Cover Image

RoboBrain 2.5: Depth in Sight, Time in Mind

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Huajie, Zhou, Enshen, Li, Zhiyu, Xu, Yijie, Ji, Yuheng, Chen, Xiansheng, Chi, Cheng, Wang, Pengwei, Jia, Huizhu, Ao, Yulong, Cao, Mingyu, Chen, Sixiang, Li, Zhe, Liu, Mengzhen, Wang, Zixiao, Rong, Shanyu, Lyu, Yaoxu, Zhao, Zhongxia, Co, Peterson, Li, Yibo, Han, Yi, Xie, Shaoxuan, Yao, Guocai, Wang, Songjing, Zhang, Leiduo, Yang, Xi, Jiao, Yance, Shi, Donghai, Xie, Kunchang, Nie, Shaokai, Men, Chunlei, Lin, Yonghua, Wang, Zhongyuan, Huang, Tiejun, Zhang, Shanghang
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866915742440488960
author	Tan, Huajie Zhou, Enshen Li, Zhiyu Xu, Yijie Ji, Yuheng Chen, Xiansheng Chi, Cheng Wang, Pengwei Jia, Huizhu Ao, Yulong Cao, Mingyu Chen, Sixiang Li, Zhe Liu, Mengzhen Wang, Zixiao Rong, Shanyu Lyu, Yaoxu Zhao, Zhongxia Co, Peterson Li, Yibo Han, Yi Xie, Shaoxuan Yao, Guocai Wang, Songjing Zhang, Leiduo Yang, Xi Jiao, Yance Shi, Donghai Xie, Kunchang Nie, Shaokai Men, Chunlei Lin, Yonghua Wang, Zhongyuan Huang, Tiejun Zhang, Shanghang
author_facet	Tan, Huajie Zhou, Enshen Li, Zhiyu Xu, Yijie Ji, Yuheng Chen, Xiansheng Chi, Cheng Wang, Pengwei Jia, Huizhu Ao, Yulong Cao, Mingyu Chen, Sixiang Li, Zhe Liu, Mengzhen Wang, Zixiao Rong, Shanyu Lyu, Yaoxu Zhao, Zhongxia Co, Peterson Li, Yibo Han, Yi Xie, Shaoxuan Yao, Guocai Wang, Songjing Zhang, Leiduo Yang, Xi Jiao, Yance Shi, Donghai Xie, Kunchang Nie, Shaokai Men, Chunlei Lin, Yonghua Wang, Zhongyuan Huang, Tiejun Zhang, Shanghang
contents	We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io
format	Preprint
id	arxiv_https___arxiv_org_abs_2601_14352
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	RoboBrain 2.5: Depth in Sight, Time in Mind Tan, Huajie Zhou, Enshen Li, Zhiyu Xu, Yijie Ji, Yuheng Chen, Xiansheng Chi, Cheng Wang, Pengwei Jia, Huizhu Ao, Yulong Cao, Mingyu Chen, Sixiang Li, Zhe Liu, Mengzhen Wang, Zixiao Rong, Shanyu Lyu, Yaoxu Zhao, Zhongxia Co, Peterson Li, Yibo Han, Yi Xie, Shaoxuan Yao, Guocai Wang, Songjing Zhang, Leiduo Yang, Xi Jiao, Yance Shi, Donghai Xie, Kunchang Nie, Shaokai Men, Chunlei Lin, Yonghua Wang, Zhongyuan Huang, Tiejun Zhang, Shanghang Robotics We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io
title	RoboBrain 2.5: Depth in Sight, Time in Mind
topic	Robotics
url	https://arxiv.org/abs/2601.14352