{"slug": "a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction", "title": "A Study of Conditional Diffusion Models for Open-Loop Control under Dry Friction and Stiction", "summary": "A new arXiv study (arXiv:2609.01756v1) finds that Action Diffusion, a conditional diffusion model using a compact 1D U-Net, reduces terminal error and stuck steps for open-loop control of a point-mass system with dry friction and stiction, outperforming uniform random shooting, structured random shooting, and the Cross-Entropy Method (CEM), especially in low-sample regimes. The results suggest conditional diffusion can generate temporally coherent control sequences that overcome stiction by conditioning on initial and target states.", "body_md": "arXiv:2609.01756v1 Announce Type: new\nAbstract: Diffusion models have recently emerged as expressive generative priors for planning and control. This paper studies Action Diffusion, an action-sequence diffusion formulation used as an open-loop proposal distribution for a point-mass system with dry friction and stiction. In this benchmark, motion starts only when the applied input exceeds a static-friction threshold, so effective controls occupy a small and temporally structured subset of the action-sequence space. A compact conditional 1D U-Net generates bounded control sequences conditioned on initial and target states. We compare it with uniform random shooting, random shooting from the same structured dataset prior, and the Cross-Entropy Method (CEM). Results show that Action Diffusion reduces terminal error and stuck steps, especially in low-sample regimes. These results indicate that conditional diffusion provides an effective mechanism for generating temporally coherent control sequences that overcome stiction by conditioning and recombining structured control primitives from the training prior for state-to-state open-loop control.", "url": "https://wpnews.pro/news/a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction", "canonical_source": "https://arxiv.org/abs/2609.01756", "published_at": "2026-09-03 04:00:00+00:00", "updated_at": "2026-09-03 04:23:26.831577+00:00", "lang": "en", "topics": ["machine-learning", "generative-ai", "ai-research"], "entities": ["arXiv", "Action Diffusion", "U-Net", "Cross-Entropy Method"], "alternates": {"html": "https://wpnews.pro/news/a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction", "markdown": "https://wpnews.pro/news/a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction.md", "text": "https://wpnews.pro/news/a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction.txt", "jsonld": "https://wpnews.pro/news/a-study-of-conditional-diffusion-models-for-open-loop-control-under-dry-friction.jsonld"}}