Ademiloluwa Adeniji

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2025-200

December 16, 2025

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-200.pdf

Robots remain far behind humans in their ability to learn broadly from the world. While large language and vision models have achieved remarkable generalization by training on the collective artifacts of human activity, robot learning continues to depend on narrowly curated, robot-collected datasets and hand-designed objectives. This dissertation explores an alternative paradigm in which robots learn directly from human experience, using the physical interactions, perceptions, and decisions of people in everyday life as a scalable source of supervision.

Advisors: Pieter Abbeel

---

BibTeX citation:

@phdthesis{Adeniji:EECS-2025-200,
    Author= {Adeniji, Ademiloluwa},
    Editor= {Abbeel, Pieter and Levine, Sergey and Goldberg, Ken},
    Title= {Toward Robots that Learn from Everyday Human Experience},
    School= {EECS Department, University of California, Berkeley},
    Year= {2025},
    Month= {Dec},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-200.html},
    Number= {UCB/EECS-2025-200},
    Abstract= {Robots remain far behind humans in their ability to learn broadly from the world. While large language and vision models have achieved remarkable generalization by training on the collective artifacts of human activity, robot learning continues to depend on narrowly curated, robot-collected datasets and hand-designed objectives. This dissertation explores an alternative paradigm in which robots learn directly from human experience, using the physical interactions, perceptions, and decisions of people in everyday life as a scalable source of supervision.},
}

EndNote citation:

%0 Thesis
%A Adeniji, Ademiloluwa 
%E Abbeel, Pieter 
%E Levine, Sergey 
%E Goldberg, Ken 
%T Toward Robots that Learn from Everyday Human Experience
%I EECS Department, University of California, Berkeley
%D 2025
%8 December 16
%@ UCB/EECS-2025-200
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-200.html
%F Adeniji:EECS-2025-200