arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.18224cs.ROcs.LG
收藏

SimVLA:一种简单的VLA基线用于机器人操作

SimVLA: Attributing Gains in VLA Models Through Controlled Ablation

Yuankai Luo, Woping Chen, Tong Liang, Zhenguo Li

AI总结:

SimVLA通过简化设计实现了最先进的机器人操作性能,展示了最小参数模型在模拟和真实环境中的优越表现。

摘要:

视觉-语言-动作(VLA)模型已逐渐成为通用机器人操作的有希望的范式,利用大规模预训练来实现强大性能。该领域在增加空间先验和多样的架构创新方面迅速发展。然而,这些进步往往伴随着不同的训练配方和实现细节,这使得难以区分经验增益的确切来源。在本文中,我们介绍了SimVLA,一种流线型基线,旨在为VLA研究建立一个透明的参考点。通过严格解耦感知与控制,使用标准的视觉-语言骨干网络和轻量级的动作头,并标准化关键的训练动态,我们证明了最小设计可以实现最先进的性能。尽管只有0.5B参数,SimVLA在标准模拟基准上优于多十亿参数模型,无需机器人预训练。SimVLA在与pi0.5相媲美的真实机器人性能上也达到了同等水平。我们的结果使SimVLA成为一种稳健、可重复的基线,能够为未来的架构创新明确归因于经验增益。网站:https://frontierrobo.github.io/SimVLA

英文摘要:

Vision-Language-Action (VLA) models often bundle architectural changes with different pretraining data, backbone scales, and optimization recipes, obscuring what actually drives progress. We introduce SimVLA, a deliberately minimal VLA, a standard vision-language backbone with a lightweight continuous-action head, as a controlled testbed for this attribution problem; our contribution is methodological and empirical (a controlled attribution study and a minimal-baseline calibration), not a new technique. Across LIBERO, CALVIN, WidowX, and Google Robot, one-knob-at-a-time ablations show that training dynamics are the largest measured driver, producing performance swings of $Δ$$\approx$54--94\%, while task configuration and architecture have smaller effects under matched settings. Despite using a small backbone and no additional large-scale robot-data VLA pretraining before benchmark-specific training, SimVLA reaches 98.6\% average success on LIBERO, remains competitive across the other benchmarks, and transfers to held-out real-robot scenes. These results suggest that simple, carefully controlled VLA baselines remain underexplored and provide a calibration point for future architectural claims within the VLM-encoder plus lightweight-head family. Website: https://frontierrobo.github.io/SimVLA

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。

↑