Brian Okorn

I am a robotics research scientist at The AI Institute focusing on robotic perception and learning as it applies to object centric manipulation. My goal is to develop vision systems that allow robots to interact intelligently with novel objects and learn easily from human interaction.

I received my PhD at the CMU Robotics Institute as part of the R-PaD Lab where I developed zero-shot, and self-supervised methods of learning pose estimation, object detection, and scene flow prediction. Prior to CMU, I worked as a researcher in the Unmanned Systems Branch of the Naval Information Warfare Center (NIWC) Pacific, formerly SPAWAR System Center Pacific, developing perception algorithms for surface, underground, and littoral robots and have worked on vision systems for the NASA Robonaut with the Johnson Space Center under the NSTRF Fellowship.

Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  CV

profile photo

Research

My research centers on object-centric vision for manipulation with a focus on zero-shot and self-supervised methods.

project image

TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation


Chuer Pan*, Brian Okorn*, Harry Zhang*, Ben Eisner*, David Held
Conference on Robot Learning (CoRL), 2022
[PDF] [Project Page] [Video]

project image

Deep Projective Rotation Estimation through Relative Supervision


Brian Okorn*, Chuer Pan*, Martial Hebert, David Held
Conference on Robot Learning (CoRL), 2022
[PDF] [Project Page] [Video]

project image

OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimation


Qiao Gu, Brian Okorn, David Held
Robotics and Automation Letters (RA-L) with presentation at the International Conference of Robotics and Automation (ICRA), 2022
[PDF] [Video] [Long Video] [Code]

project image

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement


Ankit Goyal, Arsalan Mousavian, Chris Paxton, Yu-Wei Chao, Brian Okorn, Jia Deng, Dieter Fox
Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[PDF] [Project Page]

project image

Object Pose Estimation without Direct Supervision


Brian Okorn
PhD Thesis, 2022
[PDF]

project image

Self-Supervised Point Cloud Completion via Inpainting


Himangi Mittal, Brian Okorn, Arpit Jangid, David Held
British Machine Vision Conference (BMVC), 2021
[PDF] [Project Page] [Video]

project image

ZePHyR: Zero-shot Pose Hypothesis Rating


Brian Okorn*, Qiao Gu*, Martial Hebert, David Held
International Conference of Robotics and Automation (ICRA), 2021
[PDF] [Project Page] [Video] [Long Video] [Code]

project image

Visual Self-Supervised Reinforcement Learning with Object Reasoning


Yufei Wang*, Gautham Narayan Narasimhan*, Xingyu Lin, Brian Okorn, David Held
Conference on Robot Learning (CoRL), 2020
[PDF] [Project Page] [Code]

project image

Learning Orientation Distributions for Object Pose Estimation


Brian Okorn, Mengyun Xu, Martial Hebert, David Held
International Conference on Intelligent Robots and Systems (IROS), 2020
[PDF] [Project Page] [Video]

project image

Cloth Region Segmentation for Robust Grasp Selection


Jianing Qian*, Thomas Weng*, Luxin Zhang, Brian Okorn, David Held
International Conference on Intelligent Robots and Systems (IROS), 2020
[PDF] [Project Page]

project image

Just Go with the Flow: Self-Supervised Scene Flow Estimation


Himangi Mittal, Brian Okorn, David Held
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[PDF] [Project Page] [Teaser Video] [Video] [Code]

project image

Learning Adaptive Sampling Distributions for Motion Planning by Self-Imitation


Ratnesh Madaan, Sam Zeng, Brian Okorn, Sebastian Scherer
International Conference on Intelligent Robots and Systems (IROS), Workshop on Machine Learning in Robot Motion Planning, 2018
[PDF]

project image

Counter Tunnel Exploration, Mapping, and Localization with an Unmanned Ground Vehicle


Jacoby Larson, Brian Okorn, Tracy Pastore, David Hooper, Jim Edwards
SPIE Unmanned Systems Technology, 2014
[PDF]

project image

Ego-Motion Estimation on Range Images using High-Order Polynomial Expansion


Brian Okorn, Josh Harguess
Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W), 2014
[PDF]

project image

Smuggling Tunnel Mapping using Slide Image Registration


Brian Okorn
Master’s Thesis, 2011
[PDF]

project image

Toward Automated Modeling of Floor Plans


Brian Okorn, Xuehan Xiong, Burcu Akinci, Daniel Huber
3D Data Processing, Visualization and Transmission Conference (3DPVT), 2010
[PDF]

project image

Using Laser Scanners for Modeling and Analysis in Architecture, Engineering, and Construction


Daniel Huber, Burcu Akinci, Pingbo Tang, Antonio Adan, Brian Okorn, Xuehan Xiong
Conference on Information Sciences and Systems (CISS), 2010
[PDF]





Design and source code from Leo Keselman's website, originally from Jon Barron's website