NVIDIA Physical AI: Robotaxi + Skild AI Demo 2026

Published September 12, 2026 — Santa Clara, California. NVIDIA announced on September 10, 2026 major expansions to its physical AI portfolio: physical AI for robotaxi, Skild AI single-video training demo, Jetson Thor robotics platform, Cosmos world foundation model updates, and Isaac Lab/Sim updates. Targets robotaxi, humanoid robots, industrial automation, and other physical AI applications.

Data last verified September 12, 2026 from NVIDIA blog (September 10, 2026), AP coverage, Skild AI research, and NVIDIA developer documentation.

Quick Answer

NVIDIA announced Sep 10, 2026: physical AI for robotaxi + Skild AI single-video training demo. Components: (1) DRIVE Hyperion 9 - 9th-gen autonomous vehicle reference platform, 2,000 TOPS compute, full DriveOS stack. (2) Skild AI partnership - training autonomous systems from single video, 1000x data reduction. (3) Jetson Thor - next-gen robotics computer, Blackwell GPU, 2,000 TOPS for humanoid robots. (4) Cosmos world model updates - physics-based simulation. (5) Isaac Lab/Sim - robot training simulation. Target: robotaxi, humanoid, industrial automation (NVIDIA blog, September 10, 2026; AP, September 10, 2026).

NVIDIA physical AI portfolio overview

Source: NVIDIA blog (September 10, 2026); AP coverage; NVIDIA developer documentation.

DRIVE Hyperion 9 for robotaxi

DRIVE Hyperion 9 is NVIDIA's ninth-generation reference platform for autonomous vehicle development. The platform is designed for L4 (fully autonomous under defined conditions) robotaxi and trucking applications.

Hardware

• Compute: 2x NVIDIA Drive AGX Thor processors, 2,000 TOPS of AI performance.
• Sensors: 12 surround cameras (8MP, 60Hz), 9 radars (long/medium/short range), 2 lidars (128+ channels), 12 ultrasonics.
• Positioning: GNSS receiver, IMU, wheel odometry.
• Connectivity: 5G, Wi-Fi 6E, Ethernet, CAN bus for vehicle integration.

Software

• DriveOS: safety-certified operating system (ASIL-D), sensor drivers, runtime.
• DriveWorks: sensor fusion, perception, planning, control middleware.
• Safety stack: redundancy, fault detection, fail-operational behaviors.
• Cybersecurity: ISO/SAE 21434 compliant, secure boot, encrypted communication.

Certifications and compliance

• ISO 26262 ASIL-D: highest automotive functional safety level.
• ISO 21448 SOTIF: safety of the intended functionality.
• ISO/SAE 21434: automotive cybersecurity.
• UN-R157: automated lane keeping systems.
• FMVSS, CMVSS, E-mark: vehicle safety standards.

Customer ecosystem

DRIVE Hyperion 9 customers include: (1) Robotaxi operators: Waymo, Cruise, Pony.ai, AutoX, WeRide. (2) Trucking: Aurora, TuSimple, Plus, Kodiak Robotics. (3) Automakers: Mercedes-Benz (Drive Pilot L3), BMW, Volvo, Polestar, Lucid, NIO, Xpeng, Li Auto. (4) Tier 1 suppliers: Bosch, Continental, ZF, Aptiv. (5) New entrants: dozens of robotaxi startups globally. Robotaxi commercial deployments: planned 2027-2028 (NVIDIA, 2026).

Skild AI single-video training

Skild AI is a robotics AI company building foundation models for robot control, founded in 2023 by former Carnegie Mellon researchers Deepak Pathak and Abhinav Gupta. Skild's approach: build a 'robot brain' foundation model that can be adapted to different robot embodiments and tasks.

Single-video training demo

The single-video training demo (announced September 10, 2026) shows Skild AI's foundation model learning new physical tasks from a single video. The model:

1. Watches a video of a task being performed (by a human or another robot).
2. Understands the task using vision-language model capabilities.
3. Plans execution by reasoning about object affordances, physics, and goal states.
4. Executes the task on a real robot, adapting to its specific embodiment.

Traditional robot training requires 1,000+ hours of robot teleoperation data per task. Skild's approach: 1 video, infinite robots. The implications are significant for:

• Industrial robots: factory robots learning new assembly tasks in minutes instead of weeks.
• Household robots: home robots learning new chores from YouTube videos.
• Surgical robots: surgical assistants learning new procedures from surgeon demonstrations.
• Agricultural robots: harvesting robots learning new crop varieties from farmer demonstrations.
• Last-mile delivery: delivery robots adapting to new environments from video.

Jetson Thor robotics computer

Jetson Thor is the next-generation robotics computer, announced in 2024 and shipping in volume in 2025-2026:

Source: NVIDIA Jetson product specifications (2026).

Jetson Thor target applications

• Humanoid robots: Figure 02, 1X Neo, Sanctuary Phoenix, Apptronik Apollo, Tesla Optimus, Agility Digit, Unitree H1.
• Autonomous Mobile Robots (AMRs): warehouse robots, hospital delivery, hotel service.
• Industrial automation: assembly, welding, painting, inspection.
• Surgical robots: Intuitive Surgical da Vinci, Medtronic Hugo, Johnson & Johnson Ottava.
• Agricultural robots: John Deere autonomous tractors, harvesters.
• Last-mile delivery: Nuro, Starship Technologies, Kiwibot.
• Defense and security: Boston Dynamics Spot, Ghost Robotics Vision 60.
• Service robots: restaurant, retail, hospitality robots.

Jetson Thor pricing: $3,000-$5,000 per module (vs $2,000-$4,000 for Jetson Orin). Volume discounts available for OEMs (NVIDIA, 2026).

Cosmos world foundation model

Cosmos is NVIDIA's world foundation model (WFM) for physical AI. WFMs generate physics-based video simulations of environments, enabling robot training in simulated worlds without the cost and risk of real-world training.

Cosmos key features

• Physics accuracy: models gravity, friction, collisions, deformable objects, fluid dynamics.
• Sensor simulation: generates RGB cameras, depth, lidar, radar outputs.
• Domain randomization: varies lighting, weather, object positions, materials for robust training.
• Camera control: precise control of camera trajectory, focal length, and aperture.
• Long-horizon generation: generates extended video sequences for training.
• Integration: integrates with Isaac Sim, Isaac Lab, and DRIVE Sim for full-stack simulation.

Cosmos applications

• Robotaxi simulation: rare event simulation (children running into street, emergency vehicles, unusual weather).
• Humanoid robot training: manipulation tasks, bipedal locomotion, human-robot interaction.
• Industrial automation: assembly line variations, fault recovery, quality inspection.
• Autonomous trucking: long-tail scenarios, weather variations, construction zones.
• Surgical simulation: rare complication simulation, instrument handling.

Isaac Sim and Isaac Lab updates

NVIDIA Isaac Sim (Omniverse-based robotics simulation) and Isaac Lab (robot learning framework) were updated September 10, 2026:

Isaac Sim updates

• New sensor models: more accurate camera, lidar, IMU, force/torque sensor simulation.
• Improved physics: better soft body, fluid, and granular media simulation.
• Reinforcement learning support: tighter integration with RL training workflows.
• Synthetic data generation: scalable data generation with domain randomization.

Isaac Lab updates

• New robot models: support for the latest humanoid robots, AMRs, and industrial arms.
• Sim-to-real transfer: improved techniques for transferring trained policies to real robots.
• Imitation learning: tighter integration with teleoperation data collection.
• Multi-robot learning: support for coordinating multiple robots.

Physical AI market context

The physical AI market is rapidly growing:

• Total market: $50B+ in 2026; projected $300B+ by 2030 (Goldman Sachs, McKinsey).
• Robotaxi market: $5B+ in 2026; projected $200B+ by 2030.
• Humanoid robot market: $2B+ in 2026 (mostly R&D); projected $30B+ by 2030.
• Industrial automation: $30B+ in 2026; projected $80B+ by 2030.
• AMR/warehouse robot market: $8B+ in 2026; projected $30B+ by 2030.

NVIDIA is positioned as the primary compute and platform provider, with potential to capture 30-50% of the physical AI compute market. NVIDIA's automotive and robotics revenue: $2B+ in FY2026, projected $5-10B+ by FY2028 (NVIDIA; Goldman Sachs, 2026).

FAQ

Is robotaxi commercially available in 2026?
Limited commercial robotaxi deployments exist in 2026: Waymo in Phoenix, San Francisco, Los Angeles, Austin; Cruise (limited) in San Francisco; Pony.ai in Beijing, Shanghai, Guangzhou, Shenzhen; AutoX in Shenzhen, Beijing; WeRide in Beijing, Guangzhou. Most operate within specific geofenced areas with safety drivers available. Mass-market L4 robotaxi (no safety driver, any location) is projected for 2028-2030. DRIVE Hyperion 9 targets this 2027-2028 commercial deployment window (NVIDIA, 2026).

How does Skild AI's single-video training compare to other robot learning approaches?
Robot learning approaches comparison: (1) Skild AI single-video - 1 video, generalizes across tasks/robots. (2) Behavior cloning - thousands of teleoperation demonstrations per task. (3) Reinforcement learning - millions of simulation episodes per task. (4) Imitation learning from play - hours of human demonstration data. (5) Self-supervised learning - large amounts of unlabeled robot interaction data. Skild's approach is most efficient in terms of data requirements but requires powerful foundation models and may not generalize to all physical tasks. The single-video demo is a research milestone; production deployment is still 1-2 years away (Skild AI; NVIDIA, 2026).