arXiv:2511.14161v2 Announce Type: replace-cross 
Abstract: Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots.

RoboTidy هو معيار جديد مصمم لتنظيم المنزل الموجه بواسطة اللغة، حيث يعالج القيود الموجودة في المعايير الحالية التي لا نمذج تفضيلات المستخدم ولا تدعم الحركة. يتضمن 500 مشهد منزلي فوتورياليستي بتقنية 3D Gaussian Splatting ويقدم مسارات واسعة للتلاعب والملاحة لتسهيل التدريب والتقييم في مهام العمل بلغة الرؤية والتنقل بلغة الرؤية.

RoboTidy es un nuevo estándar diseñado para la organización del hogar guiada por el lenguaje, que aborda las limitaciones de los estándares actuales que no modelan las preferencias del usuario ni apoyan la movilidad. Presenta 500 escenas domésticas fotorealistas de 3D Gaussian Splatting y proporciona extensas trayectorias de manipulación y navegación para facilitar la formación y evaluación en tareas de Acción-Lenguaje-Visión y Navegación-Lenguaje-Visión.

RoboTidy est une nouvelle référence conçue pour le rangement domestique guidé par le langage, répondant aux limites des références actuelles qui ne modélisent pas les préférences des utilisateurs et ne soutiennent pas la mobilité. Il propose 500 scènes domestiques photoréalistes en 3D Gaussian Splatting et fournit d'importantes trajectoires de manipulation et de navigation pour faciliter la formation et l'évaluation dans les tâches de Vision-Language-Action et de Vision-Language-Navigation.

RoboTidy is a new benchmark designed for language-guided household tidying, addressing the limitations of current benchmarks that fail to model user preferences and support mobility. It features 500 photorealistic 3D Gaussian Splatting household scenes and provides extensive manipulation and navigation trajectories to facilitate training and evaluation in Vision-Language-Action and Vision-Language-Navigation tasks.

RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action

One More Thing in AI – Your Shortcut to AI Mastery

RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Guidejar-4eb95b

Grubby.AI

LangWatch

HomeVisualizer.AI

Ready to build your own newsroom?