PGTT：用于感知式有腿运动的相位引导地形遍历
PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion
AI总结：
研究针对有腿机器人感知强化学习控制器的不足，提出相位引导地形遍历（PGTT）方法，通过奖励塑造强化步态结构，编码腿相位等，在特定训练下，该方法在多种场景成功率高且速度跟踪可比，还能跨平台转移。
摘要：
最先进的有腿机器人感知强化学习控制器通常要么（i）施加基于振荡器或 IK 的步态先验，这会限制动作空间、使策略优化有偏差并限制跨机器人形态的适应性，要么（ii）盲目运行，无法预测后腿地形且对观测噪声敏感。我们提出相位引导地形遍历（PGTT），一种通过奖励塑造来强化步态结构的感知感知深度强化学习方法，与基于振荡器或 IK 的动作先验相比减少了归纳偏差。PGTT 将每腿相位编码为三次 Hermite 样条，根据局部高度图统计调整摆动高度并添加摆动相位接触惩罚，策略直接在关节空间中运行以实现与形态无关的部署。在 MuJoCo 中使用课程学习和域随机化在程序生成的楼梯状地形上训练，PGTT 在推扰（比次优基线中位数高 7.5%）和离散障碍物（高 9%）情况下在评估的基线中取得最高成功率，同时保持可比的速度跟踪。我们在 Unitree Go2 上使用实时 LiDAR 高程到高度图管道验证了 PGTT，并使用相同超参数在 ANYmal-C 上报告了初步结果。这些结果提供了早期证据，表明地形自适应、相位引导的奖励塑造可以在没有特定平台策略先验或广泛重新调整的情况下跨平台转移。
英文摘要：
State-of-the-art perceptive Reinforcement Learning controllers for legged robots typically either (i) impose oscillator-or IK-based gait priors that constrain the action space, bias policy optimization, and limit adaptability across robot morphologies, or (ii) operate "blind," making them unable to anticipate hind-leg terrain and brittle to observation noise. We propose Phase-Guided Terrain Traversal (PGTT), a perception-aware deep-RL approach that enforces gait structure through reward shaping, thereby reducing inductive bias compared to oscillator- or IK-conditioned action priors. PGTT encodes per-leg phase as a cubic Hermite spline, adapts swing height to local heightmap statistics, and adds a swing-phase contact penalty, while the policy acts directly in joint space for morphology-agnostic deployment. Trained in MuJoCo (MJX) on procedurally generated stair-like terrains with curriculum learning and domain randomization, PGTT achieves the highest success rate among the evaluated baselines under push disturbances (median +7.5% over the next-best baseline) and on discrete obstacles (+9%), while maintaining comparable velocity tracking. We validate PGTT on a Unitree Go2 using a real-time LiDAR elevation-to-heightmap pipeline and report preliminary results on ANYmal-C using the same hyperparameters. These results provide early evidence that terrain-adaptive, phase-guided reward shaping can transfer across platforms without platform-specific policy priors or extensive re-tuning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
