الملخص
We present LYRIC, a generative flow-matching controller for language-driven physics-based contact-rich interaction control, that enables simulated characters to perform contact-rich whole-body object interactions from a free-form language instruction and a sparse terminal object goal. To obtain reliable expert trajectories from imperfect motion-capture references, a single tracking policy is trained using geometry-conditioned interaction rewards and relaxed reference tracking near hand-object contact. To guide interaction progress without prescribing a full-body kinematic reference, we factorize the controller into a task-level planner that predicts short-horizon object and humanoid-root trajectories, and an action generator that resolves whole-body motion and contacts in closed loop. After behavior cloning, we freeze the planner and post-tune the action generator on policy using the planner's predictions as stable supervision for intermediate task progression. In a controlled OMOMO evaluation, our tracker achieves 64.3% success compared with 53.2% for an InterMimic reimplementation, while a unified policy achieves 76.5% on the full OMOMO dataset. On the held-out split, LYRIC achieves 90.3% task success, compared with 74.2% for the strongest matched kinematic-planner baseline, with better semantic alignment and motion quality. Without retraining, the controller also supports test-time object-waypoint guidance. Qualitative results further demonstrate robust, natural contact-rich interactions and zero-shot transfer to novel object shapes. The webpage is available at https://neu-vi.github.io/LYRIC/
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Han, Z., Meng, Z., Tanke, J., Matsumoto, M., Bashkirov, S., Fan, Y., Engin, S., Shim, D., Shibuya, T., Mitsufuji, Y., & Jiang, H. (2026). LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction. https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction
MLA 9
Han, Zeyu, et al. "LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction." https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction.
شيكاغو (المؤلف–التاريخ)
Han, Zeyu, Zichong Meng, Julian Tanke, Minami Matsumoto, Sergey Bashkirov, Yingruo Fan, Selim Engin, Dongseok Shim, Takashi Shibuya, Yuki Mitsufuji, and Huaizu Jiang. 2026. "LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction." https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction.
هارفارد
Han, Z., Meng, Z., Tanke, J., Matsumoto, M., Bashkirov, S., Fan, Y., Engin, S., Shim, D., Shibuya, T., Mitsufuji, Y. and Jiang, H. (2026) 'LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction', Available at: https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction.
فانكوفر
Han Z, Meng Z, Tanke J, Matsumoto M, Bashkirov S, Fan Y, et al. LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction. https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction
IEEE
Z. Han, Z. Meng, J. Tanke, M. Matsumoto, S. Bashkirov, Y. Fan, S. Engin, D. Shim, T. Shibuya, Y. Mitsufuji, and H. Jiang, "LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction," https://omanscience.com/ar/articles/lyric-language-driven-physics-based-character-control-for-contact-rich-whole-body-object-interaction.