In general, I'm interested in enabling autonomous robots to act intelligently, particularly in the context of planning hierarchically in the presence of uncertainty. Specifically, I work on developing/learning representations to enable long-horizon decision making for multi-modal robotics problems in partially observable, real-world domains. Before MIT, I studied Mechanical Engineering and Aerospace Engineering at the California Institute of Technology.
Reasoning over Hierarchical Abstractions for Long-Horizon Planning in Robotics
Christopher Bradley
PhD Thesis, MIT 2024
Committe: Nicholas Roy,
Luca Carlone,
George Konidaris,
Pulkit Agrawal
The unifying aim of the work in this thesis is to develop approaches which enable robots to solve complex tasks in large-scale, real-world environments without human intervention. Contributions demonstrate the importance of accounting for imperfection in hierarchical abstraction during planning in various robotics contexts.
Learning to Guide Search in Long-Horizon Task and Motion Planning
Christopher Bradley,
Nicholas Roy
CoRL 2022 Workshop on Learning, Perception, and Abstraction for Long-Horizon Planning
Using GNNs to learn to guide search within Task and Motion Planning.
Learning and Planning for Temporally Extended Tasks in Unknown Environments
Christopher Bradley,
Adam Pacheck,
Gregory J. Stein,
Sebastian Castro,
Hadas Kress-Gazit,
Nicholas Roy
ICRA 2021
Solving complex tasks specified with Linear Temporal Logic in partially explored environments.
A self driving license: Ensuring autonomous vehicles deliver on the promise of safer roads
Christopher Bradley*,
Victoria Preston*
MIT Science Policy Review, 2020
Thoughts on the development of regulations for self-driving cars.