轻量级视觉语言动作模型，让机器人更快更准执行语言指令
AnoleVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation
- 用深层状态空间模型替代传统变压器，高效处理多模态序列
- 真实场景下任务成功率比大型模型高21个百分点，推理速度提升3倍
- 适合移动端机械臂部署，兼顾效率与任务泛化能力
本研究针对语言引导的机器人操作问题，要求机器人基于视觉观察和自然语言指令操作各类物体。该任务对服务机器人在人类环境中的安全、效率与任务泛化能力提出高要求。尽管视觉-语言-动作模型（VLAs）已展现优异性能，但其在资源受限环境中的部署仍受标准Transformer主干计算成本高的制约。为此，我们提出AnoleVLA，一种采用深层状态空间模型处理多模态序列的轻量级VLA。该模型利用其轻量化与快速序列状态建模能力，高效处理视觉与文本输入，实现轨迹的高效生成。我们在仿真与物理实验中评估了该方法。值得注意的是，在真实世界测试中，AnoleVLA相比代表性大规模VLA，任务成功率提升21个百分点，同时推理速度约快3倍。
原文摘要 · Abstract (English)
In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based on visual observations and natural language instructions. This task is essential for service robots that operate in human environments, and requires safety, efficiency, and task-level generality. Although Vision-Language-Action models (VLAs) have demonstrated strong performance for this task, their deployment in resource-constrained environments remains challenging because of the computational cost of standard transformer backbones. To overcome this limitation, we propose AnoleVLA, a lightweight VLA that uses a deep state space model to process multimodal sequences efficiently. The model leverages its lightweight and fast sequential state modeling to process visual and textual inputs, which allows the robot to generate trajectories efficiently. We evaluated the proposed method in both simulation and physical experiments. Notably, in real-world evaluations, AnoleVLA outperformed a representative large-scale VLA by 21 points for the task success rate while achieving an inference speed approximately three times faster.
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。