paper-with-me

홈 › Papers

RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots

2026-03-04 · Soroush Nasiriany, Sepehr Nasiriany, Abhiram Maddukuri, Yuke Zhu arxiv

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remains difficult to gauge how close we are to this vision. The field lacks a reproducible, large-scale benchmark for systematic evaluation. To fill this gap, we present RoboCasa365, a comprehensive simulation benchmark for household mobile manipulation. Built on the RoboCasa platform, RoboCasa365 introduces 365 everyday tasks across 2,500 diverse kitchen environments, with over 600 hours of human demonstration data and over 1600 hours of synthetically generated demonstration data -- making it one of the most diverse and large-scale resources for studying generalist policies. RoboCasa365 is designed to support systematic evaluations for different problem settings, including multi-task learning, robot foundation model training, and lifelong learning. We conduct extensive experiments on this benchmark with state-of-the-art methods and analyze the impacts of task diversity, dataset scale, and environment variation on generalization. Our results provide new insights into what factors most strongly affect the performance of generalist robots and inform strategies for future progress in the field.

📄 PDF Abstract BibTeX arXiv:2603.04356

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

2024-06-04 · Soroush Nasiriany, Abhiram Maddukuri, Lance Zhang, Adeet Parikh 외

Recent advancements in Artificial Intelligence (AI) have largely been propelled by scaling. In Robotics, scaling is hindered by the lack of access to massive robot datasets. We advocate using realistic physical simulatio…

Imitation LearningText to 3D

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

2026-06-15 · Hao Li, Ganlong Zhao, Yufei Liu, Haotian Hou 외 arxiv

Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show that large-scale egocentric human videos…

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

2026-06-30 · Lang Cao, Renhong Chen, Luyi Li, Peng Wang 외 arxiv

Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by…

Reinforcement LearningContinuous Control

Riemann-1.0: An Embodied World Action Model for Physical AI

2026-08-27 · Haofeng Sun, Jiangbo Pei, Fei Kang, Zexiang Liu 외 arxiv

We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 jointly models multi-view visual observations, robot states, and embodiment-specific actions within a unif…

Robot Manipulation

Multi-Task Interactive Robot Fleet Learning with Visual World Models

2024-10-30 · Huihan Liu, Yu Zhang, Vaarij Betala, Evan Zhang 외

Recent advancements in large-scale multi-task robot learning offer the potential for deploying robot fleets in household and industrial settings, enabling them to perform diverse tasks across various environments. Howeve…