论文标题
通过控制屏障功能和神经辐射场为基于视力的控制器执行安全性
Enforcing safety for vision-based controllers via Control Barrier Functions and Neural Radiance Fields
论文作者
论文摘要
为了浏览复杂的环境，机器人必须越来越多地使用高维视觉反馈（例如图像）进行控制。但是，依靠高维图像数据来控制决策会提出重要的问题；特别是，我们如何证明视觉反馈控制器的安全性？控制障碍功能（CBF）是在状态反馈设置中证明反馈控制器安全性的强大工具，但是由于需要预测未来的观察以评估屏障功能，因此传统上，CBF非常适合视觉反馈控制。在这项工作中，我们通过利用神经辐射场（NERFS）的最新进展来解决这个问题，这些神经辐射场（NERFS）学习了3D场景的隐式表示，并且可以从以前未见的摄像机的角度呈现图像，以提供基于CBF的控制器的单步视觉远景。这种新颖的组合能够滤除不安全的动作和干预以保持安全性。我们在实时仿真实验中证明了控制器的效果，在实时模拟实验中，它成功阻止了机器人采取危险的行动。
To navigate complex environments, robots must increasingly use high-dimensional visual feedback (e.g. images) for control. However, relying on high-dimensional image data to make control decisions raises important questions; particularly, how might we prove the safety of a visual-feedback controller? Control barrier functions (CBFs) are powerful tools for certifying the safety of feedback controllers in the state-feedback setting, but CBFs have traditionally been poorly-suited to visual feedback control due to the need to predict future observations in order to evaluate the barrier function. In this work, we solve this issue by leveraging recent advances in neural radiance fields (NeRFs), which learn implicit representations of 3D scenes and can render images from previously-unseen camera perspectives, to provide single-step visual foresight for a CBF-based controller. This novel combination is able to filter out unsafe actions and intervene to preserve safety. We demonstrate the effect of our controller in real-time simulation experiments where it successfully prevents the robot from taking dangerous actions.
