WOLF-VLA：面向视觉-语言-动作学习的全身人形最优运动框架
WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning
AI总结：
提出WOLF-VLA框架，结合全身最优控制运动合成与大规模多模态数据集，训练VLA模型从自然语言指令生成人形运动策略，在多种任务中展现强鲁棒性和竞争力。
摘要：
视觉-语言-动作（VLA）模型最近在机器人操作中展示了强大的泛化能力，但由于数据稀缺、缺乏动态一致的演示以及在学习管道中编码最优性和安全性的困难，它们在全身体、接触丰富的人形运动中的应用仍然严重未被探索。本文介绍了一个统一框架WOLF-VLA，它将全身最优控制（OC）运动合成与大规模多模态数据集相结合，以训练能够直接从自然语言指令生成人形运动策略的VLA模型。我们构建了一个全面的动态可行人形轨迹数据集，涵盖六个与运动相关的任务族，每个任务族通过环境变化、物体颜色、放置位置和视觉干扰物进行参数化。我们使用收集的关节轨迹、自我中心视觉观察和自然语言指令训练了一个VLA模型，得到的策略表现出强大的推理能力和对初始条件变化的鲁棒性，并在多个任务和环境设置中具有竞争力的性能。系统的消融研究证明了每种模态对模型性能的影响。完整的数据集、模型检查点和基准测试模拟套件将公开发布，为全身人形运动丰富的VLA控制建立一个可复现的动态一致基准，并推动可扩展的指令驱动运动策略迁移的未来研究。
英文摘要：
Vision-Language-Action (VLA) models have recently demonstrated strong generalization in robotic manipulation, yet their applicability to whole-body, contact-rich humanoid locomotion remains severely underexplored due to data scarcity, the absence of dynamically consistent demonstrations, and the difficulty of encoding optimality and safety in learning-based pipelines. This work introduces a unified framework WOLF-VLA that integrates whole-body optimal-control (OC) motion synthesis with large-scale multi-modal dataset to train VLAs capable of generating humanoid locomotion policies directly from natural-language instructions. We construct a comprehensive dataset of dynamically feasible humanoid trajectories across six locomotion-related task families, each parameterized by environmental variations, object colors, placements, and visual distractors. We train a VLA model using the collected joint trajectories, ego-centric visual observations and natural language instruction, yielding a policy that exhibits strong reasoning and robustness to initial-condition variability, and competitive performance across several tasks and environment settings. A systematic ablation study demonstrates the impact of each modality on the model performance. The full dataset, model checkpoints, and benchmarking simulation suite will be openly released, establishing a reproducible dynamically consistent benchmark for whole-body humanoid locomotion rich VLA control and enabling future research in scalable transfer of instruction-driven locomotion policies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
