Kaiyu Zheng

I'm a first-year Ph.D. student at Brown University, advised by Stefanie Tellex in the H2R Lab. My research interests are in robotics, machine learning and artificial intelligence.

Graduated from the University of Washington in June 2018, with both M.S. and B.S. in Computer Science, and minor in Mathematics. At UW, I was a research assistant at the UW Neural Systems Lab, working with Andrzej Pronobis and Rajesh Rao from 2016 to 2018. In spring 2015, I worked on device integration of Myo at the UW Movement Control Lab, advised by Vikash Kumar and Emo Todorov. (CV)

My Chinese name is 郑开宇 (simplified), or 鄭開宇 (traditional).

Preprints

From Pixels to Buildings: End-to-end Probabilistic Deep Networks for Large-scale Semantic Mapping
Kaiyu Zheng, Andrzej Pronobis
International Conference on Robotics and Automation (ICRA) 2019, under review.
[project] [show abstract] [hide video]

Conference Papers

Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps
Kaiyu Zheng, Andrzej Pronobis, Rajesh P. N. Rao
AAAI Conference on Artificial Intelligence (AAAI 2018). oral presentation.
[pdf] [bibtex] [slides] [project] [show abstract] [hide video]

Workshop Papers

Learning Semantic Maps with Topological Spatial Relations Using Graph-Structured Sum-Product Networks
Kaiyu Zheng, Andrzej Pronobis, Rajesh P. N. Rao
IROS 2017 2nd Workshop on Machine Learning Methods for High-Level Cognitive Capabilities (ML-HLCR 2017).
[pdf] [bibtex] [project] [link to workshop]

Thesis

Learning Large-Scale Topological Maps Using Sum-Product Networks
Kaiyu Zheng
Senior Thesis, 2017
[pdf] [bibtex] [show abstract]
Shortlisted for the UW CSE Best Senior Thesis Award.

Resources

ROS Navigation Tuning Guide
Kaiyu Zheng, 2017.
[pdf] [bibtex] [ROS site] [hide video]

Projects

Forcasting Solar Irradiance by Learning from Time Series Data
Course project for CSE 546 (Machine Learning). Partnered with Kousuke Ariga*
Power generation from solar panels at a Photovoltaic (PV) power plant is directly proportional to solar irradiance, which depends on weather conditions. The goal of our project is to develop and analyze different machine learning methods to predict solar irradiance, leveraging a solar irradiance dataset. See abstract and report below.
[pdf] [show abstract]
Storage and Retrieval of Robotic Laser Range Data in Database Systems
Course project for CSE 544 (Database Systems). Partnered with Joshua Fan*
The goal of our project is to enable storing images of laser-range observations into a relational database, and retrieving similar images to a query image efficiently. We build a pipeline to extract image features and store them into a relational database following the Bag-of-Visual-Words model, and we implemented FIDS ("Flexible Image Database System") to speed up image retrieval, as well as Locality Sensitive Hashing to store data in a way that allows for faster retrieval. See abstract and report below.
[pdf] [show abstract]

Presentations

Probabilistic Semantic Mapping Using Graph-Structured Sum-Product Networks
Kaiyu Zheng, Andrzej Pronobis, Rajesh P. N. Rao
UW Computer Science & Engineering Industry Affiliates Research Day
— on 11/15/2017 in Seattle, WA, US.
[poster] [slides] [show abstract]
Learning Semantic Maps with Topological Spatial Relations Using Graph-Structured Sum-Product Networks
Kaiyu Zheng, Andrzej Pronobis, Rajesh P. N. Rao
IROS 2017 2nd Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics
— on 9/28/2017 in Vancouver, BC, Canada.
[poster] [slides] [show video]
Training Deep Probabilistic Models for Semantic Mapping with Mobile Robots
Kousuke Ariga*, Kaiyu Zheng*, Andrzej Pronobis
20th Undergraduate Research Symposium at the University of Washington, 2017
— on 5/19/2017 in Seattle, WA, US.
[poster] [show abstract]

More about Me

Email: kaiyu_zheng [at] brown [dot] edu

Github: zkytony

Dumping ground for more projects, writings, interests.