用两阶段采样法高效发现机器人部署失败边界，解决工业场景验证难题。
ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling
- 先用拉丁超立方采样覆盖8维参数空间，再聚焦成功率30%-70%的临界区
- 5万次实验中，模型成功识别出可解析的失败边界方程，AUC达0.780
- 揭示大模型在仿真与真实工业环境间存在97.65%成功率断崖差距
在工业场景中部署学习到的机器人操作策略需要严格的预部署验证，但高维参数空间的全量测试不可行。本文提出ROBOGATE，一个结合物理仿真与两阶段自适应采样的部署风险管理体系，用于高效发现操作参数空间中的失败边界。第一阶段在8维参数空间中采用拉丁超立方采样（LHS）；第二阶段集中于成功率30%-70%的过渡区域进行边界聚焦采样。基于NVIDIA Isaac Sim（Newton物理引擎），我们评估了四种机器人形态（Franka Panda 7-DOF、UR3e 6-DOF、UR5e 6-DOF、UR10e 6-DOF）上的脚本化抓取放置控制器，共完成超过5万次实验。我们的逻辑回归风险模型获得AUC 0.780，识别出闭式失败边界方程。进一步对比了八种视觉-语言-动作（VLA）策略，包括在LIBERO-Spatial上训练20,000步的微调版NVIDIA GR00T N1.6（3B）。同一检查点在LIBERO（MuJoCo）上达到97.65%成功率，但在ROBOGATE的68个工业场景中为0%，呈现97.65个百分点的跨仿真器差距，凸显部署验证挑战。受量子计算中NVIDIA提出的验证层范式启发，ROBOGATE为物理人工智能提供此类验证层。代码开源。
原文摘要 · Abstract (English)
Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We present ROBOGATE, a deployment risk management framework that combines physics-based simulation with a two-stage adaptive sampling strategy to efficiently discover failure boundaries in the operational parameter space. Stage 1 employs Latin Hypercube Sampling (LHS) across an 8-dimensional parameter space; Stage 2 applies boundary-focused sampling concentrated in the 30-70% success rate transition zone. Using NVIDIA Isaac Sim with Newton physics, we evaluate a scripted pick-and-place controller across four robot embodiments -- Franka Panda (7-DOF), UR3e (6-DOF), UR5e (6-DOF), and UR10e (6-DOF) -- totaling over 50,000 experiments. Our logistic regression risk model achieves AUC 0.780 and identifies a closed-form failure boundary equation. We further benchmark eight VLA (Vision-Language-Action) policies, including a fine-tuned NVIDIA GR00T N1.6 (3B) trained on LIBERO-Spatial for 20K steps. The same checkpoint achieves 97.65% success rate on LIBERO (MuJoCo) but 0% on RoboGate's 68 industrial scenarios in NVIDIA Isaac Sim -- a 97.65 percentage point cross-simulator gap on a single model that underscores the deployment validation challenge. Inspired by the validation-layer paradigm NVIDIA codified for quantum computing with Ising, ROBOGATE provides this validation layer for Physical AI. Open-source.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。