← All research

BYU Robotics & Dynamics Lab · Sep 2026 – Present

Whole-Body Manipulation with a Soft Robotic Torso

Teaching a large robot with two soft, pneumatic arms to hug and lift heavy boxes, learned entirely in simulation and transferred to hardware with no fine-tuning.

Curtis C. Johnson, Carlo Alessi, Egidio Falotico, Alejandro Pelaez, Cameron Collyer, Randon Sandall, Marc D. Killpack · Manuscript in preparation

Three panels: reward shaping via a motion primitive, CPU-parallelized training in MuJoCo, and policy evaluation in simulation and on hardware
Guided reward shaping, parallelized training in MuJoCo, then zero-shot transfer to the real robot.

About the project

Soft robots are well suited to whole-body manipulation because their compliance makes contact forgiving, but that same softness makes them hard to model and control. The lab's original work, by Johnson, Alessi, Falotico, and Killpack, trained a reinforcement-learning policy entirely in a fast MuJoCo simulation, guided by a simple grasping motion primitive, and transferred it straight to hardware: 88% success lifting boxes of up to ~10 kg with no fine-tuning.

The robot lifting five different cardboard boxes
Hardware trials across five boxes of different sizes and masses.

My role In progress

I joined in September 2026 to contribute to the revised paper:

Figures courtesy of the paper's authors, BYU Robotics & Dynamics Lab.

← Back to all research