Ethan K. Gordon

Ethan Headshot

I am a Postdoctoral Researcher at the University of Pennsylvania (GRASP) advised by Michael Posa in the DAIR Lab. With funding from the Boston Dynamic AI Institute, I am developing active exploration and online learning algorithms for dexterous manipulation with sparse (e.g. tactile) perception.

In 2023, I completed my PhD in the Personal Robotics Lab at the University of Washington, where I was advised by Siddhartha Srinivasa and collaborated with Tapomayukh Bhattacharjee. My dissertation involved developing online learning algorithms for tractably adaptable food manipulation with the primary application of robot-assisted feeding for those with mobility impairments. Previously, I received my BSE from Princeton University, where I studied neuromorphic silicon photonics with Paul Prucnal.

I have also had the pleasure to work on varifocal VR headsets at Meta (Oculus VR). In my spare time, I enjoy skiing, singing a cappella, and D&D.

What's New?

Apr 2024 Started at Michael Posa's DAIR Lab at UPenn
Apr 2024 Selected for the 2024 Husky 100!
Mar 2024 Best Demonstration Award at HRI 2024, Boulder, CO
Mar 2024 Running the HRI Pioneers Workshop at HRI 2024, Boulder, CO
Dec 2023 Defended my dissertation and received my PhD from UW!
Nov 2023 Presented at CoRL 2023, Atlanta, GA
Nov 2023 The Assistive Dexterous Arm (ADA) Feeding Demo is awarded the People's Choice Prize at UW Demo Day
Jun 2023 Awarded Best Poster at the Workshop on Assistive Manipulation at ICRA 2023, London, UK
Mar 2023 Awarded Best Design Paper at HRI 2023, Stockholm, SE
Jan 2023 Accepted as an HRI 2023 Pioneer, Stockholm, SE

Research

Robotic manipulation can advance the human condition in so many ways: from physical assistance for those with mobility impairments to construction tasks in dangerous environments to the fine grain motions of surgery. All of these tasks require the robot to adapt to previously-unseen and uncertain environments. Just as humans continuously build and refine our understanding of this world over time, a robot should be able to treat every second of deployment as a learning opportunity. My goal is to understand how to capitalize on these opportunities to make contact-rich dexterous manipulation as intuitive to robots as to people.

Select Publications


Towards General Single-Utensil Food Acquisition with Human-Informed Actions

Towards General Single-Utensil Food Acquisition with Human-Informed Actions

Ethan K. Gordon*, Amal Nanavati*, Ramya Challa, Bernie Hao Zhu, Taylor A. Kessler Faulkner, Siddhartha S. Srinivasa
Conference on Robot Learning (CoRL) 2023, Atlanta, GA, USA


Online augmentation of learned grasp sequence policies for more adaptable and data-efficient in-hand manipulation,

Online augmentation of learned grasp sequence policies for more adaptable and data-efficient in-hand manipulation,

Ethan K. Gordon, Rana Soltani-Zarrin
International Conference on Robotics and Automation (ICRA) 2023, London, UK


Design principles for robot-assisted feeding in social contexts

Design principles for robot-assisted feeding in social contexts

Amal Nanavati*, PatrĂ­cia Alves-Oliveira*, Tyler Schrenk, Ethan K. Gordon, Maya Cakmak, and Siddhartha S. Srinivasa
Conference on Human-Robot Interaction (HRI) 2023, Stockholm, Sweden
Best Design Paper


Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer

Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer

Suneel Belkhale, Ethan K. Gordon, Dorsa Sadigh, Tapomayukh Bhattacharjee, Siddhartha S. Srinivasa
International Conference on Robotics and Automation (ICRA) 2022, Philadelphia, PA, USA


Benchmarking Structured Policies and Policy Optimization for Dexterous Object Manipulation

Benchmarking Structured Policies and Policy Optimization for Dexterous Object Manipulation

Niklas Funk, Charles Schaff, Rishabh Madan, Takuma Yoneda, Julen Urain De Jesus, Joe Watson, Ethan K. Gordon, Felix Widmaier, Stefan Bauer, Siddhartha S. Srinivasa, Tapomayukh Bhattacharjee, Matthew R. Walter, Jan Peters
IEEE Robotics and Automation Letters (RA-L), SI: Robotic Grasping and Manipulation 2021


Leveraging Post Hoc Context for Faster Learning in Bandit Settings with Applications in Robot-Assisted Feeding

Leveraging Post Hoc Context for Faster Learning in Bandit Settings with Applications in Robot-Assisted Feeding

Ethan K. Gordon, Sumegh Roychowdhury, Tapomayukh Bhattacharjee, Kevin Jamieson, and Siddhartha S. Srinivasa
International Conference on Robotics and Automation (ICRA) 2021, Xi'an, China


Adaptive Robot-Assisted Feeding: An Online Learning Framework for Acquiring Previously-Unseen Food Items

Adaptive Robot-Assisted Feeding: An Online Learning Framework for Acquiring Previously-Unseen Food Items

Ethan K. Gordon, Xiang Meng, Tapomayukh Bhattacharjee, Matt Barnes, and Siddhartha S. Srinivasa
Conference on Intelligent Robots and Systems (IROS) 2020, Las Vegas, NV, USA


Is more autonomy always better? Exploring preferences of mobility-impaired users in robot-assisted feeding

Is more autonomy always better? Exploring preferences of mobility-impaired users in robot-assisted feeding

Tapomayukh Bhattacharjee, Ethan K. Gordon, Rosario Scalise, Maria E. Cabrera, Anat Caspi, Maya Cakmak, and Siddhartha S. Srinivasa
Conference on Human-Robot Interaction (HRI) 2020, Cambridge, UK


Robot-Assisted Feeding: Generalizing Skewering Strategies across Food Items on a Plate

Robot-Assisted Feeding: Generalizing Skewering Strategies across Food Items on a Plate

Ryan Feng, Younsun Kim, Gilwoo Lee, Ethan K. Gordon, Matt Schmittle, Shivaum Kuma, Tapomayukh Bhattacharjee, and Siddhartha S. Srinivasa
International Symposium on Robotics Research (ISRR) 2019, Hanoi, Vietnam