Yuhang Hu ๐ŸŒŸ

๐Ÿ‘จโ€๐ŸŽ“ PhD Student at the Creative Machines Lab at Columbia University, under the mentorship of Professor Hod Lipson.

๐Ÿ”ฌ Research Focus

My research revolves around robotics and artificial intelligence, with key interests in:

  • ๐Ÿค– Humanoid robots (legged robot, face robot and robot arm)
  • ๐Ÿ”„ Self-modeling robots (AI algorithm)
  • ๐Ÿง  Robot self-awareness (AI algorithm)

๐Ÿš€ Research Highlights

โœจ Here are some of my key projects and contributions:

  • Facial Robots ๐ŸŽญ
    Developed facial robots capable of dynamic human-like expressions through soft-skin modeling and self-supervised learning.

  • Self-Supervised Learning Framework ๐Ÿง‘โ€๐Ÿ’ป
    Designed a system that enables large models to:

    • ๐Ÿ› ๏ธ Identify robot configurations
    • ๐Ÿ‘๏ธ Control legged robots using egocentric visual self-models
    • ๐Ÿงน Understand and tidy messy environments by grasping the concept of tidiness

๐ŸŒ Vision

My long-term ambition is to enable robots to become lifelong learning machines through self-supervision. This vision aims to empower robots to:

  • โš™๏ธ Adapt quickly to new environments
  • ๐Ÿ”„ Transfer skills across different robotic platforms
  • ๐Ÿ“š Continuously acquire new abilitiesโ€”just like humans

๐Ÿ”ฅ News

The New York Times
sym

โ€˜Consciousnessโ€™ in Robots Was Once Taboo. Now Itโ€™s the Last Word.

๐Ÿ“„The New York Times

๐Ÿ“ Publications

Nature Machine Intelligence
sym

Teaching Robots to Build Simulations of Themselves

Robots now use raw video to build kinematic self-awareness, similar to how humans learn to dance by watching their mirror reflection. Our goal is a robot that understands its own body, adapts to damage, and learns new skills without constant human programming. In the new study, we developed a way for robots to autonomously model their 3D shapes using a single regular 2D camera. This breakthrough was driven by three brain-mimicking AI systems known as deep neural networks. These inferred 3D motion from 2D video, enabling the robot to understand and adapt to its movements. The new system could also identify alterations to the bodies of the robots, such as a bend in an arm, and help them adjust their motions to recover from this simulated damage.

Yuhang Hu, Jiong Lin, Hod Lipson

๐Ÿ†•Coverage ๐Ÿ“„PAPER

Science Robotics
sym

Human-robot facial coexpression

Humanoid robots are capable of mimicking human expressions by perceiving human emotions and responding after the human has finished their expression. However, a delayed smile can feel artificial and disingenuous compared with a smile occurring simultaneously with a companionโ€™s smile. We trained our anthropomorphic facial robot named Emo to display an anticipatory expression to match its human companion. Emo is equipped with 26 motors and flexible silicone skin to provide precise control over its facial expressions. The robot was trained with a video dataset of humans making expressions. By observing subtle changes in a human face, the robot could predict an approaching smile 839 milliseconds before the human smiled and adjust its face to smile simultaneously.

Yuhang Hu, Boyuan Chen, Jiong Lin, Yunzhe Wang, Yingke Wang, Cameron Mehlman, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

Project in 2020
sym

Mini Bidedal Robot

Design a legged robot starting from scratch, including CAD, electronics, embedding system, and deep reinforcement learning.

Yuhang Hu

๐ŸŽฌVIDEO

IROS 2024
sym

Reconfigurable Robot Identification from Motion Data

Can a robot autonomously understand and adapt to its physical form and functionalities through interaction with its environment? This question underscores the transition towards developing self-modeling robots without reliance on external sensory or pre-programmed knowledge about their structure. Here, we propose a meta- self-modeling that can deduce robot morphology through proprioception-the robotโ€™s internal sense of its bodyโ€™s position and movement. Our study introduces a 12-DoF reconfigurable legged robot, accompanied by a diverse dataset of 200k unique configurations, to systematically investigate the relationship between robotic motion and robot morphology.

Yuhang Hu, Yunzhe Wang, Ruibo Liu, Zhou Shen, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

arxiv
sym

Knolling Bot: Learning Robotic Object Arrangement from Tidy Demonstrations

๐Ÿค– Attention busy people! Imagine you are very busy and donโ€™t have time to tell the robot where everything should be placed!๐Ÿงน So, donโ€™t you think robots need to understand tidiness? ๐Ÿค”

This paper๐Ÿ“‘ shows how robots can learn the concept of โ€œknollingโ€ from tidy demonstrations, allowing them to automatically organize your table in a neat and efficient way. ๐Ÿงนโœจ

Yuhang Hu, Zhizhuo Zhang, Xinyue Zhu, Ruibo Liu, Philippe Wyder, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

arxiv
sym

Egocentric Visual Self-Modeling for Autonomous Robot Dynamics Prediction and Adaptation

We developed an approach that allows robots to learn their own dynamics using only a first-person camera view, without any prior knowledge! ๐ŸŽฅ๐Ÿ’ก

๐Ÿฆฟ Tested on a 12-DoF robot, the self-supervised model showcased the capabilities of basic locomotion tasks.

๐Ÿ”ง The robot can detect damage and adapt its behavior autonomously. Resilience! ๐Ÿ’ช

๐ŸŒ The model proved its versatility by working across different robot configurations!

๐Ÿ”ฎ This egocentric visual self-model could be the key to unlocking a new era of autonomous, adaptable, and resilient robots.

Yuhang Hu, Boyuan Chen, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

NeurIPS 2023 @ Robot Learning Workshop
sym

Enhancing Object Organization with Self-supervised Graspability Estimation

A robotic system that integrates visual perception, a self-supervised graspability estimation model, knolling models, and robot arm controllers to efficiently organize an arbitrary number of objects on a table, even when they are closely clustered or stacked.

Yuhang Hu, Zhizhuo Zhang, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

ICRA 2021
sym

Smile like you mean it: Driving animatronic robotic face with learned models

Eva 2.0: A physical humanoid face robot with soft skin โž• A vision-based self-supervised learning framework for facial mimicry.

Boyuan Chen, Yuhang Hu, Lianfeng Li, Sara Cummings, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

ICRA 2021
sym

Visual perspective taking for opponent behavior modeling

Humans learn at a young age to infer what others see and cannot see from a different point-of-view, and learn to predict othersโ€™ plans and behaviors. These abilities have been mostly lacking in robots, sometimes making them appear awkward and socially inept. Here we propose an end-to-end long-term visual prediction framework for robots to begin to acquire both these critical cognitive skills, known as Visual Perspective Taking (VPT) and Theory of Behavior (TOB).

Boyuan Chen, Yuhang Hu, Robert Kwiatkowski, Shuran Song, Hod Lipson

๐ŸŽฌVIDEO ๐Ÿ“„PAPER

Nature Nanotechnology
sym

Multiplexed reverse-transcriptase quantitative polymerase chain reaction using plasmonic nanoparticles for point-of-care COVID-19 diagnosis

Quantitative polymerase chain reaction (qPCR) offers the capabilities of real-time monitoring of amplified products, fast detection, and quantitation of infectious units, but poses technical hurdles for point-of-care miniaturization compared with end-point polymerase chain reaction. Here we demonstrate plasmonic thermocycling, in which rapid heating of the solution is achieved via infrared excitation of nanoparticles, successfully performing reverse-transcriptase qPCR (RT-qPCR) in a reaction vessel containing polymerase chain reaction chemistry, fluorescent probes and plasmonic nanoparticles. The method could rapidly detect SARS-CoV-2 RNA from human saliva and nasal specimens with 100% sensitivity and 100% specificity, as well as two distinct SARS-CoV-2 variants.

Nicole R Blumenfeld, Michael Anne E Bolene, Martin Jaspan, Abigail G Ayers, Sabin Zarrandikoetxea, Juliet Freudman, Nikhil Shah, Angela M Tolwani, Yuhang Hu, Terry L Chern, James Rogot, Vira Behnam, Aditya Sekhar, Xinyi Liu, Bulent Onalir, Robert Kasumi, Abdoulaye Sanogo, Kelia Human, Kasey Murakami, Goutham S Totapally, Mark Fasciano, Samuel K Sia

๐Ÿ“„PAPER