cs.RONov 8, 2026

Kimodo-Policy: Learning Kinematic Action Models for Humanoid Loco-Manipulation

Authors: Yunheng Wang, Jiaxi Zhang, Wei Lu, Yuetong Fang, Taowen Wang, Yixiao Feng, Shuning Zhang, Junzhe Xu, 

Organizations: HKUST(GZ) · JD Explore Academy · BJUT · Cambridge

Abstract

Humanoid loco-manipulation requires continuous coordination of high-dimensional whole-body motion to realize task objectives. While vision-language-action models and world action models transfer semantic and visual-dynamics priors to robot control, these priors do not necessarily capture the structure of robot motion. We introduce Kinematic Action Models (KAMs), a paradigm that treats whole-body motion as a direct pretraining target and uses a pretrained motion generator as the primary action-generation backbone. KAMs ground learned temporal and cross-body coordination priors through task conditioning, visual observations, and execution feedback. We present Kimodo-Policy as an initial instantiation, combining a frozen Kimodo text-to-motion backbone with lightweight ControlNet-based visual conditioning. A root-body-hand hierarchy coordinates locomotion and manipulation, while motion-history conditioning and repeated action-chunk prediction bridge motion synthesis and closed-loop control. Following large-scale loco-manipulation pretraining, the policy achieves the highest overall success among compared policies on multi-task HumanoidArena (72.14%), competitive performance on SIMPLE, and 60% mean success across eight real-world tasks, with 678M parameters (92M trainable). Ablations support the contribution of the pretrained motion backbone. Together, these results provide initial evidence for motion generation as a complementary foundation for humanoid action learning.

Figures & tables

Explore similar work

CardsList
  1. WB-WAM: Heterogeneous Body-Hand Pre-training for Humanoid Loco-Manipulation

    Sep 28, 2026Chuan Qin, Shaoting Zhu, Siyuan Luo +4Humanoid Loco-ManipulationMultimodal Pretraining

  2. MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation

    Jun 8, 2026Jia Zheng, Teli Ma, Yudong Fan +3Humanoid Loco-ManipulationHumanoid Robot Control