DELTA：用于稀疏地形四足机器人运动的基于可变形高程的局部地形注意力编码器
DELTA: Deformable Elevation-Based Local Terrain Attention Encoder for Sparse-Terrain Quadrupedal Locomotion
浏览论文内容
中文总结 AI 辅助
该研究针对稀疏地形四足机器人运动的地形编码问题，提出DELTA编码器，通过固定成本的注意力机制提升学习效率与泛化性，实现仿真到现实的迁移。
中文摘要 AI 辅助
在稀疏地形上实现稳定的四足机器人运动，需要选择与状态相关的地形证据以实现精准的足部放置。基于模型的立足点规划器虽能提供精准的立足点选择，但严重依赖显式模型假设。近期基于注意力的地图编码（AME）研究表明，端到端强化学习（RL）可学习隐式的立足点引导。然而，密集AME编码的计算成本随地图分辨率升高而增加，限制了其在细粒度稀疏地形上的可扩展性。我们提出DELTA，一种基于可变形高程的局部地形注意力编码器。DELTA预测状态条件下的采样位置，从自适应局部高程块中形成地形证据令牌，且仅关注固定大小的令牌集。凭借固定的采样和块设置，DELTA编码器的成本与地图分辨率无关。实验显示，DELTA在标准分辨率下实现的最终 traversal 性能与AME相当，同时提升了学习效率。这种固定的编码器成本使其可使用更高分辨率的地形地图，改善细粒度稀疏地形上的 traversal 效果。DELTA还展现出对由连续和离散地形元素组成的未见混合评估赛道的强泛化能力。除仿真环境外，DELTA在RAIBO2上成功实现了仿真到现实的迁移。对学习到的采样偏移和注意力权重的分析表明，DELTA无需立足点标签或注意力监督，即可采样可踏区域并关注与未来触地相关的地形证据。
英文摘要
Stable quadrupedal locomotion on sparse terrain requires selecting state-relevant terrain evidence for precise foot placement. Model-based foothold planners provide precise foothold selection but rely heavily on explicit model assumptions. Recent attention-based map encoding (AME) studies show that end-to-end reinforcement learning (RL) can learn implicit foothold guidance. However, the computational cost of dense AME encoding grows with map resolution, limiting its scalability to fine-grained sparse terrain. We propose DELTA, a Deformable Elevation-Based Local Terrain Attention encoder. DELTA predicts state-conditioned sampling locations, forms terrain evidence tokens from adaptive local elevation patches, and attends only to a fixed-size token set. With fixed sampling and patch settings, DELTA's encoder cost is independent of map resolution. Experiments show that DELTA achieves final traversal performance comparable to AME at the standard resolution while improving learning efficiency. This fixed encoder cost enables the use of higher-resolution terrain maps, improving traversal on fine-grained sparse terrain. DELTA also demonstrates strong generalization to unseen mixed evaluation courses composed of continuous and discrete terrain elements. Beyond simulation, DELTA demonstrates successful sim-to-real transfer on RAIBO2. Analysis of the learned sampling offsets and attention weights shows that DELTA samples steppable regions and attends to terrain evidence relevant to future touchdowns without foothold labels or attention supervision.
发表机构
- Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
机构由 AI 辅助整理，请以论文原文为准。
