发表机构
the National Institute of Advanced Industrial Science and Technology（国立先进工业科学技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对现有运动模型对新机器人具身泛化能力差的问题，提出基于GNN的KING模型，实现轮式与腿式机器人的统一运动表示，仅需少量数据即可适配新具身并实现高精度里程计估计。
AI 中文摘要
运动模型可为特征匮乏环境下的里程计估计提供可靠运动约束，此类环境中外感知传感性能下降，惯性测量单元（IMU）积分会发生漂移。基于学习的运动模型可捕捉非线性效应，实现比基于模型的方法更精准的里程计估计；然而，多数现有学习模型仅针对单一具身训练，对新具身的泛化能力极差。这种泛化困难源于不同具身的本体感知测量值的含义与结构存在差异，包括关节数量和地面接触元件（如轮子、足端）。为应对该挑战，本文提出KING，一种基于图神经网络（GNN）的运动模型，通过将机器人具身表示为通用图，明确融入机器人具身信息。研究表明，轮式与腿式运动模型可通过统一表示来表达，从而实现适用于轮式和腿式机器人的单一模型。KING在涵盖不同具身的数据集上训练，可提供轮式与腿式运动学的统一表示，并在真实环境中实现高精度里程计估计。KING仅需利用具身描述（如URDF文件）和车载本体感知数据（编码器与IMU）即可估计精准里程计，且仅需1分钟数据即可通过少样本学习适配新机器人具身，无需为每个机器人从零开始在新数据集上重新训练。项目页面可访问：this https URL
英文摘要
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/
CommentsIROS 2026
