AGILE：一种综合的人形机器人定位-操作学习工作流
AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning
AI总结：
AGILE提出了一种端到端的人形机器人强化学习工作流，通过标准化政策开发流程减少仿真到现实的失败模式，提升可靠性和可重复性。
摘要：
近期强化学习（RL）的进步使仿真中的人形行为令人印象深刻，但将这些结果转移到新机器人仍具有挑战性。在许多真实部署中，瓶颈不再是仿真吞吐量或算法设计，而是缺乏将环境验证、训练、评估和部署联系在一起的系统性基础设施。为此，我们提出了AGILE，一种端到端的人形RL工作流，标准化政策开发生命周期以缓解常见的仿真到现实失败模式。AGILE包含四个阶段：（1）交互式环境验证，（2）可重复训练，（3）统一评估，（4）通过机器人/任务配置描述符驱动的部署。对于评估阶段，AGILE支持基于场景的测试和随机滚出，通过共享的一套运动质量诊断，实现自动化回归测试和原理化的鲁棒性评估。AGILE还集成了训练稳定化和训练阶段的算法增强，以提高优化稳定性和仿真到现实的转移。有了这个流程，我们在两个硬件平台（Unitree G1和Booster T1）上验证了AGILE，涵盖行走、恢复、动作模仿和定位-操作五个代表性的人形技能，实现了稳定的仿真到现实转移。整体而言，AGILE表明，标准化的端到端工作流可以显著提高人形RL开发的可靠性和可重复性。
英文摘要：
Recent advances in reinforcement learning (RL) have enabled impressive humanoid behaviors in simulation, yet transferring these results to new robots remains challenging. In many real deployments, the primary bottleneck is no longer simulation throughput or algorithm design, but the absence of systematic infrastructure that links environment verification, training, evaluation, and deployment in a coherent loop. To address this gap, we present AGILE, an end-to-end workflow for humanoid RL that standardizes the policy-development lifecycle to mitigate common sim-to-real failure modes. AGILE comprises four stages: (1) interactive environment verification, (2) reproducible training, (3) unified evaluation, and (4) descriptor-driven deployment via robot/task configuration descriptors. For evaluation stage, AGILE supports both scenario-based tests and randomized rollouts under a shared suite of motion-quality diagnostics, enabling automated regression testing and principled robustness assessment. AGILE also incorporates a set of training stabilizations and algorithmic enhancements in training stage to improve optimization stability and sim-to-real transfer. With this pipeline in place, we validate AGILE across five representative humanoid skills spanning locomotion, recovery, motion imitation, and loco-manipulation on two hardware platforms (Unitree G1 and Booster T1), achieving consistent sim-to-real transfer. Overall, AGILE shows that a standardized, end-to-end workflow can substantially improve the reliability and reproducibility of humanoid RL development.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
