{"ID":2866258,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21664","arxiv_id":"2509.21664","title":"Generating Stable Placements via Physics-guided Diffusion Models","abstract":"Stably placing an object in a multi-object scene is a fundamental challenge in robotic manipulation, as placements must be penetration-free, establish precise surface contact, and result in a force equilibrium. To assess stability, existing methods rely on running a simulation engine or resort to heuristic, appearance-based assessments. In contrast, our approach integrates stability directly into the sampling process of a diffusion model. To this end, we query an offline sampling-based planner to gather multi-modal placement labels and train a diffusion model to generate stable placements. The diffusion model is conditioned on scene and object point clouds, and serves as a geometry-aware prior. We leverage the compositional nature of score-based generative models to combine this learned prior with a stability-aware loss, thereby increasing the likelihood of sampling from regions of high stability. Importantly, this strategy requires no additional re-training or fine-tuning, and can be directly applied to off-the-shelf models. We evaluate our method on four benchmark scenes where stability can be accurately computed. Our physics-guided models achieve placements that are 56% more robust to forceful perturbations while reducing runtime by 47% compared to a state-of-the-art geometric method.","short_abstract":"Stably placing an object in a multi-object scene is a fundamental challenge in robotic manipulation, as placements must be penetration-free, establish precise surface contact, and result in a force equilibrium. To assess stability, existing methods rely on running a simulation engine or resort to heuristic, appearance-...","url_abs":"https://arxiv.org/abs/2509.21664","url_pdf":"https://arxiv.org/pdf/2509.21664v1","authors":"[\"Philippe Nadeau\",\"Miguel Rogel\",\"Ivan Bilić\",\"Ivan Petrović\",\"Jonathan Kelly\"]","published":"2025-09-25T22:32:35Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}