{"ID":2893079,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13871","arxiv_id":"2507.13871","title":"Safety Certification in the Latent space using Control Barrier Functions and World Models","abstract":"Synthesising safe controllers from visual data typically requires extensive supervised labelling of safety-critical data, which is often impractical in real-world settings. Recent advances in world models enable reliable prediction in latent spaces, opening new avenues for scalable and data-efficient safe control. In this work, we introduce a semi-supervised framework that leverages control barrier certificates (CBCs) learned in the latent space of a world model to synthesise safe visuomotor policies. Our approach jointly learns a neural barrier function and a safe controller using limited labelled data, while exploiting the predictive power of modern vision transformers for latent dynamics modelling.","short_abstract":"Synthesising safe controllers from visual data typically requires extensive supervised labelling of safety-critical data, which is often impractical in real-world settings. Recent advances in world models enable reliable prediction in latent spaces, opening new avenues for scalable and data-efficient safe control. In t...","url_abs":"https://arxiv.org/abs/2507.13871","url_pdf":"https://arxiv.org/pdf/2507.13871v1","authors":"[\"Mehul Anand\",\"Shishir Kolathaya\"]","published":"2025-07-18T12:50:27Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\",\"cs.LG\",\"eess.SY\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}