Zero-Shot Adaptation to Robot Structural Damage via Natural Language-Informed Kinodynamics Modeling

2026-02-12 · Anuj Pokhrel, Aniket Datar, Mohammad Nazeri, Francesco Cancelliere, Xuesu Xiao arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.12385

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Zero-Shot Transfer Learning for Structural Health Monitoring using Generative Adversarial Networks and Spectral Mapping

2022-12-07 · Mohammad Hesam Soleimani-Babakamali, Roksana Soleimani-Babakamali, Kourosh Nasrollahzadeh, Onur Avci 외

Gathering properly labelled, adequately rich, and case-specific data for successfully training a data-driven or hybrid model for structural health monitoring (SHM) applications is a challenging task. We posit that a Tran…

Domain Adaptation Generative Adversarial Network Structural Health Monitoring Transfer Learning

Deep Reinforcement Learning for Single-Shot Diagnosis and Adaptation in Damaged Robots

2019-10-02 · Shresth Verma, Haritha S. Nair, Gaurav Agarwal, Joydip Dhar 외

Robotics has proved to be an indispensable tool in many industrial as well as social applications, such as warehouse automation, manufacturing, disaster robotics, etc. In most of these scenarios, damage to the agent whil…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation

2026-06-30 · Héctor Laria, Yiping Han, Julian D. Santamaria, Kai Wang 외 arxiv

Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse …

Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots

2025-03-16 · Binggwong Leung, Worasuchad Haomachai, Joachim Winther Pedersen, Sebastian Risi 외

Artificial neural networks can be used to solve a variety of robotic tasks. However, they risk failing catastrophically when faced with out-of-distribution (OOD) situations. Several approaches have employed a type of syn…

Out-of-Distribution Generalization

The Cross-Domain Generalization Cost of Offensive Language Detection

2026-07-26 · Ruixing Ren, Junhui Zhao, Xiaoke Sun, Qiuping Li arxiv

Offensive language detection models generally suffer performance degradation when deployed across datasets and across languages, yet most existing studies stop at reporting this phenomenon and lack a systematic methodolo…

Domain Generalization