Official account for OpenDriveLab @hkuniversity and Beyond. We do cutting-edge research in Robotics, Autonomous Driving.
Email: contact@opendrivelab.com
📣 #Recognition#ResearchAward As we usher in the Year of Horse, our team recognizes outstanding members from the past year in the exceptional contribution of areas. Congratulations!!! Let’s rock ‘n’ roll in 2026 🕶️🍾🎆🥂#opendrivelab
Proud to co-organize the AlpaSim E2E Closed-Loop Challenge with @kesai_labs and NVIDIA’s ASPIRE Group. This post traces the journey from NAVSIM to photorealistic closed-loop evaluation—and our shared effort to make progress in autonomous driving measurable. Learn more ↓
🚀 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
🚀 Join us at the #CVPR 2026 Workshop:
From Labs to Life: Embodied Intelligence in the Wild
(opendrivelab.com/cvpr2026/wo…)
As embodied AI moves into the real world, we ask: how can agents perceive, reason, and act reliably in the wild?
Featuring invited talks from: Hao Su, Zhiyu Huang, Jiahui Lei, Yilun Du, Rika Antonova, Jiatao Gu.
📅 9:00 AM - 5:30 PM, June 3, 2026
📍 Four Seasons 1, Colorado Convention Center.
#CVPR#EmbodiedAI#PhysicalAI#Robotics
🎉 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
📢📢📢 Call for Contributions @ RSS 2026
Towards Robust Execution of Long-Horizon Whole-Body Control Tasks
🧑💻👩💻🧑💻 Speakers:
- Javier Alonso-Mora (TU Delft)
- Leslie Pack Kaelbling (MIT)
- Shan Luo (King's College London)
- Hamidreza Kasaei (University of Groningen)
- Roberto Martín-Martín (UT Austin)
- Fan Shi (NUS)
📝📝📝 Call for Contributions:
We invite researchers to share their work with the community through submissions to the workshop in a variety of formats beyond traditional papers, including reports, demos, video, and etc. Submissions may include research papers or reports, but we equally welcome alternative formats such as videos demonstrating systems in action, demos, interactive artifacts, or other creative presentations of research ideas. We particularly welcome ongoing, preliminary, or exploratory work.
🌍🌍🌍 Website:
opendrivelab.com/rss2026/wor…#RSS2026#AI#Embodied
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.
🚀 MM-Hand 1.0 Tech Report released: a 21-DoF multi-modal modular dexterous robotic hand with remote tendon-driven actuation.
Motors are relocated outside the hand, freeing space for tactile sensors, joint encoders, in-palm stereo vision, and maintainable modular fingers.
MM-Hand achieves 25N fingertip force through 1m tendon-sheath transmission and supports closed-loop joint control for dexterous manipulation research.
Paper: arxiv.org/abs/2604.17245
Page: opendrivelab.com/MM-Hand#Robotics#DexterousHand#EmbodiedAI
🧐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
【1/5】🌍 WorldEngine: Towards the Era of Post-Training for Physical AI
🎯 A post-training framework for Physical AI that systematically addresses the long-tail safety-critical data scarcity problem in autonomous driving.
🧱The missing infrastructure for Physical AI post-training in AD. Open-source. Production-validated.
github.com/OpenDriveLab/Worl…#WorldEngine#PhysicalAI#OpenDriveLab
UMI made robot data collection intuitive.
🤖 TAMEn takes it further — bringing vision and touch into a unified, closed-loop learning system.
🌏 opendrivelab.com/TAMEn
📑 arxiv.org/abs/2604.07335
🔗 github.com/OpenDriveLab/TAME…
✨ What’s new:
- Dual-mode data collection (MoCap ↔ VR)
- Online replayability check
- AR-in-the-loop + real-time tactile feedback (tAmeR)
- Self-evolving pyramid data pipeline
🚀 Results:
34% → 75% success rate on bimanual tasks.
This marks a shift from usable data to self-improving data engines.
TAMEn turns robots from "blind operators" into tactile-aware, evolving collaborators.
#EmbodiedAI#Tactile#Robotics#Bimanual#TAMEn
#WorldEngine is one of the most exciting projects in AD in the past years!
It's a post-training framework tackling the scarcity of long-tail safety-critical scenarios by: mining -> 3DGS reconstruction and dynamic agents control w/ behavior world models -> RL post-training.
Introducing #WorldEngine, github.com/OpenDriveLab/Worl…, a two-year long project. The missing infrastructure for Physical AI post-training in Autonomous driving. Open-source. Production-validated.