Robot Model Identification and Learning: A Modern Perspective

T Lee, J Kwon, PM Wensing… - Annual Review of Control …, 2023 - annualreviews.org
In recent years, the increasing complexity and safety-critical nature of robotic tasks have
highlighted the importance of accurate and reliable robot models. This trend has led to a …

Towards high-accuracy axial springback: Mesh-based simulation of metal tube bending via geometry/process-integrated graph neural networks

Z Wang, C Wang, S Zhang, L Qiu, Y Lin, J Tan… - Expert Systems with …, 2024 - Elsevier
Springback has always been a stubborn defect that affects the axial accuracy of metal
bending. The finite element simulation of springback enables effective control and precise …

Learning rigid dynamics with face interaction graph networks

KR Allen, Y Rubanova, T Lopez-Guevara… - arxiv preprint arxiv …, 2022 - arxiv.org
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex
geometry and the strong non-linearity of the interactions. While graph neural network (GNN) …

Unifying predictions of deterministic and stochastic physics in mesh-reduced space with sequential flow generative model

L Sun, X Han, H Gao, JX Wang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Accurate prediction of dynamical systems in unstructured meshes has recently shown
successes in scientific simulations. Many dynamical systems have a nonnegligible level of …

Swarm reinforcement learning for adaptive mesh refinement

N Freymuth, P Dahlinger, T Würth… - Advances in …, 2024 - proceedings.neurips.cc
Abstract The Finite Element Method, an important technique in engineering, is aided by
Adaptive Mesh Refinement (AMR), which dynamically refines mesh regions to allow for a …

Learning flexible body collision dynamics with hierarchical contact mesh transformer

YY Yu, J Choi, W Cho, K Lee, N Kim, K Chang… - arxiv preprint arxiv …, 2023 - arxiv.org
Recently, many mesh-based graph neural network (GNN) models have been proposed for
modeling complex high-dimensional physical systems. Remarkable achievements have …

Learned Neural Physics Simulation for Articulated 3D Human Pose Reconstruction

M Andriluka, B Tabanpour, CD Freeman… - … on Computer Vision, 2024 - Springer
We propose a novel neural network approach to model the dynamics of articulated human
motion with contact. Our goal is to develop a faster and more convenient alternative to …

Object Dynamics Modeling with Hierarchical Point Cloud-based Representations

C Kim, L Fuxin - Proceedings of the IEEE/CVF Conference …, 2024 - openaccess.thecvf.com
Modeling object dynamics with a neural network is an important problem with numerous
applications. Most recent work has been based on graph neural networks. However physics …

Learning 3D Particle-based Simulators from RGB-D Videos

WF Whitney, T Lopez-Guevara, T Pfaff… - arxiv preprint arxiv …, 2023 - arxiv.org
Realistic simulation is critical for applications ranging from robotics to animation. Traditional
analytic simulators sometimes struggle to capture sufficiently realistic simulation which can …

Simultaneous learning of contact and continuous dynamics

B Bianchini, M Halm, M Posa - Conference on Robot …, 2023 - proceedings.mlr.press
Robotic manipulation can greatly benefit from the data efficiency, robustness, and
predictability of model-based methods if robots can quickly generate models of novel objects …