{"version":"1","article":{"id":"robot-watchdog-graph-failure-detection-2026","slug":"robot-watchdog-graph-failure-detection-2026","language":"en","url":"https://haberpaper.com/en/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=en","title":"Robot-WATCHDOG tracks failures through object relationships","summary":"Researchers affiliated with French institutions presented a robot-failure detector that tracks how objects are positioned and related during a task. They evaluated it on an existing benchmark and a new dataset with two tasks.","category":"business","region":"world","topics":["ai"],"published_at":"2026-10-13T20:11:52+03:00","modified_at":"2026-10-13T20:11:52+03:00","publication_basis":"publication-record","event_period":"2026-10-09","event_period_basis":"event-or-reference-period","sources":[{"name":"arXiv, Robot-WATCHDOG: failure detection through object-centric graph representation (arXiv:2610.13403)","url":"https://arxiv.org/abs/2610.13403","checkedAt":"2026-10-13","publishedAt":"2026-10-09"}],"translations":[{"language":"tr","url":"https://haberpaper.com/tr/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=tr"},{"language":"en","url":"https://haberpaper.com/en/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=en"},{"language":"ar","url":"https://haberpaper.com/ar/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=ar"},{"language":"fr","url":"https://haberpaper.com/fr/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=fr"},{"language":"es","url":"https://haberpaper.com/es/news/robot-watchdog-graph-failure-detection-2026","api_url":"https://haberpaper.com/api/v1/articles/robot-watchdog-graph-failure-detection-2026?lang=es"}],"data_types":[],"data":null,"data_compilations":[],"data_downloads":[],"content":{"paragraphs":["A preprint posted on arXiv on 9 October by researchers affiliated with Université Paris-Saclay, CEA, Inria and CNRS examines the limits of detecting manipulation failures from image similarity alone. Robot-WATCHDOG represents objects in a scene and their relationships over time as a graph. The team tests one score that measures geometric and relational deviation from expert demonstrations, and a second that predicts future object states with a graph-attention network and Transformer.","The authors tested both approaches on four compatible tasks from an earlier robot-failure benchmark and on two tasks they created: table setting and waste sorting on a moving conveyor. They excluded interactions such as liquids and deformable objects that do not fit the method’s assumption of persistent object identity. The paper reports that both graph-based scores outperformed image-based detectors particularly on failures involving object interactions and task structure; the non-training geometric-relational score had the strongest overall results and lowest inference cost. The findings are limited to the datasets and tasks selected in the paper and do not establish a safety system validated for every robot or failure type. The work is a preprint that has not yet undergone peer review."],"key_points":[],"sections":[]},"text":"Researchers affiliated with French institutions presented a robot-failure detector that tracks how objects are positioned and related during a task. They evaluated it on an existing benchmark and a new dataset with two tasks.\n\nA preprint posted on arXiv on 9 October by researchers affiliated with Université Paris-Saclay, CEA, Inria and CNRS examines the limits of detecting manipulation failures from image similarity alone. Robot-WATCHDOG represents objects in a scene and their relationships over time as a graph. The team tests one score that measures geometric and relational deviation from expert demonstrations, and a second that predicts future object states with a graph-attention network and Transformer.\n\nThe authors tested both approaches on four compatible tasks from an earlier robot-failure benchmark and on two tasks they created: table setting and waste sorting on a moving conveyor. They excluded interactions such as liquids and deformable objects that do not fit the method’s assumption of persistent object identity. The paper reports that both graph-based scores outperformed image-based detectors particularly on failures involving object interactions and task structure; the non-training geometric-relational score had the strongest overall results and lowest inference cost. The findings are limited to the datasets and tasks selected in the paper and do not establish a safety system validated for every robot or failure type. The work is a preprint that has not yet undergone peer review.","corrections":[],"editorial_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"business","url":"https://haberpaper.com/assets/illustrations/business-1536.webp","width":1536,"height":1024,"alt":"Symbolic industrial workshop with machinery, a warehouse and a crane.","language":"en"},"section_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"business","url":"https://haberpaper.com/assets/illustrations/business-1536.webp","width":1536,"height":1024,"alt":"Symbolic industrial workshop with machinery, a warehouse and a crane.","language":"en"}}}