不用预设步态，让四足机器人自适应地形省电奔跑
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
- 分模块设计：任务、限制、能耗、感知各司其职
- 能耗降低56%，越界违规减少96%，性能接近传统方法
- 无需步态先验，直接在真实机器人上零样本部署
基于学习的四足机器人行走通常依赖复杂的奖励函数，将任务定义、运行限制、步态偏好和地形适应耦合在一个优化目标中。我们改用分离机制：任务通过奖励实现，运行限制通过约束处理，步态偏好通过能量最小化驱动，地形适应则依赖外部感知调节能耗。实验证明这些模块协同可实现高效、自适应的行走，移除任一模块都会导致特定故障。本方法摒弃显式的步态先验（如腾空时间、接触次数、抬脚高度目标），转而依靠涌现行为。相比传统复杂奖励基线，本方法在相似地形穿越能力下，成本运输降低56%，运行限制违规减少96%。所生成策略在真实机器人Unitree Go2上实现零样本迁移，仅使用激光雷达进行高程建图。
原文摘要 · Abstract (English)
Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation within a single optimization objective. We instead treat these functions through distinct mechanisms: rewards for task specification, constraints for operational limits, energy minimization for gait preference, and exteroceptive perception for adapting energy use to terrain difficulty. We show that these components jointly enable efficient, terrain-adaptive locomotion, and that removing each component exposes a distinct failure mode. Our formulation removes explicit gait priors (including air-time, contact-count, and foot-clearance targets) in favor of emergent behavior. Compared to a conventional complex-reward baseline, our formulation achieves comparable terrain traversal while reducing cost of transport by 56% and operational-limit violations by 96%. The resulting policies transfer zero-shot to a physical Unitree Go2 using LiDAR-based elevation mapping. Project website with videos: https://tinyurl.com/locomposition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。