← Library · Frontier
NVIDIA AI Introduces ASPIRE, a Self-Improving Robotics Framework
NVIDIA, in collaboration with several universities, has launched ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system for robotics. ASPIRE writes and refines robot control programs and distills validated fixes into a reusable skill library. It achieved 31% zero-shot performance on LIBERO-Pro Long Tasks in simulation, using Claude Code for agentic programming.
Why it matters
ASPIRE advances autonomous robotics by enabling robots to iteratively improve their skills and build reusable knowledge. This framework can accelerate the development of more capable and adaptable robotic systems for complex real-world tasks.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free