Quadrupedal robots resemble the physical ability of legged animals to walk through unstructured terrains. However, designing a controller for quadrupedal robots poses a significant challenge due to their functional complexity and requires adaptation to various terrains. Recently, deep reinforcement learning, inspired by how legged animals learn to walk from their experiences, has been utilized to synthesize natural quadrupedal locomotion. However, state-of-the-art methods strongly depend on a complex and reliable sensing framework. Furthermore, prior works that rely only on proprioception have shown a limited demonstration for overcoming challenging terrains, especially for a long distance. This work proposes a novel quadrupedal locomotion learning framework that allows quadrupedal robots to walk through challenging terrains, even with limited sensing modalities. The proposed framework was validated in real-world outdoor environments with varying conditions within a single run for a long distance.

翻译：四足机器人具备类似有腿动物在非结构化地形中行走的物理能力。然而，由于其功能复杂性及需适应多种地形，设计四足机器人控制器面临重大挑战。近年来，受有腿动物从经验中学习行走的启发，深度强化学习已被用于合成自然四足运动。然而，现有最先进方法高度依赖复杂且可靠的感知框架。此外，仅依赖本体感觉的先前研究在克服具有挑战性的地形（尤其是长距离行走）方面表现有限。本文提出一种新型四足运动学习框架，即使感知模态受限，也能使四足机器人在挑战性地形中行走。该框架在真实户外环境中进行了验证，涵盖单次运行中长距离内的多变条件。