Alex Church

About

Alex Church is a leading researcher in tactile robotics, specializing in deep reinforcement learning, sim-to-real transfer, and biomimetic tactile sensing. His work bridges the gap between vision and touch by applying advanced deep learning techniques to optical tactile sensors, enabling robots to perceive and interact with their environments with unprecedented dexterity. Church’s most-cited paper (113 citations) demonstrates how deep learning can revolutionize robot touch, much like it has for robot vision, using an optical biomimetic sensor for edge perception and contour following. He further advanced the field with Tactile Gym 2.0 (50 citations), a platform that lowers the barrier to high-resolution tactile research through sim-to-real reinforcement learning. His notable contributions include Bi-Touch (34 citations), which tackles bimanual tactile manipulation, and TouchSDF (21 citations), a DeepSDF approach for 3D shape reconstruction from tactile data. Church has also pioneered tactile-based tasks like learning to type on a Braille keyboard (33 citations) and developed robust sim-to-real transfer methods for tactile control. His work on the Tactile Model O hand and tactile saliency prediction underscores his commitment to making tactile robotics accessible and resilient in unstructured environments. With over 280 total citations, Church is shaping the future of dexterous, touch-enabled robots.

Research Focus

Key Achievements

Top Papers

1. 1
   From Pixels to Percepts: Highly Robust Edge Perception and Contour Following Using Deep Learning and an Optical Biomimetic Tactile Sensor

   113 citations · 2019
2. 2
   Tactile Gym 2.0: Sim-to-Real Deep Reinforcement Learning for Comparing Low-Cost High-Resolution Robot Touch

   50 citations · 2022
3. 3
   Bi-Touch: Bimanual Tactile Manipulation With Sim-to-Real Deep Reinforcement Learning

   34 citations · 2023
4. 4
   Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard

   33 citations · 2020
5. 5
   TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction Using Vision-Based Tactile Sensing

   21 citations · 2024
6. 6
   Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing

   18 citations · 2023
7. 7
   Tactile Model O: Fabrication and Testing of a 3D-Printed, Three-Fingered Tactile Robot Hand

   7 citations · 2020
8. 8
   Attention for Robot Touch: Tactile Saliency Prediction for Robust Sim-to-Real Tactile Control

   4 citations · 2023
9. 9
   Optical Tactile Sim-to-Real Policy Transfer via Real-to-Sim Tactile Image Translation.

   4 citations · 2021
10. 10
    Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation

    3 citations · 2021

Key Collaborators

Contact & Links