Skip to main content
No image available
AI·The Robot Report·1 min read

Vision-Language-Action Models Are Replacing Modular Robotics Pipelines

A new class of AI models called vision-language-action (VLA) systems is changing how humanoid robots process instructions and interact with the world. Instead of separate modules for seeing, planning, and moving, VLAs like Figure AI's Helix, NVIDIA's GR00T N1, and Google DeepMind's RT-1 combine vision, language understanding, and motor control into a single end-to-end model. Helix uses a dual-system design — a large vision-language backbone handles high-level reasoning while a smaller action model runs at high frequency for precise manipulation. GR00T N1 takes a generalist approach, training across multiple robot types and tasks. The practical result: robots that can follow natural language instructions, carry out multi-step tasks, and adapt to new environments without hand-tuned pipelines. Several teams have demonstrated on-device deployment with reduced latency. The shift matters because it moves humanoid robots closer to general-purpose assistants that understand what you ask and can actually do it.

VLAFigure AINVIDIAGoogle DeepMindHelixGR00T N1AIHumanoid
Read original source

Related News

View All News →
NVIDIA Introduces Cosmos Policy: World Foundation Models That Teach Robots to ActAI

NVIDIA Introduces Cosmos Policy: World Foundation Models That Teach Robots to Act

NVIDIA unveiled Cosmos Policy, a new approach to robot control that fine-tunes its Cosmos Predict world foundation model to directly generate robot actions. Instead of bolting separate perception and control modules together, Cosmos Policy encodes robot actions, physical states, and success scores as latent video frames — allowing a single model to handle visuomotor control, future-state prediction, and action planning simultaneously. The system achieved state-of-the-art results on LIBERO and RoboCasa manipulation benchmarks, outperforming both diffusion policies trained from scratch and vision-language-action models. By inheriting the pretrained model's understanding of physics and temporal dynamics, Cosmos Policy represents a significant step toward general-purpose robot intelligence built on video foundation models.

·The Robot Report / NVIDIA
Figure AI's Fleet of Figure 03 Robots Now Operates 24/7 Without Human SupervisionHumanoid

Figure AI's Fleet of Figure 03 Robots Now Operates 24/7 Without Human Supervision

Figure AI CEO Brett Adcock revealed that a fleet of seven Figure 03 humanoid robots at the company's Sunnyvale headquarters is now operating autonomously around the clock — nights, weekends, and holidays — without human babysitters. When a robot's battery runs low, it navigates itself to a wireless inductive charging dock (2 kW, full charge in about one hour), while a fully charged replacement robot vacates the dock and takes over the active task. If a unit hits a hardware or software fault, it removes itself to a triage area and a backup swaps in automatically. The system, powered by Figure's Helix AI architecture, eliminates the hand-coded C++ stack the company previously relied on. Figure now occupies five buildings in Sunnyvale and is building its 'BotQ' factory targeting 12,000 units per year initially, scaling to 100,000. The milestone moves Figure beyond staged demos toward the kind of continuous, unsupervised fleet operation needed to make humanoid robots commercially viable — starting with manufacturing partners like BMW.

·Figure AI / Brett Adcock
No image available
Humanoid

Humanoid Launches KinetIQ: An AI Framework for Orchestrating Fleets of Humanoid Robots

UK-based Humanoid unveiled KinetIQ, an AI framework for end-to-end orchestration of humanoid robot fleets across both wheeled and bipedal platforms. The system coordinates fleet-level operations and individual robot behavior through four cognitive layers — from high-level task allocation and workflow optimization down to task execution using Vision-Language-Action models and whole-body control trained via reinforcement learning. The announcement comes after Humanoid completed a live logistics trial at Siemens processing 60 totes per hour, and secured a deal with Schaeffler to deploy hundreds of its robots across factories. Founded in 2024, Humanoid has quickly positioned itself as a leading European contender in the commercial humanoid race.

·IEEE Spectrum / Humanoid