Ryan Hoque

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2024-69

May 9, 2024

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-69.pdf

Recent breakthroughs in deep learning have revolutionized natural language processing, computer vision, and robotics. Nevertheless, reliable robot autonomy in unstructured environments remains elusive. Without the Internet-scale data available for language and vision, robotics faces a unique chicken-and-egg problem: robot learning requires large datasets from deployment at scale, but robot learning is not yet reliable enough for deployment at scale. We propose a scalable human-in-the-loop learning paradigm as a potential solution to this paradox, and we argue that it is the key ingredient behind the recent growth of large-scale robot deployments in applications such as autonomous driving and e-commerce order fulfillment. We develop novel formalisms, algorithms, benchmarks, systems, and applications for this setting and evaluate its performance in extensive simulation and physical experiments.

This dissertation is composed of three complementary parts. In Part I, we propose novel algorithms and systems for interactive imitation learning, in which autonomous robots can actively query human supervisors for assistance when needed. In Part II, we introduce interactive fleet learning, which generalizes interactive imitation learning to multiple robots and multiple human supervisors. In Part III, we introduce and study systems for remote supervision of robot fleets over the Internet, enabling interactive fleet learning at a distance. Throughout this thesis, we design algorithms and systems with an emphasis on scalability in terms of the number of robots, number of humans, amount of human supervision required, dataset size, and distribution of physical locations. We conclude with a discussion of limitations and opportunities for future work.

Advisors: Ken Goldberg

---

BibTeX citation:

@phdthesis{Hoque:EECS-2024-69,
    Author= {Hoque, Ryan},
    Title= {Scalable Lifelong Imitation Learning for Robot Fleets},
    School= {EECS Department, University of California, Berkeley},
    Year= {2024},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-69.html},
    Number= {UCB/EECS-2024-69},
    Abstract= {Recent breakthroughs in deep learning have revolutionized natural language processing, computer vision, and robotics. Nevertheless, reliable robot autonomy in unstructured environments remains elusive. Without the Internet-scale data available for language and vision, robotics faces a unique chicken-and-egg problem: robot learning requires large datasets from deployment at scale, but robot learning is not yet reliable enough for deployment at scale. We propose a scalable human-in-the-loop learning paradigm as a potential solution to this paradox, and we argue that it is the key ingredient behind the recent growth of large-scale robot deployments in applications such as autonomous driving and e-commerce order fulfillment. We develop novel formalisms, algorithms, benchmarks, systems, and applications for this setting and evaluate its performance in extensive simulation and physical experiments. 

This dissertation is composed of three complementary parts. In Part I, we propose novel algorithms and systems for interactive imitation learning, in which autonomous robots can actively query human supervisors for assistance when needed. In Part II, we introduce interactive fleet learning, which generalizes interactive imitation learning to multiple robots and multiple human supervisors. In Part III, we introduce and study systems for remote supervision of robot fleets over the Internet, enabling interactive fleet learning at a distance. Throughout this thesis, we design algorithms and systems with an emphasis on scalability in terms of the number of robots, number of humans, amount of human supervision required, dataset size, and distribution of physical locations. We conclude with a discussion of limitations and opportunities for future work.},
}

EndNote citation:

%0 Thesis
%A Hoque, Ryan 
%T Scalable Lifelong Imitation Learning for Robot Fleets
%I EECS Department, University of California, Berkeley
%D 2024
%8 May 9
%@ UCB/EECS-2024-69
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2024/EECS-2024-69.html
%F Hoque:EECS-2024-69