统一潜空间逐步学习多种物理角色技能，支持跨任务复用与长时序适应。
Progressively Learning Heterogeneous Skills in a Unified Latent Space
- 在统一潜空间中分步学习不同来源的运动技能，共享解码器避免重复训练。
- 实现高精度动作追踪与文本驱动生成，挑战条件下成功率仍超85%。
- 适合需要多技能融合与长期任务适应的智能体控制场景。
我们提出 HetSkills，一种用于物理角色控制的新框架，旨在统一潜空间中逐步学习异构技能。核心思想是将该潜空间视为共享可执行接口，实现来自不同数据源、监督形式和任务的技能无缝整合。HetSkills 首先学习一个动作追踪技能，建立稳固的动作控制基础，并生成可跨任务复用的共享运动解码器，无需重新训练或额外控制器。为防止文本到动作技能依赖捷径而非学习语言语义，引入运动直觉蒸馏以锚定文本生成于语言语义，并设计任务引导模块，根据高层语言指令动态调整动作。这使 HetSkills 在保持自然运动的同时持续扩展技能库，显著提升长时序任务适应能力。实验表明，其在动作追踪、文本到动作生成、动作补全及下游任务适应中均表现优异，在挑战性条件下仍取得高成功率。
原文摘要 · Abstract (English)
We propose HetSkills, a novel framework designed to progressively learn heterogeneous skills within a unified latent space for physics-based character control. The core idea is to treat this latent space as a shared executable interface, enabling seamless integration of skills learned from diverse data sources, supervision forms, and tasks. HetSkills begins by learning a tracking skill that establishes a strong foundation in motion control and creates a shared motion decoder, which can be reused across tasks without the need for retraining or separate controllers. To prevent the text-to-motion skill from exploiting shortcut pathways instead of learning language semantics, we introduce motion intuition distillation to ground text-to-motion generation in language semantics and a task-guidance module that dynamically adjusts actions based on high-level language instructions. This enables HetSkills to preserve natural motion while continuously expanding its skill repertoire, making it highly adaptable for long-horizon tasks. Experimental results demonstrate the effectiveness in motion tracking, text-to-motion generation, motion completion, and downstream task adaptation, achieving impressive success rates even under challenging conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。