Skild AI Launches S1 Robot Model Trained on NVIDIA Physical AI Stack
스킬드AI(Skild AI)는 엔비디아의 시뮬레이션 및 학습 기술을 기반으로 구축한 새로운 로봇 파운데이션 모델 S1이 단 한 번의 영상 시청만으로 낯설고 긴 작업을 학습한다고 밝혔다.
한 줄 답
What did Skild AI announce with NVIDIA about its new S1 robot model?
스킬드AI(Skild AI)가 단 한 번의 영상 시연만으로 재훈련 없이 새로운 다단계 작업을 학습하는 로봇 파운데이션 모델 'S1'을 공개했다. 엔비디아의 아이작 랩(Isaac Lab), 코스모스(Cosmos), 옴니버스(Omniverse), 텐서RT(TensorRT) 기술을 기반으로 구축된 S1은 새로운 작업에서 66%의 단계 성공률을 기록해, 9%에 그친 비교 시스템을 크게 앞섰다고 스킬드AI는 밝혔다. 회사의 연간 매출 실행률(run rate)은 현재 1억 달러에 달한다.
핵심 요약
- 스킬드 AI는 자사의 로봇 파운데이션 모델 S1이 가중치를 업데이트하거나 과제별 재학습을 거치지 않고도, 단 한 번의 시연 영상만으로 처음 접하는 장시간 과제를 학습할 수 있다고 밝혔다.
- The company reports S1 succeeded at about 66% of steps on new multistep tasks in its tests, compared with 9% for a similar AI system it compared against.
- Skild는 데이터 생성부터 시뮬레이션, 학습, 배포에 이르기까지 Isaac Lab, Cosmos, Cosmos Curator, Omniverse, Isaac Sim, Nsight, TensorRT 등 NVIDIA 기술을 활용해 S1을 구축하고 학습시켰다.
- Skild says it reached a $100 million annual revenue run rate roughly 10 months after its first commercial deployment and has more than 60 deployment partnerships.
- 스킬드(Skild), 엔비디아, 폭스콘이 엔비디아 블랙웰 시스템을 조립하기 위해 듀얼암 매니퓰레이터에 스킬드 브레인을 도입한다고 발표했다.
Skild AI has released S1, a robot foundation model the company says can learn an unfamiliar, multistep task from a single video demonstration without retraining or additional task-specific data. The model, which launched last week according to NVIDIA, was built and trained using NVIDIA's physical AI infrastructure across data generation, simulation, training and deployment.
How S1 Works
Skild says an operator records a video of a task and feeds it to S1 as a prompt. The model interprets the objects, intent and sequence shown in the video, then maps that information onto actions for whichever robot it is controlling, without updating its weights. The company calls this approach in-context learning.
According to Skild, S1 can carry out unfamiliar tasks lasting up to 10 minutes, including plant potting, pancake making, pour-over coffee brewing and kit assembly, some involving dozens of manipulation steps the robot hasn't previously performed in that order. In one plant-potting test cited by the company, the team went from recording a demonstration to autonomous execution on hardware in 11 minutes. Skild also says the model can adjust when objects move and recover from errors during a task.
Skild reports that in its tests on new, multistep tasks, S1 succeeded at about 66% of steps, compared with 9% for a similar AI system, and estimates that one short video example can provide value comparable to roughly 380 hands-on training examples, which the company says would otherwise take a person 50 to 100 hours to collect manually.
NVIDIA Technology Behind the Model
According to NVIDIA, Skild trained its "shared robot brain" using simulation, human video and teleoperation data, drawing on several parts of NVIDIA's stack. Cosmos, described as an open world foundation model, is used to diversify training data and convert video into structured descriptions, while Cosmos Curator annotates, filters and organizes data at scale.
Skild also uses NVIDIA's Omniverse libraries and the Isaac Sim framework to generate data and validate robot behavior in simulated environments before real-world deployment, and applies reinforcement learning in Isaac Lab, an open modular robot learning framework powered by the Newton physics engine, to model forces, contact, collision and pressure. NVIDIA said it and Skild are jointly developing new GPU-accelerated simulation solvers for modeling how robots grip and manipulate objects, which will be added to Newton for all developers. NVIDIA Nsight tools are used to identify training performance bottlenecks, and the TensorRT software development kit optimizes the model for inference.
Commercial Deployment
NVIDIA states that Skild reached a $100 million annual revenue run rate about 10 months after its first commercial deployment and has established more than 60 deployment partnerships spanning manufacturing, logistics, inspection, security and food preparation.
One active deployment, described in the announcement, involves Skild, NVIDIA and Foxconn using the Skild Brain on dual-arm manipulators for assembly of NVIDIA Blackwell systems. In a demonstrated workflow, a robot installs a busbar and limit block and fastens 16 screws while adapting to disturbances during the task, according to NVIDIA.
Deepak Pathak, cofounder and CEO of Skild AI, said in the announcement: "Learning by experience, and not preprogramming, is the step change that has happened in robotics. NVIDIA Isaac Lab and NVIDIA Cosmos technologies help Skild create the scalable, diverse experience its robots need to learn across many scenarios and embodiments."
Source: NVIDIA Blog, "Skild AI Taps NVIDIA Physical AI to Teach Robots New Tasks From a Single Video," published September 10, 2026.
자주 묻는 질문
- What is Skild AI's S1 model?
- S1은 스킬드AI(Skild AI)가 내놓은 로봇 파운데이션 모델로, 단 한 번의 시연 영상만 보여주면 재훈련 없이도 여러 단계로 이루어진 새로운 작업을 학습해 수행할 수 있다고 회사 측은 설명한다.
- How does S1 learn new tasks?
- 스킬드에 따르면, 오퍼레이터가 원하는 작업을 담은 영상을 녹화해 모델에 프롬프트로 제공하면, S1은 영상에 나타난 사물과 동작 순서를 해석해 눈앞에 있는 로봇을 위한 행동으로 매핑한다. 회사는 이 기법을 '인컨텍스트 학습'이라고 부른다.
- What NVIDIA technologies did Skild use to build S1?
- 스킬드는 데이터에는 엔비디아의 코스모스(Cosmos)와 코스모스 큐레이터(Cosmos Curator)를, 시뮬레이션에는 옴니버스(Omniverse)와 아이작 심(Isaac Sim)을, 강화학습에는 뉴턴 물리 엔진을 탑재한 아이작 랩(Isaac Lab)을, 훈련 및 추론 최적화에는 엔사이트(Nsight)와 텐서RT(TensorRT)를 사용했다고 밝혔다.
- Where is the technology being deployed?
- 스킬드는 자사와 엔비디아, 폭스콘이 스킬드 브레인을 탑재한 양팔 로봇을 활용해 엔비디아 블랙웰 시스템을 조립하고 있으며, 이 외에도 제조, 물류, 검사, 보안, 식품 조리 분야에서 60건이 넘는 배치 파트너십을 맺고 있다고 밝혔다.