发表机构
The University of Osaka; Institute of Science Tokyo（大阪大学; 东京科学大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出具身感知机框架，将躯体建模为感知机，通过协同优化肌肉骨骼机器人的控制策略与肌肉配置，实现具身智能，兼具稳定性、高学习效率与小模型规模，为具身AI系统设计提供新路径。
AI 中文摘要
人工智能技术的最新进展已实现复杂控制策略的先进设计。相比之下，许多机器人仍采用简单的躯体设计，这会限制其对环境的适应能力。具身机器人学研究表明，设计良好的躯体可通过躯体与环境的物理交互部分替代控制与计算的作用，但此类设计仍高度依赖专家直觉。因此，亟需一套用于躯体设计的系统理论框架，以及躯体与控制器协同优化的方法。为解决这一问题，本文提出具身感知机（Embodied Perceptron）这一理论框架，该框架将神经网络与物理躯体系统统一起来。在该视角下，躯体本身可作为感知机：机械参数对应权重，物理非线性特性则充当激活函数。通过将物理约束表示为权重、非线性特性表示为激活函数，可将物理躯体建模为神经网络形式。该系统表示使我们能从理论上明确解释，躯体可替代部分神经控制功能。作为应用，本文对肌肉骨骼机器人的控制策略与肌肉配置进行协同优化，结果显示，由此产生的具身智能可提供固有稳定性、提升学习效率，且能大幅减小模型规模——即便采用单神经元控制器亦是如此。这些结果搭建起信息世界与物理世界的桥梁，为理解和系统设计具身人工智能系统提供了途径。
英文摘要
Recent advances in AI technologies have enabled the advanced design of complex control policies. In contrast, focusing on the body, many robots still employ simple bodies that can limit adaptability to environments. Studies in embodied robotics have shown that well-designed bodies can partially replace the role of control and computation with physical body-environment interactions, yet such designs still depend heavily on expert intuition. There is a need for a systematic theoretical framework for body design, as well as a method for joint optimization of the body and controller. To address this, we introduce the Embodied Perceptron, a theoretical framework that unifies neural networks and physical body systems. In this view, the body itself acts as a perceptron: mechanical parameters correspond to weights, and physical nonlinearities play the role of activation functions. By representing physical constraints as weights and nonlinear properties as activation functions, a physical body can be modeled in neural-network form. The system representation enables us to explicitly and theoretically explain that the body can substitute for part of the neural control. As an application, we co-optimize control policy and muscle configuration in a musculoskeletal robot and show that the resulting embodied intelligence can provide inherent stability, improve learning efficiency, and drastically reduce model size-even with a single-neuron controller. The results bridge the informational and physical worlds and provide a pathway toward understanding and systematic design of embodied AI systems.
Comments10 pages, 7 figures, 2026 IEEE/SICE International Symposium on System Integration (SII)
Journal refProc. 2026 IEEE/SICE International Symposium on System Integration (SII), pp. 167-172, 2026
DOI：10.1109/SII64115.2026.11404727
