Robot Learns Physical Tasks From Just 3–12 Seconds of a Demo

Robot learns physical tasks from just 3–12 seconds of a demo

A new robot foundation model can learn physical tasks from a single demonstration lasting just 3 to 12 seconds, then attempt the task without any gradient updates or fine-tuning. Developed by Generalist AI, GEN-1.5 is designed to learn directly from physical examples rather than requiring engineers to retrain the model for every new job. The company says the model can infer what it is supposed to do from a short sensorimotor demonstration and im…

The Future of AI: Robots That Learn and Improvise on Site

Deliberative Improvisation: Unlike competitors focusing on raw speed, the GEN-1.5 model utilizes a 0.8s inference-time “deliberation” window to navigate tool failures, achieving a 99% task success rate. Tactile Texture Mapping: The system demonstrates advanced Sim-to-Real transfer, distinguishing between organic textures (like fruit) and rigid industrial tools during high-dexterity maneuvers. Scaling Capacity: Backed by 500,000 training hours an…

I Saw the Future of AI in a Robot That Can Learn on the Spot

During a recent visit to Generalist AI, I watched a robotic arm improvise and use a banana as a tool.

😺 The ACTUAL ChatGPT 3 moment for robotics (one-shot learning)

Generalist’s GEN-1.5 robot learns tasks from seconds-long demonstrations, offering a glimpse at how AI systems could learn from the physical world.

GEN-1.5: Generalist AI teaches robots new tasks from a single demo

Robotics startup Generalist AI has unveiled GEN-1.5, an AI model that teaches robots new tasks from a single demonstration. The article GEN-1.5: Generalist AI teaches robots new tasks from a single demo appeared first on The Decoder.