arXiv Open Access 2026

RoboBrain 2.5: Depth in Sight, Time in Mind

Huajie Tan Enshen Zhou Zhiyu Li Yijie Xu Yuheng Ji +30 lainnya
Lihat Sumber

Abstrak

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

Topik & Kata Kunci

Penulis (35)

H

Huajie Tan

E

Enshen Zhou

Z

Zhiyu Li

Y

Yijie Xu

Y

Yuheng Ji

X

Xiansheng Chen

C

Cheng Chi

P

Pengwei Wang

H

Huizhu Jia

Y

Yulong Ao

M

Mingyu Cao

S

Sixiang Chen

Z

Zhe Li

M

Mengzhen Liu

Z

Zixiao Wang

S

Shanyu Rong

Y

Yaoxu Lyu

Z

Zhongxia Zhao

P

Peterson Co

Y

Yibo Li

Y

Yi Han

S

Shaoxuan Xie

G

Guocai Yao

S

Songjing Wang

L

Leiduo Zhang

X

Xi Yang

Y

Yance Jiao

D

Donghai Shi

K

Kunchang Xie

S

Shaokai Nie

C

Chunlei Men

Y

Yonghua Lin

Z

Zhongyuan Wang

T

Tiejun Huang

S

Shanghang Zhang

Format Sitasi

Tan, H., Zhou, E., Li, Z., Xu, Y., Ji, Y., Chen, X. et al. (2026). RoboBrain 2.5: Depth in Sight, Time in Mind. https://arxiv.org/abs/2601.14352

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓