Soft Robot Control
It is difficult to precisely control soft robots due to their complicated dynamics. We utilize global linear embedding and control techniques to demonstrate previously unachievable performance capabilities such as trajectory following and automated object sorting. [rss2019] [tro2020] [icra-ral2021] [iros-ral2021] [ijrr2024]
Soft Robot Modeling
The behavior of soft robots is challenging to predict because of their many degrees of freedom and nonlinear material properties. We utilize a combination of physics-based and data-driven techniques to construct models that inform the design and control of real soft robotics systems. [ral2018] [icra2019]
Soft Robot Design
Soft robots are well-suited for tasks that require safely interacting with delicate objects and humans. However, they have a number of shortcomings that limit their usefulness such as low payload capacity, poor proprioception, and slow response times. We develop novel mechanisms, materials, and sensors to address these shortcomings and increase the physical capabilities of soft robots. [iros2023] [scirob2023]
Soft Actuator Design
Soft actuators can impart spatial forces without imposing a rigid structure. We explore ways of utilizing geometry and reinforcing elements such as fibers and beams to design fluid-driven actuators with desired properties. [icra2017] [jmr2018] [icra-ral2022] [iros2024]
Biomimetic Robots
Robotics offers biologists a powerful tool for experimentally evaluating evolutionary hypotheses. We design robots to mimic specific biological traits to allow the fitness of those traits to be assessed via controlled experiments. [icra2020]