ASPIRE: Agentic /Skills Discovery for Robotics
2026-06-30 • Robotics
RoboticsArtificial IntelligenceMultiagent Systems
AI summaryⓘ
The authors present ASPIRE, a system that helps robots teach themselves how to do tasks by writing and improving their own control programs over time. It learns from trying tasks, fixing mistakes, and saving those lessons as reusable skills for new jobs. ASPIRE is better than previous methods at handling complex tasks in both simulations and real robots, and it can even use what it learned to tackle new challenges without extra training. Their work shows how robots can get smarter and more flexible by building libraries of useful behaviors.
robot programmingcontinual learningrobot control programsskill libraryclosed-loop executionautonomous failure diagnosisevolutionary searchsim-to-real transfermultimodal perceptionlong-horizon tasks
Authors
Runyu Lu, Yubo Wu, Ethan Kou, Letian Fu, Wenli Xiao, Ajay Mandlekar, Yinzhen Xu, Guanya Shi, Ken Goldberg, Ang Chen, Mosharaf Chowdhury, Yuke Zhu, Linxi "Jim" Fan, Guanzhi Wang
Abstract
Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm while compounding experience into a reusable skill library. ASPIRE discovers skills that persist across tasks, simulation and real-world settings, and embodiments. It operates in an open-ended loop with three components: (1) a closed-loop robot execution engine that exposes fine-grained multimodal traces, enabling autonomous failure diagnosis, repair synthesis, and validation; (2) a continually expanding skill library that distills validated fixes into reusable, transferable knowledge; and (3) evolutionary search that generates diverse task sequences and control programs to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on LIBERO-Pro manipulation under perturbation, 72% on Robosuite bimanual handover, and 32% on BEHAVIOR-1K long-horizon household tasks. Its accumulated library also enables zero-shot generalization to unseen long-horizon tasks: on LIBERO-Pro Long, ASPIRE achieves 31% success versus 4% for prior methods despite their use of test-time reasoning and retries. Finally, simulation-discovered skills provide initial evidence of sim-to-real transfer, substantially reducing real-robot programming effort across different embodiments and robot APIs.