James M. Bern
ETH Zurich
16 Papers
James M. Bern is an academic researcher from ETH Zurich. The author has contributed to research in topics: Computer science & Robot. The author has an hindex of 9, co-authored 10 publications. Previous affiliations of James M. Bern include Massachusetts Institute of Technology & Carnegie Mellon University.
Chat about Author
Papers
Soft Robot Control With a Learned Differentiable Model
James M. Bern,Yannick Schnider,Pol Banzet,Nitish Kumar,Stelian Coros +4 more
- 01 May 2020
TL;DR: This paper learns a differentiable model of a soft robot’s quasi-static physics, and then performs gradient-based optimization to find optimal open-loop control inputs and finds that the learned model captures phenomena that would be absent from an idealized physically-based simulation.
104
Real2Sim: visco-elastic parameter estimation from dynamic motion
TL;DR: The effectiveness of the method for optimizing visco-elastic material parameters of a finite element simulation to best approximate the dynamic motion of real-world soft objects is demonstrated.
75
Computational Design of Robotic Devices From High-Level Motion Specifications
TL;DR: A novel heuristic function estimates how much an intermediate robot design needs to change before it becomes able to execute the target motion trajectories, and demonstrates the effectiveness of this computational design method by automatically creating a variety of robotic manipulators and legged robots.
73
Interactive Robotic Manipulation of Elastic Objects
Simon Duenser,James M. Bern,Roi Poranne,Stelian Coros +3 more
- 01 Oct 2018
TL;DR: This paper model elastic objects using the Finite Element Method through a quasi-static assumption, which enables an interactive, simulation-based control methodology, wherein user-specified deformations for the elastic objects are automatically mapped to joint angle commands.
58
Reconfiguration planning for pivoting cube modular robots
Cynthia Sung,James M. Bern,John Romanishin,Daniela Rus +3 more
- 26 May 2015
TL;DR: This paper analyzes the pivoting cube model and provides provably correct algorithms for self-reconfiguration of modular robots that move by pivoting, and shows that if an initial configuration does not contain any of three subconfigurations, then it can reconfigure into a line.