052022-231458463
DOI:10.7907/8rz4-7b35
Related URLs:
URLURL TypeDescription
http://www.gshi.meAuthorPersonal website
https://ieeexplore.ieee.org/document/8794351PublisherArticle adapted for chapter 3
https://ieeexplore.ieee.org/document/9196800PublisherArticle adapted for chapter 4
https://ieeexplore.ieee.org/document/9508420PublisherArticle adapted for chapter 4
https://www.science.org/doi/10.1126/scirobotics.abm6597PublisherArticle adapted for chapter 5
https://ieeexplore.ieee.org/document/9290355PublisherArticle adapted for chapter 6
https://proceedings.mlr.press/v120/liu20a.htmlPublisherArticle adapted for chapter 6
https://ieeexplore.ieee.org/document/9561483PublisherArticle adapted for chapter 7
https://papers.nips.cc/paper/2021/hash/52fc2aee802efbad698503d28ebd3a1f-Abstract.htmlPublisherArticle adapted for chapter 9
https://papers.nips.cc/paper/2020/hash/ed46558a56a4a26b96a68738a0d28273-Abstract.htmlPublisherArticle adapted for chapter 10
https://dl.acm.org/doi/10.1145/3508037PublisherArticle adapted for chapter 10
https://papers.nips.cc/paper/2020/hash/155fa09596c7e18e50b58eb7e0c6ccb4-Abstract.htmlPublisherArticle adapted for chapter 11
https://papers.nips.cc/paper/2021/hash/298f587406c914fad5373bb689300433-Abstract.htmlPublisherArticle adapted for chapter 11
https://dl.acm.org/doi/10.1145/3508038PublisherArticle adapted for chapter 11
https://arxiv.org/abs/2010.11637arXivArticle adapted for chapter 11
ORCID:
AuthorORCID
Shi, Guanya0000-0002-9075-3705
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:14994
Collection:CaltechTHESIS
Deposited By: Guanya Shi
Deposited On:09 Aug 2022 23:46
Last Modified:16 Aug 2022 15:49

Thesis Files

[img] PDF - Final Version
See Usage Policy.

12MB

Repository Staff Only: item control page