用数据自动学习可解释的跳跃四足机器人简化模型。
Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots
- 用线性自编码器+符号回归从数据中提取任务特异性动力学。
- 在多机器人、多跳跃模式下，性能超越经典aSLIP模型。
- 模型可解释性强，适合需要物理一致性的控制场景。
简化模型在四足机器人运动规划与控制中至关重要，但现有模板通常针对特定运动模式手工设计。这促使我们开发一种直接从数据中自动提取任务特异性、可解释的低维动力学的方法。本文提出将线性自编码器与符号回归结合，线性自编码器为配置、速度、加速度和输入提供一致的隐空间嵌入，使稀疏非线性动力学识别（SINDy）能在紧凑且符合物理规律的空间中运行。通过多阶段、混合感知训练策略，确保接触切换时隐坐标的一致性。验证聚焦于四足跳跃这一典型、复杂但可控的场景，此时结构化模型尤为关键。结果表明，所获符号动力学在仿真与实机测试中均优于当前最优的手工设计的受驱动弹簧倒立摆（aSLIP）基准模型，适用于多种机器人及跳跃模式。
原文摘要 · Abstract (English)
Reduced-order models are central to motion planning and control of quadruped robots, yet existing templates are often hand-crafted for a specific locomotion modality. This motivates the need for automatic methods that extract task-specific, interpretable low-dimensional dynamics directly from data. We propose a methodology that combines a linear autoencoder with symbolic regression to derive such models. The linear autoencoder provides a consistent latent embedding for configurations, velocities, accelerations, and inputs, enabling the sparse identification of nonlinear dynamics (SINDy) to operate in a compact, physics-aligned space. A multi-phase, hybrid-aware training scheme ensures coherent latent coordinates across contact transitions. We focus our validation on quadruped jumping-a representative, challenging, yet contained scenario in which a principled template model is especially valuable. The resulting symbolic dynamics outperform the state-of-the-art handcrafted actuated spring-loaded inverted pendulum (aSLIP) baseline in simulation and hardware across multiple robots and jumping modalities.
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。