Quadruped robots are proliferating in industrial environments where they carry sensor suites and serve as autonomous inspection platforms. Despite the advantages of legged robots over their wheeled counterparts on rough and uneven terrain, they are still yet to be able to reliably negotiate ubiquitous features of industrial infrastructure: ladders. Inability to traverse ladders prevents quadrupeds from inspecting dangerous locations, puts humans in harm's way, and reduces industrial site productivity. In this paper, we learn quadrupedal ladder climbing via a reinforcement learning-based control policy and a complementary hooked end-effector. We evaluate the robustness in simulation across different ladder inclinations, rung geometries, and inter-rung spacings. On hardware, we demonstrate zero-shot transfer with an overall 90% success rate at ladder angles ranging from 70{\deg} to 90{\deg}, consistent climbing performance during unmodeled perturbations, and climbing speeds 232x faster than the state of the art. This work expands the scope of industrial quadruped robot applications beyond inspection on nominal terrains to challenging infrastructural features in the environment, highlighting synergies between robot morphology and control policy when performing complex skills. More information can be found at the project website: https://sites.google.com/leggedrobotics.com/climbingladders.

翻译：四足机器人正在工业环境中迅速普及，它们搭载传感器套件并作为自主检测平台使用。尽管腿式机器人在崎岖不平地形上相较于轮式机器人具有优势，但它们仍无法可靠地应对工业基础设施中普遍存在的特征：梯子。无法穿越梯子阻碍了四足机器人对危险区域的检测，将人类置于危险境地，并降低了工业现场的生产效率。本文通过基于强化学习的控制策略与配套钩状末端执行器，实现了四足机器人的梯攀爬能力。我们在仿真环境中评估了不同梯子倾角、横档几何形状和横档间距下的系统鲁棒性。在硬件实验中，我们展示了零样本迁移能力：在70°至90°的梯子角度范围内达到90%的整体成功率，在未建模扰动下保持稳定的攀爬性能，且攀爬速度比现有技术快232倍。这项工作将工业四足机器人的应用范围从常规地形检测扩展到环境中的挑战性基础设施特征，凸显了在执行复杂技能时机器人形态与控制策略之间的协同效应。更多信息请访问项目网站：https://sites.google.com/leggedrobotics.com/climbingladders。