From 3a90112e9921a1fa937c23f1d7b71070759457a6 Mon Sep 17 00:00:00 2001 From: Runyu Lu Date: Wed, 19 Aug 2026 11:52:20 -0700 Subject: [PATCH] Add ASPIRE code link --- source/_data/SymbioticLab.bib | 1 + 1 file changed, 1 insertion(+) diff --git a/source/_data/SymbioticLab.bib b/source/_data/SymbioticLab.bib index ec236bcb..f92f1063 100644 --- a/source/_data/SymbioticLab.bib +++ b/source/_data/SymbioticLab.bib @@ -2572,6 +2572,7 @@ @Article{aspire:arxiv26 publist_confkey = {arXiv:2607.00272}, publist_link = {paper || https://arxiv.org/abs/2607.00272}, publist_link = {website || https://research.nvidia.com/labs/gear/aspire/}, + publist_link = {code || https://github.com/NVlabs/ASPIRE}, publist_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. }