William Shen

I'm a PhD student in Computer Science at MIT CSAIL, advised by Leslie Kaelbling and Tomás Lozano-Pérez. I also collaborate with Phillip Isola and others in the Embodied Intelligence group.

I am interested in planning and perception for robotics, and how we can enable robots to reason about long-horizon tasks and generalize in the real-world.

I was previously a software engineer at Amazon Web Services, and completed my undergraduate degree at the Australian National University. I'm originally from New Zealand 🇳🇿.

You can contact me on my email willshen@mit.edu.

Google Scholar  /  GitHub  /  Twitter  /  LinkedIn

profile photo
Recent News

[ More ]

Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
William Shen*, Ge Yang*, Alan Yu, Jansen Wong, Leslie Pack Kaelbling, Phillip Isola
Conference on Robot Learning (CoRL), 2023 (Best Paper Award)
arXiv / website / code / video

We distill features from 2D foundation models into 3D feature fields, and enable few-shot language-guided manipulation that generalizes across object poses, shapes, appearances and categories.

Also presented at the CVPR 2023 Workshop on 3D Vision and Robotics .

Learning Domain-Independent Planning Heuristics with Hypergraph Networks
William Shen, Felipe Trevizan, Sylvie Thiébaux
International Conference on Automated Planning and Scheduling (ICAPS), 2020
pdf / bib / code / video

We present STRIPS-HGN, the first approach capable of learning domain-independent planning heuristics from scratch using hypergraph neural networks.

Also presented at the AAAI GenPlan20 workshop.

Guiding Search with Generalized Policies for Probabilistic Planning
William Shen, Felipe Trevizan, Sam Toyer, Sylvie Thiébaux, Lexing Xie
Symposium on Combinatorial Search (SoCS), 2019
pdf / bib / slides

We combine generalized neural network policies (Action Schema Networks) with search algorithms (MCTS) to exploit the strengths and overcome the weaknesses of each to solve probabilistic planning problems.

Also presented at the ICAPS HSDIP'19 workshop.

Thesis and Reports
Learning Heuristics for Planning with Hypergraph Networks
William Shen,
Honours Thesis, 2019
pdf / bib / slides

We introduce STRIPS-HGN, a hypergraph neural network capable of learning domain-independent planning heuristics by exploiting the structure induced by the delete relaxation of a planning problem. Our learned heuristics generalize across initial and goal states, problem sizes, and even domains.

Action Schema Networks with Monte-Carlo Tree Search: The Best of Both Worlds
William Shen,
Undergraduate Research Report, 2018
pdf / bib

We introduce novel techniques which leverage Action Schema Networks (ASNets) to perform simulations in Monte-Carlo Tree Search (MCTS), and in the selection phase of MCTS. We show that these synergies improve suboptimal learning, robustness and planning performance.


William Shen — Website Template