Problem
Research questions and friction points this paper is trying to address.
Language-Driven
Physics-Based
Contact-Rich Interaction
Whole-Body Object Interactions
Free-Form Language Instruction
LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction
🤖 AI Summary
研究提出LYRIC控制器，通过语言指令和稀疏目标实现物理模拟角色的全身物体交互，使用几何条件奖励训练策略并分解控制器为任务规划器和动作生成器。
📝 Abstract
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/
Innovation
Methods, ideas, or system contributions that make the work stand out.
Language-Driven Control
Physics-Based Simulation
Contact-Rich Interaction
Generative Flow-Matching
Task-Level Planning
🔎 Similar Papers
No similar papers found.
