Embedded Files
Kostas Bekris
Kostas Bekris is an Assistant Professor at the Computer Science Department at Rutgers University.
Towards Effective Modeling of Tensegrities
Sam Kriegman
Sam Kriegman
Sam Kriegman is a computer scientist with a joint postdoctoral appointment at the Wyss Institute at Harvard and the Allen Discovery Center at Tufts. His research draws inspiration from the origin and subsequent evolution of life, and applies the underlying mechanisms of self-organization and natural selection to the creation of novel autonomous machines. These machines can in some cases perform useful work, or they may be used as scientific tools to understand how animals evolve, grow, move, sense, and think.
Sim2real for Biological Robots
In this talk, I will describe the computational and biological tools used to create Xenobots: living robots composed entirely of frog (Xenopus) cells. I will conclude with ideas about how to improve design (sim), manufacture (real), transference (sim2real), and system identification (real2sim) for xenobots other kinds of biological and biohybrid robots.
Gang Zheng
Gang Zheng received the B.E. and M.E. degrees in Communication and systems from Wuhan University China in 2001 and 2004 respectively and the Ph.D. degree in automatic control from ENSEA Cergy-Pontoise France in 2006. Since 2007 he has held postdoctoral positions at INRIA Grenoble at the Laboratoire Jean Kuntzmann and at ENSEA. He joined INRIA Lille as a permanent researcher from September 2009. His research interests include control and observation of nonlinear systems and its applications to rigid and soft robotics. Gang Zheng is a senior member of IEEE.
Cosserat-based Optimization Design for Slender Soft Manipulators
Considering a slender soft manipulator controlled via arranged actuators with bounded magnitudes, this talk investigates the design optimization for such a soft robot. For this purpose, we select the Discrete Cosserat method to establish the mathematical model of soft manipulators, based on which we propose an optimization approach to determine the optimal design of the investigated soft robot in order to achieve certain performance objectives. Finally, we validate the proposed method through various numerical simulations.
Andrew Spielberg
Andrew Spielberg
Andrew Spielberg is a Postdoctoral Fellow at Harvard University. His research focuses on developing algorithms to co-design novel types of rigid and soft robots in form and behavior, and automatically fabricate them. His work has touched upon topics in soft matter and differentiable simulation, numerical optimization and machine learning for robot control and design, and digital fabrication processes such as 3D printing and textile-manufacturing. He received his B.S. and M.Eng from Cornell University and his Ph.D. from MIT. His work won the best paper award at CHI, and has been nominated for best paper awards at ICRA and Robosoft.
Differentiable Simulation and Learning-Based Co-Design For Soft Robots
Despite the recent growth in computational techniques for soft robot sensing and control, soft robot design cycles remain long and manually-driven. The dream of a rapid design cycle for soft robotics is stymied not only by their expensive simulation, but also by the complex interplay between their high-dimensional form and rich dynamical behavior. In this talk, I will discuss recent progress in efficiently co-designing soft robots' "bodies" (geometry, materials, sensor placement, and actuation placement) and "brains" (control, proprioceptive models, and higher-level reasoning). Our solutions leverage the natural union of fast, GPU-accelerated differentiable simulation and modern deep learning architectures and algorithms. I will conclude this talk by providing an overview of lessons learned and future opportunities in the field.
Page updated
Google Sites
Report abuse