Arvi Gjoka

arvi.gjoka@nyu.edu

I am a final year PhD student at Courant Institute, NYU, where I am co-advised by Daniele Panozzo and Denis Zorin. My thesis is Computational Design through Differentiable Elastodynamic Simulation, Parametrized by Geometric Techniques, for Applications in Soft Robotics. During my PhD, my research has revolved around building differentiable Finite Element based optimization methodologies for targeting computational design through inverse problems and been published mainly in SIGGRAPH. Additionally, I have done some early work exploring and benchmarking Scientific Machine Learning techniques on dynamical systems (NeurIPS). In the past few years, I have interned at Disney Research Zurich and nTop.

I am an active contributor to PolyFEM, a state-of-the-art differentiable FEM simulator that we are evolving to offer novel techniques in simulation and optimization. I am also particularly interested in fabrication methods (additive manufacturing, silicone molding), both as a verification of simulation and as a forcing function to developing new computational techniques.

Prior to this, I graduated with a BA in Physics and Computer Science at NYU and was a software engineer at Google.

latest posts

Jul 07, 2024	Cascaded Shape Optimization using PolyFEM

selected publications

Differentiable solver for time-dependent deformation problems with contact

Zizhou Huang, Davi Colli Tozoni, Arvi Gjoka , and 4 more authors

ACM Trans. Graph., May 2024

Abs

We introduce a general differentiable solver for time-dependent deformation problems with contact and friction. Our approach uses a finite element discretization with a high-order time integrator coupled with the recently proposed incremental potential contact method for handling contact and friction forces to solve ODE- and PDE-constrained optimization problems on scenes with complex geometry. It supports static and dynamic problems and differentiation with respect to all physical parameters involved in the physical problem description, which include shape, material parameters, friction parameters, and initial conditions. Our analytically derived adjoint formulation is efficient, with a small overhead (typically less than 10% for nonlinear problems) over the forward simulation, and shares many similarities with the forward problem, allowing the reuse of large parts of existing forward simulator code.We implement our approach on top of the open-source PolyFEM library and demonstrate the applicability of our solver to shape design, initial condition optimization, and material estimation on both simulated results and physical validations.
Soft Pneumatic Actuator Design using Differentiable Simulation

Arvi Gjoka, Espen Knoop, Moritz Bächer , and 2 more authors

In Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers ’24 , Denver, CO, USA, May 2024

Abs

We propose a computational design pipeline for pneumatically-actuated soft robots interacting with their environment through contact. We optimize the shape of the robot with a shape optimization approach, using a physically-accurate high-order finite element model for the forward simulation. Our approach enables fine-grained control over both deformation and contact forces by optimizing the shape of internal cavities, which we exploit to design pneumatically-actuated robots that can assume user-prescribed poses, or apply user-controlled forces. We demonstrate the efficacy of our method on two artistic and two functional examples.