Robotics Research

I’ve been immensely fortunate to have the academic resources that I have had and most of the projects resulted in publications which I link to below, but some either failed or were explored more out of personal interest – I include both below. All of the overviews are very brief, contact me if you’d like to hear more!


Proximity & Pressure-Based Manipulation Controller (MS Thesis)

Unlocking humanoid robotic, prosthetic, and exoskeleton controllers for grasping tasks.


The Infinity Gauntlet (MS Thesis)

Enabling anthropomorphic grasping imitation learning.


Learning Tube Dynamics with Massively Parallel Simulation for Robust Safety in Practice

“Thou shalt not bump into things.”


Massively Parallelized Reinforcement Learning for Trajectory-Based Controllers

30,000 robots flailing on a screen until they start sprinting around complex paths.


Real-Time Balancing of Stability and Plasticity in Continual Learning Enables Adaptive Speed Estimation Controllers for Lower-Limb Prostheses

“The essence of repression lies simply in turning something away, and keeping it at a distance, from the conscious.”
Freud, 1915, p. 147


Real-time Adaptation of Deep Learning Walking Speed Estimators Enables Biomimetic Assistance Modulation in an Open-Source Bionic Leg

Prosthetics learning to walk with users in real-time.


Transfer Learning for Efficient Walking Speed Estimation Across Novel Prosthetic Devices and Populations

Optimizing prosthetic performance by transferring learned knowledge across devices.


Accelerating Constrained Continual Learning with Dynamic Active Learning: A Study in Adaptive Speed Estimation for Lower-Limb Prostheses

Optimizing the process of real-time prosthetic adaptation to users.


Adaptive Lower-Limb Prosthetic Control: Towards Personalized Intent Recognition & Context Estimation

Personalizing prosthetic control for safer and more natural walking patterns.


Generative Networks for Biomechanical Data Synthesis to Augment Deep Learning Datasets

Enhancing prosthetic control with synthetic data to reduce the cost of real-world experimentation.


Artificial Potential Fields for Human-in-the-Loop Exoskeleton Controllers

Guiding human movement with intuitive, resistance-based control for exoskeletons.