As a Research Scientist and group leader at Disney Research, I am deeply passionate about solving real-world problems in computational robotics, fabrication, and architecture.
My core expertise is the development of differentiable simulators to tackle complex design, control, and characterization problems in (soft) robotics, architecture, and computer graphics.
More specifically, I model rigid and flexible multibody systems kinematically, quasi-statically, and dynamically, and utilize the differentiability of the simulators to (1) numerically optimize design, control, and material parameters, or to (2) learn control strategies if stochasticity is present in the modeling task.
Most recently, I have developed differentiable simulators for the design of proprioceptive soft robots, the equilibrium-constrained shape optimization of CAD models, the vibration-minimizing animation of robotic characters, and the structural optimization of architectural-scale models under worst-case loads.
Send me a note if you are interested in an internship in my group.
PhD in Computer Science
Harvard University
Master in Computer Science
ETH Zurich
A review on the use of differentiable simulation for computational design and control problems in soft robotics.
A versatile inverse kinematics formulation for the retargeting of expressive motions onto mechanical systems with kinematic loops.
A computational approach for routing artificial muscle actuators through hyperelastic soft robots, in order to achieve a desired deformation behavior.
A computational method for augmenting soft robots with proprioceptive sensing capabilities.
A novel generic shape optimization method for CAD models based on the eXtended Finite Element Method (XFEM).
An optimization-based, dynamics-aware motion retargeting system that adjusts an input motion such that visually salient low-frequency, large amplitude vibrations are suppressed.