내가 좋아할 만한 콘텐츠
If you have a log from real experiments, check it. The gyroscope on G1 saturated at 8.72 rad/s, which is 500 degrees per second. This is an extremely small value. Once the gyro saturated, the fused orientation also becomes incorrect.
Human3R: Everyone Everywhere All at Once Note: I recorded the video from the interactive demo on their project page (linked in the comment below). Abstract (excerpt): Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scenes ("everywhere"), and…
MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency @dongki56, @jaehoon9301, Yonghan Lee, Sungmin Eum, Heesung Kwon, @dmanocha tl;dr: point maps from MoGe+dense correspondences from DKM->initial alignment->graph-based refinement with 3D points…
“You can’t make progress until you are able to measure it. Robotics still doesn’t have such a rallying call. No one agrees on anything.” I 💯 agree with the recent post from @DrJimFan. To break this impasse, we are excited to announce ManipulationNet (manipulation-net.org), a…
開発中のMW botは、家と融合するセミヒューマノイドロボット。完全人型ではなく基本は折り畳まれてパントリーに隠れていて、必要な時に出てきて双腕+箱を使って"汎用的な家事"をします 急発展するAIロボット技術を駆使して「人類を家事から解放する家」を作るのが目標 来年最初のデモを出します！🙇♂️
Bringing new meaning to the word NeRD at #CoRL2025. 🤓 Neural Robot Dynamics (NeRD) bridges the sim-to-real gap with a hybrid of neural modeling and analytical simulation, unlocking zero-shot transfer and continuous learning loops for optimal robotics training. Read more &…
Certifiably Optimal Doppler Positioning using Opportunistic LEO Satellites Baoshan Song, @weisong_wen, Qi Zhang, Bing Xu, @Qmohsu tl;dr: Doppler positioning LS->QCQP->relaxation->SDP arxiv.org/abs/2509.17198
There is a live streaming on Youtube for Open-Source Hardware Workshop! youtube.com/live/ZVPIJzF1d…
youtube.com
YouTube
Open-Source Hardware Workshop @ CoRL2025
This was corl. Prof Hang zhao. Covered this work tsinghua-mars-lab.github.io/SLAM-Former/
😠💢😵💫Tired of endless data collection & fine-tuning every time you try out VLA? Meet RDT2, the first foundation model that zero-shot deploys on any robot arms with unseen scenes, objects & instructions. No collection. No tuning. Just plug and play🚀 Witness a clear sign of…
👂 Now hear this👂 v1.3.7 of 3D BBS is here, you should check it out right away
I released v1.3.7 including recent PRs. Thank you ! github.com/KOKIAOKI/3d_bbs
I hoped of posting my unified Legged Robot Autonomy setup at this workshop, but OH LORD this world never lets me do a single thing I want.
🚀#CoRL2025 and #Humanoids2025 kick off tomorrow! Our group will At CoRL - organize one workshop & present two workshop posters. At Humanoids – give three main conference presentations, present two workshop posters, organize one workshop, and deliver one invited talk. Details👇
Quantized Visual Geometry Grounded Transformer Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu tl;dr: Post-Training Quantization->VGGT arxiv.org/abs/2509.21302
🤖 Can a humanoid robot hold extreme single-leg poses like Bruce Lee's Kick or the Swallow Balance? 🤸 💥 YES. Meet HuB: Learning Extreme Humanoid Balance 🔗 Project website: hub-robot.github.io
Stein’s lemma originally formulated for Gaussian distributions applies more generally to arbitrary continuous exponential families. Allow to derive identities between raw moments for polynomial exponential families. tinyurl.com/SteinLemmaEF
Probably nothing, but multiple devices recorded video of a venue, then sent that to the @AukiNetwork's growing number of community nodes, that then collaborated to stitch it all together into this 3D map of the venue... Collaborative data capture. Collaborative reconstruction.
🤖What if you want to train rough terrain humanoid locomotion but have only flat terrain demonstrations? ⛳️In ConsMimic, we introduce a principled pipeline to learn stylistic motions from demonstrations that may not align with task objectives. See you @corl_conf in Seoul!
Excited to share our #CoRL2025 paper: Constrained Style Learning from Imperfect Demonstrations under Task Optimality. We introduce ConsMimic, optimizing a style-imitation objective with near-optimal performance constraints. 🔗 sites.google.com/view/consmimic 📄 arxiv.org/abs/2507.09371…
United States 트렌드
- 1. Lions 58.4K posts
- 2. Lions 58.4K posts
- 3. Butker 6,903 posts
- 4. Goff 10K posts
- 5. #TNABoundForGlory 23.6K posts
- 6. Baker 47.2K posts
- 7. #OnePride 4,229 posts
- 8. Kelce 9,780 posts
- 9. #SNFonNBC N/A
- 10. #DETvsKC 2,530 posts
- 11. Cal Raleigh 3,663 posts
- 12. 49ers 42.1K posts
- 13. Leon Slater 1,791 posts
- 14. #RHOP 10.3K posts
- 15. Dan Campbell 1,729 posts
- 16. Ty Dillon 1,115 posts
- 17. Gausman 2,674 posts
- 18. Gibbs 4,530 posts
- 19. Denny 5,584 posts
- 20. Bucs 14.7K posts
내가 좋아할 만한 콘텐츠
-
Deni 🖥️
@awesomedev_Deni -
XNH
@xnhxnhxnhxnhxnh -
크썸
@twoo0220 -
쫑구
@zzong_gu -
가람🌈
@garam_withtulip -
Alice||앨리스
@aliceislazy1 -
이대은(Dae-eun Lee)
@2daeeun -
wec
@howtostudyRF -
LarissaCloud🕯
@larissacloud__ -
Hosung Joo
@whendoyoucome -
감자
@drumstickbear -
dev_c10aking
@c10aking -
헌천수
@podsjw -
mz는 개발 일기를 X로 써
@RUAKIM04 -
Bigchew
@29bigchew
Something went wrong.
Something went wrong.