Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Introducing Axis Dataset V1 - the simulation dataset for scalable robot manipulation. Can noisy, crowdsourced simulation data support embodied pretraining? Yes—with enough coverage and diversity. Continual pretraining on AXIS dataset V1 lifts π0.5 from 83.9% to 88.8% on LIBERO-Plus, with performance improving consistently as the pretraining data scales from...

114,840 görüntüleme • 3 ay önce •via X (Twitter)

34 Yorum

Stone Tao profil fotoğrafı
Stone Tao3 ay önce

don’t want to put too much shade on the progress (i think sim datasets can be good ideas if executed well!), but improving on libero (which is also a sim benchmark) means very little unfortunately

Thor profil fotoğrafı
Thor3 ay önce

Let's goo 🔥

Hazzy profil fotoğrafı
Hazzy3 ay önce

you edit too much intern

KABILA profil fotoğrafı
KABILA2 ay önce

Cookingg

Jontu profil fotoğrafı
Jontu2 ay önce

This is a strong proof that diverse simulation data can meaningfully improve embodied AI.

boyBrands_ profil fotoğrafı
boyBrands_3 ay önce

He has arrived🔥

Sami profil fotoğrafı
Sami3 ay önce

So much excited for this

Apurbo profil fotoğrafı
Apurbo2 ay önce

We are so excited about this 🤘

AL Shifat profil fotoğrafı
AL Shifat3 ay önce

Axis going to make history

dviet.eth profil fotoğrafı
dviet.eth3 ay önce

This is exactly the kind of infrastructure Physical AI needs. Quality data compounds, and so does robot intelligence. Excited to see Axis Dataset V1 keep growing 😆

Noodle profil fotoğrafı
Noodle3 ay önce

cool to see those teleop sessions actually pushing the libero-plus numbers up

Acee (✱,✱) profil fotoğrafı
Acee (✱,✱)3 ay önce

Keep cooking 👌

Piggie 🧡|Bird profil fotoğrafı
Piggie 🧡|Bird3 ay önce

Overall success rate increased by 5.8%.

0xmowra.eth profil fotoğrafı
0xmowra.eth3 ay önce

Axis V1 dataset boosting robot learning with crowdsourced simulation data impressive

Red profil fotoğrafı
Red2 ay önce

Great work

| MinhDucc | Shark profil fotoğrafı
| MinhDucc | Shark3 ay önce

Axis LFG 😍

sasafonda✱,✱) profil fotoğrafı
sasafonda✱,✱)3 ay önce

gaxis

namnew profil fotoğrafı
namnew3 ay önce

gAxis

VINAY (✱,✱) profil fotoğrafı
VINAY (✱,✱)3 ay önce

Axis cooking 🔥

savagezz profil fotoğrafı
savagezz3 ay önce

cooking something

Hoangdong (✱,✱) profil fotoğrafı
Hoangdong (✱,✱)3 ay önce

gAxis

clover profil fotoğrafı
clover3 ay önce

move gaxis

vinhle (✱,✱) 🍚 ⛓ ./ profil fotoğrafı
vinhle (✱,✱) 🍚 ⛓ ./3 ay önce

Exciting to see the potential of crowdsourced simulation data in robotics, and impressive results from continual pretraining on Axis Dataset V1.

Aurora Lux profil fotoğrafı
Aurora Lux3 ay önce

AXIS Dataset V1 is a strong step forward for embodied AI—scalable, diverse simulation data is proving to be a powerful foundation for better robot learning. 🤖🚀

cbeta.base.eth profil fotoğrafı
cbeta.base.eth3 ay önce

lets goo team fight fight fight

rara profil fotoğrafı
rara3 ay önce

gaxis lfg

Linh (✱,✱) profil fotoğrafı
Linh (✱,✱)3 ay önce

Axis Dataset V1 is impressive

Nova profil fotoğrafı
Nova3 ay önce

The bot is terrible. Please update it. Its performance is like a primitive human living in a cave 😤

MAS_Enpici (✱,✱) profil fotoğrafı
MAS_Enpici (✱,✱)3 ay önce

big update and new insight

yellowopus profil fotoğrafı
yellowopus3 ay önce

lets cooking bro

KADAFER profil fotoğrafı
KADAFER3 ay önce

let him cook 🔥

dondonat (✱,✱) profil fotoğrafı
dondonat (✱,✱)3 ay önce

gaxis keep building

sagar profil fotoğrafı
sagar3 ay önce

Let's goo 🙌

Gujil Ruipa profil fotoğrafı
Gujil Ruipa3 ay önce

Open datasets like this can accelerate robotics research through collaborative innovation

Benzer Videolar

In my past research experience, finding or developing an appropriate simulation environment, dataset, and benchmark has always been a challenge. Missing features, limited support, or unexpected bugs often occupied my days and nights. Moreover, current simulation platforms are relatively fragmented—making it challenging to replicate the success of the RT-X dataset in unifying community efforts. Introducing RoboVerse, we provide a unified platform, dataset, and benchmark for scalable and generalizable robot learning. We hope to build a shared foundation to combine the community efforts. RoboVerse includes: MetaSim: We carefully designed a configuration system and a universal interface to align current robotic simulators. With MetaSim, you can use any simulator with the same code—bringing together the community’s diverse efforts under one framework! RoboVerse Dataset and Benchmark: We unify popular simulation environments and benchmarks into a single cohesive system and introduce the RoboVerse dataset—a large-scale, high-quality synthetic dataset. Additionally, we propose a standardized benchmark across both imitation learning and reinforcement learning. A cool feature enabled by our unified framework: Hybrid Simulation! You can now integrate physics engines and renderers from different simulators—e.g., using MuJoCo precise physics with Isaac photorealistic rendering. This not only elevates simulation fidelity but also significantly enhances real-world transfer performance across complex robotic applications. Hopefully, our team’s efforts could serve the robotic community to thrive vibrantly in the years to come. RoboVerse is open-sourced🥳!!! Project Page: Documentation: Github Repo: Paper:

Haoran Geng

84,425 görüntüleme • 1 yıl önce