用预训练视觉模型构建视觉控制安全过滤器，提升机器人系统安全性。
Designing Latent Safety Filters using Pre-Trained Vision Models
- 以预训练视觉模型为骨干，构建视觉安全过滤器
- 对比了微调、冻结等不同训练策略的性能差异
- 适合关注机器人视觉控制安全的开发者和研究者
确保基于视觉的控制系统安全性仍是阻碍其在关键场景部署的主要挑战。安全过滤器作为保障经典控制系统安全的有效工具，但在视觉控制中的应用仍有限。预训练视觉模型（PVRs）已被证明在多个机器人领域中是有效的感知骨干。本文探讨将PVRs用于设计视觉安全过滤器的有效性：将其作为定义失效集的分类器、基于哈密顿-雅可比（HJ）可达性的安全过滤器骨干，以及潜在世界模型的组成部分。我们分析了从头训练、微调和冻结PVRs在训练过程中带来的权衡。同时评估了某类PVR是否在所有任务中表现更优，并比较了学习的世界模型与Q函数在切换至安全策略决策中的表现，最后讨论了在资源受限设备上部署PVRs的实际考虑。
原文摘要 · Abstract (English)
Ensuring safety of vision-based control systems remains a major challenge hindering their deployment in critical settings. Safety filters have gained increased interest as effective tools for ensuring the safety of classical control systems, but their applications in vision-based control settings have so far been limited. Pre-trained vision models (PVRs) have been shown to be effective perception backbones for control in various robotics domains. In this paper, we are interested in examining their effectiveness when used for designing vision-based safety filters. We use them as backbones for classifiers defining failure sets, for Hamilton-Jacobi (HJ) reachability-based safety filters, and for latent world models. We discuss the trade-offs between training from scratch, fine-tuning, and freezing the PVRs when training the models they are backbones for. We also evaluate whether one of the PVRs is superior across all tasks, evaluate whether learned world models or Q-functions are better for switching decisions to safe policies, and discuss practical considerations for deploying these PVRs on resource-constrained devices.
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。