High-performance autonomous mobile robots endure significant mechanical stress during in-the-wild operations, e.g., driving at high speeds or over rugged terrain. Although these platforms are engineered to withstand such conditions, mechanical degradation is inevitable. Structural damage manifests as consistent and notable changes in kinodynamic behavior compared to a healthy vehicle. Given the heterogeneous nature of structural failures, quantifying various damages to inform kinodynamics is challenging. We posit that natural language can describe and thus capture this variety of damages. Therefore, we propose Zero-shot Language Informed Kinodynamics (ZLIK), which employs self-supervised learning to ground semantic information of damage descriptions in kinodynamic behaviors to learn a forward kinodynamics model in a data-driven manner. Using the high-fidelity soft-body physics simulator BeamNG.tech, we collect data from a variety of structurally compromised vehicles. Our learned model achieves zero-shot adaptation to different damages with up to 81% reduction in kinodynamics error and generalizes across the sim-to-real and full-to-1/10$^{\text{th}}$ scale gaps.

翻译：高性能自主移动机器人在野外作业（如高速行驶或崎岖地形行驶）过程中承受显著的机械应力。尽管这些平台在设计上能够承受此类工况，机械性能退化仍不可避免。结构损伤表现为与健康车辆相比持续且显著的运动学行为变化。鉴于结构失效的异质性，量化各类损伤以指导运动学建模具有挑战性。我们认为自然语言能够描述并捕捉这种损伤多样性。为此，我们提出零样本语言信息运动学模型，该方法通过自监督学习将损伤描述的语义信息映射到运动学行为中，以数据驱动的方式学习前向运动学模型。利用高保真软体物理模拟器BeamNG.tech，我们收集了多种结构受损车辆的数据。所学习的模型实现了对不同损伤的零样本自适应，运动学误差降低最高达81%，并在仿真到现实及全尺寸到1/10$^{\text{th}}$缩比尺度的迁移中展现出良好的泛化能力。