{"ID":2889670,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20892","arxiv_id":"2507.20892","title":"PixelNav: Towards Model-based Vision-Only Navigation with Topological Graphs","abstract":"This work proposes a novel hybrid approach for vision-only navigation of mobile robots, which combines advances of both deep learning approaches and classical model-based planning algorithms. Today, purely data-driven end-to-end models are dominant solutions to this problem. Despite advantages such as flexibility and adaptability, the requirement of a large amount of training data and limited interpretability are the main bottlenecks for their practical applications. To address these limitations, we propose a hierarchical system that utilizes recent advances in model predictive control, traversability estimation, visual place recognition, and pose estimation, employing topological graphs as a representation of the target environment. Using such a combination, we provide a scalable system with a higher level of interpretability compared to end-to-end approaches. Extensive real-world experiments show the efficiency of the proposed method.","short_abstract":"This work proposes a novel hybrid approach for vision-only navigation of mobile robots, which combines advances of both deep learning approaches and classical model-based planning algorithms. Today, purely data-driven end-to-end models are dominant solutions to this problem. Despite advantages such as flexibility and a...","url_abs":"https://arxiv.org/abs/2507.20892","url_pdf":"https://arxiv.org/pdf/2507.20892v1","authors":"[\"Sergey Bakulin\",\"Timur Akhtyamov\",\"Denis Fatykhov\",\"German Devchich\",\"Gonzalo Ferrer\"]","published":"2025-07-28T14:44:36Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}