Loco-Loco-RL：基于强化学习的人形机器人低成本地形测绘
Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning
- University of Louisville（路易斯维尔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出Loco-Loco-RL，利用低成本飞行时间传感器获取紧凑3D地形表示，结合令牌压缩的时间变换器策略，实现人形机器人鲁棒的地形行走，并通过仿真到现实迁移验证。
AI中文摘要：
信息丰富的地形感知对于人形机器人运动中鲁棒的强化学习策略至关重要。然而，深度相机和激光雷达等常见传感器会带来高昂的成本、功耗和处理开销，且常常产生冗余的高分辨率数据。本工作采用低成本飞行时间传感器，为人形机器人运动提供紧凑的3D局部地形表示。为高效利用这种稀疏的外部感知输入，我们引入了一种令牌压缩的时间变换器策略。本体感觉和地形观测被令牌化，并由多头自注意力变换器处理，以捕捉观测项在时间步内的关系。处理后的令牌通过基于MLP的潜在空间令牌压缩模块进行压缩，然后存储到滚动15时间步的历史中。第二个多头交叉注意力变换器从该紧凑历史中提取时间运动特征，用于策略学习。通过在时间聚合前压缩令牌，该架构保留了重要的地形观测结构，同时限制了注意力在观测历史上的维度增长。我们通过基于地形运动基准的物理硬件上的仿真到现实迁移验证了我们的方法，展示了在低成本局部地形感知下鲁棒的人形机器人地形行走。
英文摘要：
Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth cameras and LiDARs incur high cost, power, and processing overhead while often producing redundant, high-resolution data. This work uses a low-cost time-of-flight sensor to provide a compact 3D local terrain representation for humanoid locomotion. To efficiently use this sparse exteroceptive input, we introduce a token-compressed temporal transformer policy. Proprioceptive and terrain observations are tokenized and processed by a self-attention multi-head transformer to capture within-timestep relationships between observation terms. The attended tokens are then compressed through an MLP-based latent-space token compression module before being stored in a rolling 15-timestep history. A second cross-attention multi-head transformer extracts temporal locomotion features from this compact history for policy learning. By compressing tokens before temporal aggregation, the architecture preserves important terrain-observation structure while limiting the dimensional growth of attention over observation histories. We validate our method through sim-to-real transfer on physical hardware using a terrain-based locomotion benchmark, demonstrating robust humanoid terrain walking with low-cost local terrain sensing.
