Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating base configuration makes them vulnerable to real-world uncertainties, yielding substantial challenges in their locomotion control. Deep reinforcement learning has become one of the plausible alternatives for realizing a robust locomotion controller. However, the approaches that rely solely on proprioception sacrifice collision-free locomotion because they require front-feet contact to detect the presence of stairs to adapt the locomotion gait. Meanwhile, incorporating exteroception necessitates a precisely modeled map observed by exteroceptive sensors over a period of time. Therefore, this work proposes a novel method to fuse proprioception and exteroception featuring a resilient multi-modal reinforcement learning. The proposed method yields a controller that showcases agile locomotion performance on a quadrupedal robot over a myriad of real-world courses, including rough terrains, steep slopes, and high-rise stairs, while retaining its robustness against out-of-distribution situations.

翻译：四足机器人展现出在复杂环境中导航的巨大应用潜力，其鲁棒性可与动物相媲美。然而，其浮动基座构型使其易受现实世界不确定性的影响，给运动控制带来重大挑战。深度强化学习已成为实现鲁棒运动控制器的可行方案之一。然而，仅依赖本体感知的方法需通过前足接触来探测台阶存在以调整步态，这导致其无法实现无碰撞运动。与此同时，引入外部感知则需基于外部传感器在特定时段内观测到的精确建模地图。为此，本研究提出一种融合本体感知与外部感知的创新方法，其核心在于鲁棒多模态强化学习。所提出的方法构建的控制器，在四足机器人上展现出应对多种现实场景的敏捷运动性能，包括崎岖地形、陡坡和高台阶，同时保持对分布外情境的鲁棒性。