Patrick Grady

Research Scientist at Meta Reality Labs

prof_pic.jpg

Hi! My name is Patrick; I’m currently a research scientist at Meta Reality Labs in Seattle, WA. I work on computer vision for understanding hands. Before joining Meta, I finished a PhD in the Robotics department at the Georgia Institute for Technology. I was advised by Charlie Kemp and James Hays. My research was in computer vision and robotics, and my work focused on understanding precisely how humans and robots manipulate the world through the lens of contact.

Before grad school at Georgia Tech, I did my undergrad at Duke in computer science and electrical engineering. I got to lead Duke Electric Vehicles, a team of undergraduates building ultra-efficient cars. During my tenure as president, we set the world record for Most Fuel-Efficient Vehicle at 14,573 MPG, and Most Efficient Electric Vehicle at 27,482 MPGe.

In my free time, I like to fly gliders. These are a type of airplane without an engine which use thermals and mountain wave to stay aloft. My longest flight is 9 hours and covered 500 miles, and I hold 11 Georgia state records for soaring. Click here for more! I also enjoy photography and building things with my hands.

publications

  1. The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
    Mengyu Yang, Patrick Grady, Samarth Brahmbhatt, Arun Balajee Vasudevan, Charles C Kemp, and James Hays
    IEEE International Conference on Robotics and Automation (ICRA), 2024
    PDF Code Website Video
  2. Visual Contact Pressure Estimation for Grippers in the Wild
    Jeremy A Collins, Cody Houff, Patrick Grady, and Charles C Kemp
    IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2023
    PDF Code Video
  3. PressureVision++: Estimating Fingertip Pressure From Diverse RGB Images
    Patrick Grady, Jeremy A Collins, Chengcheng Tang, Christopher D Twigg, Kunal Aneja, James Hays, and Charles C Kemp
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
    PDF Code Website Video
  4. Force/Torque Sensing for Soft Grippers using an External Camera
    Jeremy A Collins, Patrick Grady, and Charles C Kemp
    IEEE International Conference on Robotics and Automation (ICRA), 2023
    PDF Code Video
  5. BodyPressure - Inferring Body Pose and Contact Pressure From a Depth Image
    Henry M Clever, Patrick Grady, Greg Turk, and Charles C Kemp
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
    PDF Code
  6. Visual Pressure Estimation and Control for Soft Robotic Grippers
    Patrick Grady, Jeremy A Collins, Samarth Brahmbhatt, Christopher D Twigg, Chengcheng Tang, James Hays, and Charles C Kemp
    IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2022
    PDF Code Video
  7. PressureVision: Estimating Hand Pressure from a Single RGB Image
    Patrick Grady, Chengcheng Tang, Samarth Brahmbhatt, Christopher D Twigg, Chengde Wan, James Hays, and Charles C Kemp
    European Conference on Computer Vision (ECCV), Oral, 2022
    PDF Code Video
  8. ContactOpt: Optimizing Contact to Improve Grasps
    Patrick Grady, Chengcheng Tang, Christopher D Twigg, Minh Vo, Samarth Brahmbhatt, and Charles C Kemp
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2021
    PDF Code Website Video
  9. Masked Reconstruction Based Self-supervision for Human Activity Recognition
    Harish Haresamudram, Apoorva Beedu, Varun Agrawal, Patrick Grady, Irfan Essa, Judy Hoffman, and Thomas Plötz
    International Symposium on Wearable Computers (ISWC), 2020
    PDF
  10. Learning to Collaborate from Simulation for Robot-Assisted Dressing
    Alexander Clegg, Zackory Erickson, Patrick Grady, Greg Turk, Charles C Kemp, and C Karen Liu
    IEEE Robotics and Automation Letters (RA-L), 2020
    PDF Video
  11. A Study of Energy Losses in the World’s Most Fuel Efficient Vehicle
    Patrick Grady, Gerry Chen, Shomik Verma, Aniruddh Marellapudi, and Nico Hotz
    IEEE Vehicle Power and Propulsion Conference (VPPC), 2019
    PDF Code Video

Mauna Loa