留意你的脚步:人形机器人运动的预期感知
Watch Your Step: Anticipated Perception for Humanoid Locomotion
AI总结:
该研究针对人形机器人运动感知冗余问题,提出轻量级落脚点预测模型(FPM)预处理高程图,使训练迭代量减至约1/3,泛化性提升,可零样本迁移至Unitree G1人形机器人。
摘要:
感知型运动策略通常会观察以机器人为中心的密集高程图,然而,只有下一步脚下方及周围的地形会影响控制决策。学习到的编码器会压缩全部视觉输入,让策略在学习基础运动任务时自行判断哪些输入重要。同时学习这两项内容会减慢训练速度,且若不采用计算成本高昂的注意力机制,会更难泛化到新地形。我们在策略处理高程图之前,先移除其中的冗余输入。一个轻量级落脚点预测模型(FPM)仅通过本体感觉和速度指令预测未来落脚点,我们仅在这些预测落脚点周围的小区域内采样高程图。我们在训练运动策略的同时训练该预测模型,随着机器人步态成熟,会定期基于新的策略 rollout 对其进行重新训练。这使得感知能够预测策略将落脚的位置,而策略则学习利用这些落脚位置周围的地形信息。通过所提出的轻量级预处理,策略达到给定地形难度所需的训练迭代次数约为使用完整地图时的三分之一。在落脚点稀疏的场景中,包括狭窄的围墙走廊,以及未见过的地形上,它的表现优于观察完整地图的策略,并且与以数倍成本训练的基于注意力的编码器表现相当。该策略零样本迁移到 Unitree G1 人形机器人,可在室内和室外环境中穿越训练分布之外的各种障碍物、楼梯、间隙和下坡台阶。
英文摘要:
Perceptive locomotion policies typically observe a dense robot-centric elevation map, although only the terrain beneath and around the next footsteps informs the control decision. Learned encoders compress the whole visual input, leaving the policy to work out which inputs matter while learning the baseline locomotion task. Learning both at once slows training and, without computationally expensive attention mechanisms, makes generalization to new terrain harder. We instead remove redundant inputs from the elevation map before the policy sees it. A lightweight foothold prediction model (FPM) predicts future footholds from proprioception and the velocity command alone, and we sample the elevation map only in small patches around these predicted footholds. We train the prediction model alongside the locomotion policy, periodically retraining it on new policy rollouts as the robot's gait matures. This allows the perception to anticipate where the policy will step, while the policy learns to leverage terrain information around those steps. With the proposed lightweight preprocessing, the policy reaches a given terrain difficulty in roughly a third of the training iterations required with the complete map. It outperforms policies that observe the complete map where footholds are sparse, including in narrow walled corridors, and on unseen terrain, and it matches an attention-based encoder trained at several times the cost. The policy transfers zero-shot to a Unitree G1 humanoid traversing various obstacles, stairs, gaps, and step-downs beyond the training distribution in both indoor and outdoor environments.
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。