Learning a locomotion policy for quadruped robots has traditionally been constrained to a specific robot morphology, mass, and size. The learning process must usually be repeated for every new robot, where hyperparameters and reward function weights must be re-tuned to maximize performance for each new system. Alternatively, attempting to train a single policy to accommodate different robot sizes, while maintaining the same degrees of freedom (DoF) and morphology, requires either complex learning frameworks, or mass, inertia, and dimension randomization, which leads to prolonged training periods. In our study, we show that drawing inspiration from animal motor control allows us to effectively train a single locomotion policy capable of controlling a diverse range of quadruped robots. The robot differences encompass: a variable number of DoFs, (i.e. 12 or 16 joints), three distinct morphologies, a broad mass range spanning from 2 kg to 200 kg, and nominal standing heights ranging from 18 cm to 100 cm. Our policy modulates a representation of the Central Pattern Generator (CPG) in the spinal cord, effectively coordinating both frequencies and amplitudes of the CPG to produce rhythmic output (Rhythm Generation), which is then mapped to a Pattern Formation (PF) layer. Across different robots, the only varying component is the PF layer, which adjusts the scaling parameters for the stride height and length. Subsequently, we evaluate the sim-to-real transfer by testing the single policy on both the Unitree Go1 and A1 robots. Remarkably, we observe robust performance, even when adding a 15 kg load, equivalent to 125% of the A1 robot's nominal mass.

翻译：传统上，四足机器人的运动策略学习局限于特定的机器人形态、质量和尺寸。针对每台新机器人通常需重复学习过程，且必须重新调整超参数和奖励函数权重，以最大化新系统的性能表现。另一种方案是尝试训练单一策略以适应不同尺寸的机器人，同时保持相同的自由度（DoF）和形态，这要么需要复杂的学习框架，要么需要进行质量、惯量和尺寸的随机化处理，从而导致训练周期延长。本研究表明，借鉴动物运动控制机制使我们能够有效训练出可控制多种四足机器人的单一运动策略。机器人差异包括：可变自由度数量（即12或16个关节）、三种不同形态、2至200公斤的宽质量范围，以及18至100厘米的标称站立高度。我们的策略对脊髓中央模式发生器（CPG）的表征进行调制，有效协调CPG的频率和振幅以产生节律输出（节律生成），随后将其映射至模式形成（PF）层。在不同机器人间，唯一变化的组件是PF层，该层调整步幅高度和长度的缩放参数。最终，我们通过在Unitree Go1和A1机器人上测试单一策略来评估仿真到现实的迁移效果。值得注意的是，即使在增加15公斤负载（相当于A1机器人标称质量的125%）的情况下，该策略仍展现出稳健的性能表现。