Loading video...

Video Failed to Load

Go Home

This Unitree G1 performed surgery with teleoperation. First successful surgery with a humanoid. A surgeon steered it from a console the whole time. It used real surgical tools, not custom robotic ones. The G1 completed two live gallbladder removals on pigs. The work just published in Nature.

64,822 views • 3 months ago •via X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

British-Pakistani consultant gynaecologist and robotic surgeon Dr Amer Raza has set a new record in Britain after pioneering single-port robotic gynaecological surgery and leading a programme that has now successfully performed more than 400 procedures using the technology. Dr Amer Raza, a graduate of Nishtar Medical College, Multan, and his team at Cromwell Hospital in London have taken single-port robotic surgery from relatively straightforward benign gynaecological procedures to some of the most complex endometriosis operations, with the programme also providing training and surgical observation for doctors from the UK and abroad. Unlike conventional multi-port robotic surgery, which generally requires several abdominal incisions, single-port robotic surgery allows the camera and multiple robotic instruments to operate through one abdominal entry point, Dr Amer Raza told Geo News in an interview. He has also received two Master Surgeon accreditations in Robotic Surgery and Advanced Endometriosis Care for his work in robotic surgery and the treatment of complex endometriosis, becoming the only consultant to hold two such Master Surgeon accreditations in Europe. The British-Pakistani surgeon received the accreditations from the US-based Surgical Review Corporation (SRC) following an external review of his surgical practice, outcomes, complications, governance and standards of patient care. The latest achievement comes just three years after Dr Raza made another record while leading a surgery using the da Vinci Surgical System for the treatment of endometriosis, a condition that can seriously affect women's health and fertility.

Murtaza Ali Shah

16,787 views • 6 days ago

In just one week, Binh and I trained a full-body Unitree G1. Here's a recap: 1. Secured a Unitree G1 humanoid through a LinkedIn post 2. Deployed TWIST2 full-body teleoperation pipelines 3. Adapted TWIST2 for Zed stereo camera & collected full-body teleoperation samples (carried by Binh ) 4. Adapted & fine-tuned NVIDIA Gr00T N1.5 VLA on the TWIST2 public datasets, which I fine-tuned on an 8xNVIDIA H100 Cluster. We picked Gr00T N1.5 as it was trained with Unitree G1 embodiment data. 5. Adapted the TWIST2 codebase to stream in the actions from Gr00T via ZMQ using a co-located NVIDIA H100 for ~200ms inference latency 6. Tested the model in sim, then deployed to the real-world Unitree G1. We streamed a training sample observation to the VLA (as we didn't want to break robot in case real observations were OOD) We were the first team in the world to deploy the full TWIST2 data collection pipeline to the unitree g1 :) Much more work ahead though, which I'll work on as a side-project over the next months: 1. Exploring the various types of 'world models': video backbones, dynamics models, v-jepa-2 models. I believe these will generalize better & train much more data-efficiently than VLM backbones 2. Speeding up inference - I believe low-latency robotics inference will be a big challenge. There are many works in video diffusion which I'd like to test (e.g. SageAttention, SparseAttention, Drifting Models). Perhaps also writing custom CUDA kernels. 3. Economics of inference scaling :) What will be the compute demands as we scale inference up to millions of humanoids? Will it run on edge or on distributed 'co-located' inference clusters? These are questions I'd like to answer. Adapted TWIST2 codebase: Adapted Gr00T-N1.5 codebase: The ETH Robotics Club are doing a cool GTC Golden ticket competition with NVIDIA , so this is my submission :) The DGX Spark compute will get me a long way with initial prototyping & especially working on inference optimization for next-gen Blackwell GPUs #NVIDIAGTC #GOLDENTICKET #ETHRC

Arnie Ramesh

23,957 views • 7 months ago