AI Paper Atlas

Research map / Optimization / Optimizers

Efficient Differentiable Contact Model with Long-range Influence

XIAOHAN YE, Kui Wu, Taku Komura, zherong pan

ICLR 2026 · Optimization › Optimizers · approach: Differentiating through embedded optimization

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the proposed long-range contact potential instead of IPC or SDRS contact models, trivial initializationgradient-based trajectory optimization in differentiable rigid-body simulator · Billiardsconvergence of lossImproved
use proposed contact model instead of baselines (IPC, SDRS, bundled gradient)gradient-based control optimization · Pushtask success / lossImproved
use proposed contact model instead of baselinesgradient-based control optimization · Gather and Sort (10 cubes)task success / lossImproved
use proposed contact model instead of baselines9-link 16-DOF ant robot · Ant-Pushtask success / lossImproved
add random sampling of control signals for initialization to baseline contact models (ablation)IPC and SDRS baselines · BilliardsconvergenceImproved
add bounding sphere hierarchy acceleration to the contact potential (ablation)proposed contact model · Billiards (random frames)cost of computing contact potentialImproved
use proposed model instead of IPC for potential evaluationcontact potential evaluation · Billiards (random frames)computation costHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy