让机器人自适应地结合飞行与轮动，大幅降低爬台阶能耗。
Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
- 用强化学习统一控制旋翼、轮子和舵机，无需预设模式切换。
- 仿真中能耗比纯飞行动作低约4倍，实机测试平均功耗降38%。
- 适合做节能型混合式机器人的研发与应用，尤其在复杂地形。
混合空地机器人兼具越障能力与续航优势，但台阶类障碍带来权衡：仅靠轮子常在边缘打滑，而小高度跃升的飞行则耗能巨大。本文提出一种能量感知的强化学习框架，训练单一连续策略协调旋翼、轮子与倾角舵机，无需预设空中或地面模式。在Isaac Lab中利用并行环境，基于本体感知与局部高度扫描进行训练，并采用硬件校准的推力/功耗模型，使奖励函数惩罚真实电能消耗。所学策略发现了融合空中推力与地面牵引的推进方式。仿真中能耗约为纯旋翼控制的1/4；将策略部署至DoubleBee原型机完成8cm高差攀爬任务，平均功耗较基于规则的解耦控制器降低38%。结果表明，高效混合驱动可通过学习自然涌现，并成功部署于真实硬件。
原文摘要 · Abstract (English)
Hybrid aerial--ground robots offer both traversability and endurance, but stair-like discontinuities create a trade-off: wheels alone often stall at edges, while flight is energy-hungry for small height gains. We propose an energy-aware reinforcement learning framework that trains a single continuous policy to coordinate propellers, wheels, and tilt servos without predefined aerial and ground modes. We train policies from proprioception and a local height scan in Isaac Lab with parallel environments, using hardware-calibrated thrust/power models so the reward penalizes true electrical energy. The learned policy discovers thrust-assisted driving that blends aerial thrust and ground traction. In simulation it achieves about 4 times lower energy than propeller-only control. We transfer the policy to a DoubleBee prototype on an 8cm gap-climbing task; it achieves 38% lower average power than a rule-based decoupled controller. These results show that efficient hybrid actuation can emerge from learning and deploy on hardware.
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。