🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

K-Net addresses instance/semantic/panoptic segmentation in a unified, simple, and effective framework. SOTA on COCO Panoptic Segmentation with 55.2% PQ. Our NeurIPS'21 paper: arxiv.org/abs/2106.14855 Project Page: mmlab-ntu.com/project/knet/ Code: github.com/ZwwWayne/K-Net

What Are Expected Queries in End-to-End Object Detection? deepai.org/publication/wh… by Shilong Zhang et al. including Jiaqi Wang, Jiangmiao Pang #Epoch #ComputerVision

Monocular 3D Object Detection with Depth from Motion deepai.org/publication/mo… by Tai Wang et al. including Jiangmiao Pang #Estimator #Statistics

Congrats to Tai’s first in-person conference during his PhD, as well as the last time : ). Talk with him about our work that using multi-view geometry to boost the performance of monocular 3d object detection.

🌪️ Despite the ongoing super Typhoon Saola in Hong Kong, I'm excited to introduce PointLLM! 🌈🔍 It's a multi-modal large language model that understands point clouds. 1/4🧵 🔗 Demo: http://101.230.144.196 📄 Paper: arxiv.org/abs/2308.16911 💻 Code: github.com/OpenRobotLab/P…

🔥Unified Human-Scene Interaction via Prompted Chain-of-Contacts🔥 #UniHSI Code: github.com/OpenRobotLab/U… Project Page: xizaoqu.github.io/unihsi/ ArXiv: arxiv.org/abs/2309.07918 Hugging Face: huggingface.co/papers/2309.07…

Seeking a policy that can empower your robot to traverse any terrain? Our Hybrid Internal Model achieves this easily and only costs 1 hour. Key Insight: Estimating environmental dynamics with the robot's response. ArXiv: arxiv.org/abs/2312.11460 Code: github.com/OpenRobotLab/H…

Check out our EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI ArXiv: arxiv.org/abs/2312.16170 Code: github.com/OpenRobotLab/E… huggingface.co/papers/2312.16…

💯

Thanks AK for posting our work! Want a humanoid robot but do not have a good fit? Check out our H-Infinity Control Policy! We let a quadruped robot stand up, walk, and keep balance with extreme disturbances. ArXiv: arxiv.org/abs/2404.14405

We will present HIMLoco at Thu 9 May 10:45 a.m. - 12:45 p.m. at Halle B #32. See you in Vienna! #ICLR2024 Also, the code of HIMLoco has been released! Have a try: github.com/OpenRobotLab/H…

We will present UniHSI at Wed 8 May 10:45 a.m. - 12:45 p.m. at Halle B #11. Hope to see you! #ICLR2024 Code has been released at github.com/OpenRobotLab/U…

We are excited to introduce #GRUtopia! The first simulated **city-scale** interactive 3D society designed for various robots that serve humans! Integrate GRScenes, GRResidents, and GRBench! 100k+ Interactive scenes, 89 scene categories~ Code: github.com/OpenRobotLab/G…

Excited to introduce the Perceptive Internal Model (PIM) for Humanoid Robots! The first policy simultaneously for: - Go up and down stairs, jump gaps, and 50cm high platforms. - Indoor and outdoor scenarios. - Unitree H1 and Fourier GR-1 robots. Paper: arxiv.org/abs/2411.14386

Check out our latest work on humanoid whole-body control！

Our latest progress on Humanoid Standing-Up Control!

Yet another new progress on humanoids. Congrats to Huayi and the team！

zero-shot sim2real transfer on manipulation

Humanoid Cockpit - Homie I’ve always believed that teleoperation systems are crucial for robots. Homie combines RL Policy and hardware systems to enable humanoid robots to perform stable loco-manipulation across large spaces. It can stably squat, stand up, and move. Stay tuned