面向四足运动的神经回路架构先验
Neural Circuit Architectural Priors for Quadruped Locomotion
AI总结：
本研究提出一种受哺乳动物四肢和脊髓神经回路启发的四足运动ANN架构，相比MLP用更少数据和参数量实现相当性能，泛化性更优，为运动控制提供了有价值的架构先验。
摘要：
基于学习的四足运动方法通常采用全连接MLP这类通用策略架构。由于此类架构包含的归纳偏置极少，实践中通常会以奖励、训练课程、模仿数据或轨迹生成器的形式引入先验知识。在自然界中，动物与生俱来的先验以其神经系统架构的形式存在，这种架构经进化塑造，赋予了动物先天能力与高效学习能力。例如，马出生后数小时内就能行走，且能通过练习快速提升。这类架构先验在用于AI的人工神经网络（ANN）架构中同样有用。本研究中，我们探究了一种受生物启发的四足运动ANN架构的优势，该架构基于哺乳动物四肢与脊髓中的神经回路构建。我们的架构取得了良好的初始性能，最终性能与MLP相当，同时使用的数据更少，参数量少几个数量级。我们的架构还展现出对任务变化的更好泛化能力，甚至无需标准的sim-to-real（仿真到现实）方法就能部署在实体机器人上。这项研究表明，神经回路能为运动控制提供有价值的架构先验，并推动未来在其他感知运动技能领域的研究。
英文摘要：
Learning-based approaches to quadruped locomotion commonly adopt generic policy architectures like fully connected MLPs. As such architectures contain few inductive biases, it is common in practice to incorporate priors in the form of rewards, training curricula, imitation data, or trajectory generators. In nature, animals are born with priors in the form of their nervous system's architecture, which has been shaped by evolution to confer innate ability and efficient learning. For instance, a horse can walk within hours of birth and can quickly improve with practice. Such architectural priors can also be useful in ANN architectures for AI. In this work, we explore the advantages of a biologically inspired ANN architecture for quadruped locomotion based on neural circuits in the limbs and spinal cord of mammals. Our architecture achieves good initial performance and comparable final performance to MLPs, while using less data and orders of magnitude fewer parameters. Our architecture also exhibits better generalization to task variations, even admitting deployment on a physical robot without standard sim-to-real methods. This work shows that neural circuits can provide valuable architectural priors for locomotion and encourages future work in other sensorimotor skills.
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。
