Joseph DelPreto

About

Joseph DelPreto is a pioneering roboticist and human-robot interaction researcher whose work spans soft robotics, biosignal-based communication, and intelligent robotic systems. He is perhaps best known for his groundbreaking development of an acoustically controlled soft robotic fish for underwater exploration, a project that has amassed over 800 citations and redefined how scientists study marine environments using biomimetic technology. DelPreto has made substantial contributions to brain-computer interfaces, demonstrating how EEG-measured error-related potentials can enable humans to correct robot behavior in real time — work that has garnered nearly 200 citations and opened new frontiers in intuitive human-robot collaboration. His research further extends into muscle-signal-driven control, tactile wearable interfaces, and deep learning approaches for robotic grasping with soft hands. A recurring theme across his portfolio is democratizing robotics — from printable robot design systems to virtual reality teleoperation for training AI models. His plug-and-play biosignal frameworks make sophisticated human-machine communication accessible without specialized calibration. With over 1,500 cumulative citations, DelPreto represents a new generation of researchers bridging neuroscience, materials science, and artificial intelligence to create robots that are safer, smarter, and more naturally collaborative.

Research Focus

Key Achievements

Top Papers

1. 1
   Exploration of underwater life with an acoustically controlled soft robotic fish

   811 citations · 2018
2. 2
   Correcting robot mistakes in real time using EEG signals

   183 citations · 2017
3. 3
   Learning Object Grasping for Soft Robot Hands

   172 citations · 2018
4. 4
   Adaptive tactile interaction transfer via digitally embroidered smart gloves

   118 citations · 2024
5. 5
   A highly-underactuated robotic hand with force and joint angle sensors

   66 citations · 2011
6. 6
   Sharing the Load: Human-Robot Team Lifting Using Muscle Activity

   62 citations · 2019
7. 7
   Cogeneration of mechanical, electrical, and software designs for printable robots from structural specifications

   45 citations · 2014
8. 8
   Helping Robots Learn: A Human-Robot Master-Apprentice Model Using Demonstrations via Virtual Reality Teleoperation

   43 citations · 2020
9. 9
   Plug-and-Play Gesture Control Using Muscle and Motion Sensors

   38 citations · 2020
10. 10
    Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection

    34 citations · 2020

Key Collaborators

Contact & Links