发表机构
Shanghai Jiao Tong University; Intelligent Game and Decision Laboratory; Renmin University of China; Shanghai Innovation Institute（上海交通大学; 智能游戏与决策实验室; 中国人民大学; 上海创新研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对机器人协同设计中控制学习反向塑造形态进化的未解决问题，提出AdaControl方法，通过监测无偏适应度评估减少计算量，使简单遗传算法性能媲美先进方法且计算量降80%
AI 中文摘要
机器人协同设计通过双层优化，将生命周期内用于适应度评估的控制器学习与跨代形态进化相结合。已有研究证实，适配良好的形态可加快控制学习速度，这一特性被称为形态智能。然而，控制学习如何反向塑造形态进化仍未被探究。本文从双向视角对脑-体交互进行整体阐释：首先证明形态对控制学习的贡献可解耦为两个正交维度，将收敛速度形式化为形态智能，将性能上限定义为互补量“真实潜能”；随后建立简洁函数关系，从个体学习曲线联合刻画这两个量，在种群层面聚合后可捕捉进化轮廓。通过对基于体素的仿真软体机器人的大量实验，我们发现过早的适应度评估会系统性低估真实潜能，并使选择偏向快速学习者，这会限制设计空间探索，损害优化效率与形态多样性；值得注意的是，广泛认可的形态鲍德温效应是该偏差的产物，而非普遍的进化趋势。因此，我们提出AdaControl，该方法在进化过程中监测对形态智能的不成比例选择，并分配最少足够的控制学习以实现无偏的适应度评估。采用AdaControl后，简单遗传算法在发现多样高性能设计方面可媲美最先进的基于生成模型的协同设计方法，且与详尽控制相比计算量最多减少80%
英文摘要
Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation with cross-generational morphological evolution. Prior work has established that well-adapted morphology facilitates faster control learning, a property termed morphological intelligence. Yet how control learning reciprocally shapes morphological evolution remains unexplored. This paper examines both directions for a holistic account of brain-body interplay. We first show that morphological contributions to control learning decouple into two orthogonal dimensions. We formalize the convergence speed as morphological intelligence and identify the performance ceiling as a complementary quantity termed true potential. A concise functional relation is then established to jointly characterize both quantities from individual learning curves, which, when aggregated at the population level, capture evolutionary profiles. Through extensive experiments on simulated voxel-based soft robots, we reveal that premature fitness evaluation systematically underestimates true potential and biases selection towards fast learners. This restricts design space exploration, compromising both optimization efficiency and morphological diversity. Notably, the widely recognized morphological Baldwin effect emerges as an artifact of this bias rather than a general evolutionary tendency. We therefore propose AdaControl, which monitors disproportionate selection for morphological intelligence during evolution and allocates minimally sufficient control learning for unbiased fitness evaluation. With AdaControl, a simple genetic algorithm rivals state-of-the-art generative-model-based co-design methods in discovering diverse high-performing designs while cutting computation by up to 80% versus exhaustive control.
