用物理约束神经网络实时自适应调整四足机器人负载，提升运动精度
Physics-informed Neural Network Predictive Control for Quadruped Locomotion
- 结合在线负载识别与物理约束神经网络，将质量参数嵌入损失函数
- 在25-100公斤负载下，定位与姿态追踪准确率提升35%，收敛更快
- 适合需要动态负载适应的四足机器人控制，兼顾精度与实时性
本研究提出一种统一控制框架——基于在线负载识别的物理信息神经网络预测控制（OPI-PINNPC），用于解决未知负载下的精确四足运动问题。通过将在线负载识别与物理信息神经网络（PINNs）结合，将识别出的质量参数直接嵌入神经网络损失函数，确保物理一致性的同时适应负载变化。物理约束的神经表示作为非线性模型预测控制器中的高效代理模型，即使在复杂腿部动力学条件下也能实现实时优化。在四足机器人平台上的实验验证表明，在25-100公斤不同负载条件下，位置与姿态追踪精度提升35%，且收敛速度显著优于以往自适应控制方法。该框架为变负载条件下维持运动性能提供了高效自适应方案。
原文摘要 · Abstract (English)
This study introduces a unified control framework that addresses the challenge of precise quadruped locomotion with unknown payloads, named as online payload identification-based physics-informed neural network predictive control (OPI-PINNPC). By integrating online payload identification with physics-informed neural networks (PINNs), our approach embeds identified mass parameters directly into the neural network's loss function, ensuring physical consistency while adapting to changing load conditions. The physics-constrained neural representation serves as an efficient surrogate model within our nonlinear model predictive controller, enabling real-time optimization despite the complex dynamics of legged locomotion. Experimental validation on our quadruped robot platform demonstrates 35% improvement in position and orientation tracking accuracy across diverse payload conditions (25-100 kg), with substantially faster convergence compared to previous adaptive control methods. Our framework provides a adaptive solution for maintaining locomotion performance under variable payload conditions without sacrificing computational efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。