# KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation of Legged and Wheeled Robots

arXiv: https://arxiv.org/abs/2608.01015 · HTML: https://mlsanity.com/paper/2608.01015/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots](https://mlsanity.com/paper/2107.07243/) (2021)
- [AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility](https://mlsanity.com/paper/2409.15783/) (2024)
- [Cerberus: Low-Drift Visual-Inertial-Leg Odometry For Agile Locomotion](https://mlsanity.com/paper/2209.07654/) (2022)
- [GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning](https://mlsanity.com/paper/2505.15211/) (2025)
- [WhONet: Wheel Odometry Neural Network for Vehicular Localisation in GNSS-Deprived Environments](https://mlsanity.com/paper/2104.02581/) (2021)
- [XMoP: Whole-Body Control Policy for Zero-shot Cross-Embodiment Neural Motion Planning](https://mlsanity.com/paper/2409.15585/) (2024)
- [Tightly-Coupled LiDAR-IMU-Wheel Odometry with an Online Neural Kinematic Model Learning via Factor Graph Optimization](https://mlsanity.com/paper/2407.08907/) (2024)
- [Tightly-Coupled LiDAR-IMU-Leg Odometry with Online Learned Leg Kinematics Incorporating Foot Tactile Information](https://mlsanity.com/paper/2506.09548/) (2025)

## Built on by (most cited first, 1 of 1)

- [Screw Attention: Rigid-Body Algebra Inside a Transformer](https://mlsanity.com/paper/2610.00904/) (2026)

## Abstract (arXiv)

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/