发表机构
Agency for Defense Development; Korea Advanced Institute of Science and Technology; DIDEN Robotics; Korea University（国防发展局; 韩国科学技术院; 迪登机器人公司; 韩国大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究使四足机器人在复杂地形实现多技能运动的问题，提出 APT-RL 框架，利用机载感知和计算自主转换技能，通过轨迹优化生成数据集训练技能，经实验验证该框架能让机器人在复杂环境敏捷机动，稳健穿越多样障碍物。
AI 中文摘要
使四足机器人穿越复杂地形（从崎岖的户外环境到城市景观），需要多种运动技能的无缝集成、步态间的平滑过渡以及仅使用机载传感器的高速感知运动。我们提出了 APT-RL（基于动作预训练变压器的强化学习），这是一个统一框架，通过仅利用机载感知和计算的自主技能转换，实现多技能运动以在复杂环境中高速穿越。我们的方法通过简化动力学的轨迹优化生成大规模、特征丰富的 2D 运动数据集。这些数据集能训练多样、可复用的运动技能，有效转移到在复杂不平地形上运行的真实四足机器人。高质量技能为高效学习复杂下游任务提供强先验，并自然扩展到 3D 环境，实现部署策略中的平滑、高速多技能运动。实际实验证明了该框架的能力：机器人能通过复杂室内障碍物和户外野外环境进行敏捷机动，包括达到每秒 6 米瞬时峰值速度的动态下拉机动。单一机载策略能稳健穿越各种障碍物，展示了我们方法的通用性和有效性。
英文摘要
Enabling quadrupedal robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (Action Pretrained Transformer-based Reinforcement Learning), a unified framework that enables multi-skill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions utilizing only onboard perception and computation. Our approach generates large-scale, feature-rich 2D motion datasets through trajectory optimization with simplified dynamics. These datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multi-skill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: the robot performs agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reach instantaneous peak speeds of up to 6 meters per second. A single onboard policy enables robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
CommentsProject page: https://skillquadsr.github.io/ ,This is the author's version of the work. It is posted here by permission of the AAAS for personal use, not for redistribution. The definitive version was published in Science Robotics on 7.15.2026; doi: 10.1126/scirobotics.adz7397. Jun-Gill Kang and Jaehyun Park are co-first authors. Seungwoo Hong and Hae-Won Park are co-corresponding authors
DOI：10.1126/scirobotics.adz7397
