PulseAugur
EN
LIVE 15:08:10
中文(ZH) 3万小时触觉数据补齐具身智能“手感”！新智具身&复旦报告三连发

Robots gain 'touch' with 30,000 hours of tactile data from XinZhi Embodied & Fudan

By PulseAugur Editorial · [3 sources] ·

XinZhi Embodied and Fudan University have released a series of technical reports introducing the N0 series models, which aim to enhance embodied intelligence by incorporating tactile data. The project includes a large dataset of over 30,000 hours of visual-tactile interaction data, along with models like N0-Foundation for unified tactile representation and N0-VTLA for predictive tactile sensing. These advancements are intended to improve robot manipulation capabilities, enabling them to better understand and interact with the physical world through touch, moving beyond purely visual perception. AI

IMPACT Enhances robot manipulation by integrating tactile feedback, potentially improving performance in complex physical tasks and advancing the field of embodied AI.

RANK_REASON The cluster details technical reports and models released by research institutions, focusing on advancements in tactile data for embodied intelligence.

Read on 量子位 (QbitAI) →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Robots gain 'touch' with 30,000 hours of tactile data from XinZhi Embodied & Fudan

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster details technical reports and models released by research institutions, focusing on advancements in tactile data for embodied intelligence.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
51 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. 量子位 (QbitAI) TIER_1 中文(ZH) · henry ·

    The World Model Has Tactile Sense! 500,000 Hours of Video Train the First Implicit Tactile World Action Model

  2. 量子位 (QbitAI) TIER_1 中文(ZH) · 鱼羊 ·

    30,000 Hours of Tactile Data Complete Embodied Intelligence "Feel"! Xingzhi Embodied & Fudan Report Three Consecutive Releases

    项目数据模型均开源

  3. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    30,000 Hours of Tactile Data Fills Embodied Intelligence Gap: XinZhi Embodied and Fudan University Release Three Technical Reports on Haptic Sensing

    XinZhi Embodied and Fudan University publish three technical reports covering 30,000 hours of tactile data for embodied intelligence, addressing the missing touch sensing capability in robot manipulation.

RELATED ENTITIES

RELATED TOPICS