Official account for OpenDriveLab @hkuniversity and Beyond. We do cutting-edge research in Robotics, Autonomous Driving. Email: [email protected]
Hong Kong
Joined June 2022
- Tweets241
- Following67
- Followers1.9K
- Likes279
OpenDriveLab retweeted
Check out Jin’s latest work on utilizing human data to unlock robot whole-body capabilities! #WBI #WholeBodyIntelligence opendrivelab.com/EgoHumanoid…
OpenDriveLab retweeted
Let's go Archon!!!!! 🤖
🤖 Building Whole-Body Intelligence for the Real World. Were Just Getting Started.
From bending down to pick up objects and navigating steps to autonomously clearing tables, operating dishwashers, and organizing refrigerators, our robots are learning to perceive, move, manipulate, and coordinate their entire bodies in real-world environments.
Powered by our Whole-Body Intelligence (WBI) framework, were building generalist humanoid foundation models by combining large-scale human whole-body data pretraining, context-aware behavioral foundation models, and efficient post-training with real-robot data - turning human experience into real-world robotic skills.
👉 Watch Whole-Body Intelligence in action in our three-minute demo. More to come. Stay tuned at archon.tech
#ArchonRobotics #WholeBodyIntelligence #WBI #Humanoid #PhysicalAGI
OpenDriveLab retweeted
Full episode dropping soon!
Geeking out with @idomihs on EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration opendrivelab.com/EgoHumanoid…
Co-hosted by @micoolcho @DJiafei
OpenDriveLab retweeted
🚀 Excited to announce our real world VLN dataset !
📦 Human first-person collected indoor & outdoor & night.
🏆 LARGEST to date.
Check it out now on Hugging Face and accelerate your real world navigation research!
👇 🔗 huggingface.co/datasets/Open…
#EmbodiedAI #VLN
OpenDriveLab retweeted
SimScale is fully open-sourced!!!
📄 arXiv: arxiv.org/abs/2511.23369
💻 Code: github.com/OpenDriveLab/SimS…
🤗 Ckpts + Sim Data: huggingface.co/datasets/Open…
OpenDriveLab retweeted
🎉 Excited to share our recent work SimScale, which has been accepted to CVPR 2026 as Oral presentation!
🤖Can we improve policies via scaling synthetic experience?
😢End-to-end driving policies struggles on safety-critical & OOD scenarios that are rare in human logs.
To tackle this, SimScale features:
🏗️ A scalable simulation pipeline synthesizes diverse, high-fidelity reactive driving scenarios upon existing logs. (See attached visualization as one synthetic data sample).
🚀 With pseudo-expert demonstrations, Sim-real co-training boosts LTF / DiffusionDrive / GTRS-Dense, up to +8.6 EPDMS on navhard, +2.9 on navtest.
🔬 Performance scales smoothly by adding simulation data alone, with no extra real-world data needed.
Joint effort by @HCTian713, @francislee2020, @OpenDriveLab, @sephy_li
OpenDriveLab retweeted
🤗RISE got accepted to RSS 2026! Can't wait to see everybody in Sydney!
💻Code: github.com/OpenDriveLab/RISE
RISE (3/N)
To address this bottleneck, we introduce RISE: Reinforcement learning via Imagination for SElf-improving robots. RISE shifts the learning environment from physical world to a Compositional World Model, which first emulates future observations for proposed actions, then evaluates imagined states to derive advantage for policy improvement.
OpenDriveLab retweeted
🌏 RISE is now open-sourced!
github.com/OpenDriveLab/RISE
🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach.
😌After sustained effort, we’re now seeing encouraging progress.
🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model
opendrivelab.com/kai0-rl/
arxiv.org/abs/2602.11075
RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision.
Incredible teamwork with @lin_kunyang111 @francislee2020 @YueXiangyu @HaoZhao_AIRSUN @smch_1127
OpenDriveLab retweeted
🚀 EgoHumanoid is now open-sourced!
A framework to realize human-to-humanoid transfer for loco-manipulation.
Full pipeline released: Pico human data collection → Unitree G1 robot data collection→ VLA training & deployment. All code available 👇
⭐ github.com/OpenDriveLab/EgoH…
Humanoid robots have been prisoners of the lab. We set them free — with human data.
We present EgoHumanoid: The first endorsement of human-to-humanoid transfer for whole-body loco-manipulation.
🔗 Home: opendrivelab.com/EgoHumanoid
📑 Arxiv: arxiv.org/abs/2602.10106
🧵👇
OpenDriveLab retweeted
Just saw Sonic — it’s incredibly solid. By far the best whole-body control model I’ve seen so far. It opens up an invaluable path to acquiring full-body coordination data for humanoid robots. Huge congrats to the team and big thanks for open-sourcing it! 🙌🔓
SONIC is now open-source!
Generalist whole-body teleoperation for EVERYONE!
Our team has long been building comprehensive pipelines for whole-body control, kinematic planner, and teleoperation, and they will all be shared.
This will be a continuous update; inference code + model already there, training code and gr00t integration coming soon!
Code: github.com/NVlabs/GR00T-Whol…
Docs: nvlabs.github.io/GR00T-Whole…
Site: nvlabs.github.io/GEAR-SONIC/
OpenDriveLab retweeted
At the RI seminar at CMU yesterday, I presented a 3 level analysis of robot skills & discussed the pros and cons of teleoperation, simulation, and learning from videos, before presenting our research. Enjoy! youtube.com/watch?v=ry8itipz…
OpenDriveLab retweeted
🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach.
😌After sustained effort, we’re now seeing encouraging progress.
🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model
opendrivelab.com/kai0-rl/
arxiv.org/abs/2602.11075
RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision.
Incredible teamwork with @lin_kunyang111 @francislee2020 @YueXiangyu @HaoZhao_AIRSUN @smch_1127
OpenDriveLab retweeted
🧥 Live-stream robotic teamwork that folds clothes. 6 clothes in 3 minutes straight.
χ₀ = 20hrs data + 8 A100s + 3 key insights:
- Mode Consistency: align your distributions
- Model Arithmetic: merge, don't retrain
- Stage Advantage: pivot wisely
🔗 mmlab.hk/research/kai0
OpenDriveLab retweeted
Humanoid robots have been prisoners of the lab. We set them free — with human data.
We present EgoHumanoid: The first endorsement of human-to-humanoid transfer for whole-body loco-manipulation.
🔗 Home: opendrivelab.com/EgoHumanoid
📑 Arxiv: arxiv.org/abs/2602.10106
🧵👇
OpenDriveLab retweeted
Glad to share me and my folks work of the last research cycle, good luck and have fun. Upvote on HF is appreciated!
χ0: huggingface.co/papers/2602.0…
χ0, a resource-efficient robotic manipulation framework addresses distributional shifts through model arithmetic, stage-aware advantage estimation, and train-deploy alignment to achieve long-horizon task reliability.
RISE: huggingface.co/papers/2602.1…
RISE, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision.
EgoHumanoid: huggingface.co/papers/2602.1…
EgoHumanoid, the first endorsement of human-to-humanoid transfer for whole-body loco-manipulation.
SparseVideoNav: huggingface.co/papers/2602.0…
Vision-language navigation systems traditionally require detailed instructions but can be improved by incorporating video generation models with sparse future planning for faster, more efficient real-world deployment.
RT @ftm_guney: I’m not at #ICCV25 but @ShadiSHamdan will be there to present our work ETA with @OpenDriveLab.
go talk to him to learn how…
OpenDriveLab retweeted
【🔥Graduate course on embodied AI - DATA8017 “Fundamentals of Autonomous Intelligent Systems” by Prof Hongyang Li🚗🤖】
Join us in Semester 1, 2025/26 to shape the next generation of autonomous tech at HKU IDS!
👉 Course Syllabus: datascience.hku.hk/data8017/
#HKUIDS #Robotics
OpenDriveLab retweeted
Super happy to have #HKUBulletin cover our research highlights;) Embodied AI on the horizon
🚗The technology behind embodied AI and autonomous cars has made huge strides in recent times, helped in part by a system devised by #HKU Professor Li Hongyang (@francislee2020) and his collaborators.
📖Read and 🎧listen now at the #HKUBulletin: bulletin.hku.hk/cover-story-…
OpenDriveLab retweeted
【Embark on a Robotic Revolution at HKU IDS! 🤖】
With keen interest in exploring how AI-driven robotics is transforming our world? Join our new course, CCAI9025!
👉More details: datascience.hku.hk/study/res…
Unlock your potential to shape the tech frontier!
#HKU #Robotics
OpenDriveLab retweeted
🚀 HERE WE GO! Join us at CVPR 2025 for a full-day tutorial: “Robotics 101: An Odyssey from a Vision Perspective”
🗓️ June 12 • 📍 Room 202B, Nashville
Meet our incredible lineup of speakers: @shahdhruv_ @GuanyaShi @davsca1 @iamborisi @deepakpathak @akanazawa @du_yilun and I covering topics from agile robotics to safe physical AI.
More details and the full schedule are available at: opendrivelab.com/cvpr2025/tu…
#CVPR2025 @CVPR
