Newest papers

SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation

Zhaohui Yang, Quanbao Lin, Chengqi Shi, Zhenglang Weng, Jicheng Lin, Boyu Chen, Tengjie Zhu, Guanzhu Ren, Jiahao Xu, Yang Feng, Xiaokang Yang, Yao Mu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30044 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Loko-manipulasi humanoid membutuhkan antarmuka yang efektif antara kebijakan tugas tingkat tinggi dan kontrol seluruh tubuh. Antarmuka yang ada biasanya bergantung pada representasi tindakan tunggal untuk keduanya niat tugas dan koordinasi seluruh tubuh. Ini dapat membebani kebijakan tingkat tinggi atau meninggalkan satu aspek kurang ditentukan. Kami menyajikan SP-HLM, sebuah kerangka kerja yang dibangun pada antarmuka yang didorong oleh pola-pos. Antarmuka ini menggabungkan lima posisi tubuh kritis tugas dengan gerak latent yang dipelajari sebelum untuk mewakili niat ruang dan koordinasi seluruh tubuh dalam bentuk komplementer. SP-VLA, sebuah model vision-language-action, pertama memprediksi posisi sparse yang relevan dengan tugas dan posisi sendi jari dari pengamatan multimodal dan instruksi bahasa menggunakan asynchronous action-chunk inference. Mengingat tujuan sparse ini, SP-

Machine translation (Meta M2M100); the English original follows.

Abstract

Humanoid loco-manipulation requires an effective interface between high-level task policies and whole-body control. Existing interfaces typically rely on a single action representation for both task intent and whole-body coordination. This may burden the high-level policy or leave one aspect underspecified. We present SP-HLM, a framework built on a sparse-pose-driven interface. The interface combines five task-critical body poses with a learned latent motion prior to represent spatial intent and whole-body coordination in complementary forms. SP-VLA, a vision-language-action model, first predicts task-relevant sparse poses and finger joint positions from multimodal observations and language instructions using asynchronous action-chunk inference. Given these sparse targets, SP-MGM, a motion generation model trained through two-stage distillation, reconstructs coordinated full-body motion in real time. A pretrained motion encoder maps this motion to a compact latent representation. SP-GMT, a general motion tracker, then integrates the explicit sparse targets with this implicit motion prior for whole-body control. Experiments in simulation and on a real humanoid robot demonstrate improved motion tracking, whole-body coordination, and loco-manipulation success over existing approaches. Additional results and videos are available on our \href{https://sp-hlm.github.io/}{\textcolor{blue}{project page}}.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Humanoid robot, Motion (physics), Computer science, Artificial intelligence, Task (project management), Computer vision

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange