外观
论文arXiv 2608.010152 个月前
KING：面向具身的运动学图神经网络，用于腿式和轮式机器人的统一运动表示
原文链接：KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation of Legged and Wheeled Robots（arXiv 2608.01015 · 发布日期：2026-08-02）
KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation of Legged and Wheeled Robots
针对跨具身运动学模型泛化差，KING用GNN统一表示轮式与腿式运动学，并在真实环境中验证高精度里程计估计。
核心要点
- 无特征环境中外感退化、IMU积分漂移，运动学约束可辅助里程计估计。
- 现有学习式运动学多针对单一具身训练，因关节和接触元素差异难以泛化。
- KING将机器人具身表示为通用图，用GNN统一轮式与腿式运动学模型。
- 跨多样具身数据训练后，KING在真实环境实现高精度里程计估计；项目页已提供。
验证范围与局限：验证范围为轮式和腿式机器人在真实环境中的里程计估计，并展示用一分钟数据适应新具身。
英文摘要 (Abstract)
Kinematic models provide reliable motion constraints for odometry estimation in featureless environments, where exteroceptive sensing degrades and IMU integration drifts. Learning-based kinematic models can achieve more accurate odometry estimation than model-based methods by capturing nonlinear effects; however, most existing learning-based models are trained on a single embodiment and generalize poorly to new embodiments. This generalization is difficult because the meanings and structures of proprioceptive measurements vary across embodiments, including the number of joints and ground-contact elements (e.g., wheels, feet). To address this challenge, we propose KING, a Graph Neural Network (GNN)-based kinematic model that explicitly incorporates robot embodiments by representing them as a common graph. We show that wheel and leg kinematic models can be expressed by a unified representation, enabling a single model for both wheeled and legged robots. Trained on datasets spanning diverse embodiments, KING provides a unified representation of wheeled and legged kinematics and achieves high-accuracy odometry estimation in real environments. KING estimates accurate odometry using only an embodiment description (e.g., a URDF file) and on-board proprioception (encoders and an IMU) and can be adapted to new robot embodiments through few-shot learning with only one minute of data, avoiding retraining from scratch on a new dataset for each robot. The project page is available at: https://smrg-aist.github.io/king_project_page/
作者：Taku Okawara, Aoki Takanose, Kenji Koide, Shuji Oishi, Masashi Yokozuka
来源
本页事实对应的公开页面，以原文为准。