Alfred E. Mann Department of Biomedical Engineering, University of Southern California, Los Angeles, CA 90089, United States of America.
Division of Biokinesiology and Physical Therapy, University of Southern California, Los Angeles, CA 90089, United States of America.
Bioinspir Biomim. 2024 Oct 24;19(6):066008. doi: 10.1088/1748-3190/ad8419.
Inspired by animals that co-adapt their brain and body to interact with the environment, we present a tendon-driven and over-actuated (i.e.joint,+1 actuators) bipedal robot that (i) exploits its backdrivable mechanical properties to manage body-environment interactions without explicit control,(ii) uses a simple 3-layer neural network to learn to walk after only 2 min of 'natural' motor babbling (i.e. an exploration strategy that is compatible with leg and task dynamics; akin to childsplay). This brain-body collaboration first learns to produce feet cyclical movements 'in air' and, without further tuning, can produce locomotion when the biped is lowered to be in slight contact with the ground. In contrast, training with 2 min of 'naïve' motor babbling (i.e. an exploration strategy that ignores leg task dynamics), does not produce consistent cyclical movements 'in air', and produces erratic movements and no locomotion when in slight contact with the ground. When further lowering the biped and making the desired leg trajectories reach 1 cm below ground (causing the desired-vs-obtained trajectories error to be unavoidable), cyclical movements based on either natural or naïve babbling presented almost equally persistent trends, and locomotion emerged with naïve babbling. Therefore, we show how continual learning of walking in unforeseen circumstances can be driven by continual physical adaptation rooted in the backdrivable properties of the plant and enhanced by exploration strategies that exploit plant dynamics. Our studies also demonstrate that the bio-inspired co-design and co-adaptations of limbs and control strategies can produce locomotion without explicit control of trajectory errors.
受动物大脑和身体协同适应环境的启发，我们提出了一种肌腱驱动和过驱动（即关节，+1 个执行器）的双足机器人，它 (i) 利用其可反向驱动的机械特性来管理身体与环境的相互作用，而无需显式控制，(ii) 使用简单的 3 层神经网络，在仅 2 分钟的“自然”电机喋喋不休（即与腿部和任务动态兼容的探索策略；类似于儿戏）后学习行走。这种脑体协作首先学会在空气中产生周期性的脚部运动，并且在双足机器人降低到与地面轻微接触时，无需进一步调整即可产生运动。相比之下，用 2 分钟的“天真”电机喋喋不休（即忽略腿部任务动态的探索策略）进行训练，不会在空中产生一致的周期性运动，并且在与地面轻微接触时会产生不稳定的运动，无法运动。当进一步降低双足机器人并使期望的腿部轨迹达到离地面 1 厘米（导致期望轨迹与实际轨迹之间的误差不可避免）时，基于自然或天真喋喋不休的周期性运动呈现出几乎相等的持续趋势，并且在天真喋喋不休的情况下出现了运动。因此，我们展示了如何通过根植于植物可反向驱动特性的持续物理适应以及利用植物动力学的探索策略，驱动在不可预见的情况下持续学习行走。我们的研究还表明，四肢和控制策略的仿生共同设计和协同适应可以在没有轨迹误差显式控制的情况下产生运动。
