4 papers · 1 filter
Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Generation
Onur Beker, Andreas René Geist, Anselm Paulus +4
Simulating rigid-body dynamics with contact in a fast, massively vectorizable, and smoothly differentiable manner is highly desirable in robotics. An important bottleneck faced by…
Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification
Minh Trinh, Andreas René Geist, Josefine Monnet +3
Accurate inverse dynamics models are essential tools for controlling industrial robots. Recent research combines neural network regression with inverse dynamics formulations of the…
Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations
Shamil Mamedov, A. René Geist, Jan Swevers +1
Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficie…
Learning deformable linear object dynamics from a single trajectory
Shamil Mamedov, A. René Geist, Ruan Viljoen +2
The manipulation of deformable linear objects (DLOs) via model-based control requires an accurate and computationally efficient dynamics model. Yet, data-driven DLO dynamics models…