NVIDIA and LG are building a next-generation humanoid robot that will make its debut at CES 2027

Q: What components from LG (actuators, sensors, batteries) will be integrated into the humanoid robot?

LG will supply actuators, sensors, and batteries for the humanoid robot by bringing together technologies from LG Electronics, LG Innotek, and LG Energy Solution. These LG subsidiaries will provide the physical components and other robot hardware.

Q: Which NVIDIA hardware platforms will power the LG humanoid robot and what are their key specs mentioned?

LG's humanoid robot will be built using NVIDIA Jetson Thor and the NVIDIA Isaac GR00T platform, powered by NVIDIA's open reasoning humanoid foundation model. NVIDIA Isaac GR00T and NVIDIA Jetson Thor hardware are described as offering low-latency 2070 FP4 TFLOPS of AI compute with 128 GB of memory.

Q: How does the Isaac GR00T vision-language-action (VLA) model enable task execution for the robot?

The Isaac GR00T vision-language-action model is a cross-embodiment multimodal model that takes language and image input and produces the actions needed to perform tasks across diverse environments, providing a strong foundation for human-like motion and task completion. Developers can start from this pretrained model that already encodes broad manipulation priors instead of training a policy from scratch, then adapt it to specific robots, tasks, and environments through post-training. The GR00T development platform also pairs this model with lab-based simulation to generate data and training information for iteration and testing.

Q: What role does NVIDIA Jetson Thor's memory and compute (128 GB, 2070 FP4 TFLOPS) play in the robot's capabilities?

The Jetson Thor’s 128 GB memory and low-latency 2070 FP4 TFLOPS of AI compute provide the on-robot processing required to run NVIDIA Isaac GR00T and the open reasoning humanoid foundation model. That compute and memory enable real-time, vision-language-action inference and training workflows that support human-like motion, task completion, and adaptation of the cross-embodiment model to specific robots, tasks, and environments.

LG and NVIDIA are partnering to accelerate the development of physical AI, which includes a full humanoid robot on track for a 2027 reveal.

VIEW GALLERY - 3

Kosta Andreadis

Senior Editor

Published Aug 17, 2026 1:32 AM CDT

1-minute read time

TL;DR: LG and NVIDIA signed an MOU to build a bipedal humanoid robot unveiled in early 2027, likely at CES. The robot will use NVIDIA Jetson Thor, Isaac GR00T (including its VLA model), and NVIDIA's humanoid foundation model, while LG supplies actuators, sensors, batteries, and manufacturing expertise.

Voice: Kosta AndreadisSpeed

0:00 / 3:22

At a recent event at NVIDIA's headquarters in Santa Clara, California, Chairman and CEO of LG Corp Kwang Mo Koo and NVIDIA Founder and CEO Jensen Huang signed a 'memorandum of understanding' that included the development of a next-generation "bipedal humanoid robot."

NVIDIA and LG are building a next-generation humanoid robot that will make its debut at CES 2027 2

VIEW GALLERY - 3 IMAGES

According to the press release, the humanoid robot will be unveiled to the public in early 2027, presumably at CES 2027, and will be built using NVIDIA Jetson Thor and NVIDIA Isaac GR00T, and powered by NVIDIA's open reasoning humanoid foundation model. On the LG side, the company will bring together LG Electronics, LG Innotek, and LG Energy Solution technologies under a single banner covering actuators, sensors, batteries, and all the physical stuff you expect from a robot.

At Computex 2026, NVIDIA unveiled its NVIDIA Isaac GR00T Development Platform, an open-source platform built specifically for humanoid robotics, created in part to speed up development. It includes lab-based simulation to generate data and training information, and lets developers demonstrate, iterate, and test advancements before real-world deployment.

The key component is the Isaac GR00T vision-language-action (VLA) model, which provides a strong foundation for human-like motion and task completion and will serve as the basis for new tasks and training specific to the robot being developed and its function(s).

"It's a cross-embodiment model that takes multimodal input, including language and images, and produces the actions needed to perform tasks across diverse environments," NVIDIA explains. "Instead of training a policy from scratch, developers can start from a model that already encodes broad manipulation priors and adapt it to specific robots, tasks, and environments through post-training."

NVIDIA Isaac GR00T and NVIDIA Jetson Thor hardware offer low-latency 2070 FP4 TFLOPS of AI compute with 128 GB of memory. And with this partnership and technology, LG plans to "accelerate the spread of AI by building industry-leading references."

NVIDIA and LG are building a next-generation humanoid robot that will make its debut at CES 2027 3

Frequently Asked Questions

TweakBot answers common questions about this news using TweakTown's own coverage from this page and related content from our archive. All answers are generated from TweakTown content and not outside sources. Tap a question to reveal the answer, or type your own below related to this content.

Question #1

What components from LG (actuators, sensors, batteries) will be integrated into the humanoid robot?

Question #2

Which NVIDIA hardware platforms will power the LG humanoid robot and what are their key specs mentioned?

Question #3

How does the Isaac GR00T vision-language-action (VLA) model enable task execution for the robot?

Question #4

What role does NVIDIA Jetson Thor's memory and compute (128 GB, 2070 FP4 TFLOPS) play in the robot's capabilities?

Have a question about this content not listed here? Ask below and TweakBot will answer it.

"The defining opportunity of physical AI is to give every machine the ability to understand the real world, reason and act safely alongside people - reshaping everyday life from the home and factory floor to the road," Jensen Huang, founder and CEO of NVIDIA, said. "Building on years of collaboration, LG and NVIDIA are combining LG's leadership in product engineering and manufacturing with NVIDIA technology to accelerate the next era of robots."