# 从光流到安全：通过尺度无关相对运动进行视觉安全认证

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-21374
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：该文面向单目自主导航安全，利用光流编码的深度归一化相对运动构建RV-C^3BF，并在仿真和TurtleBot3实机上验证避障。

# 从光流到安全：通过尺度无关相对运动进行视觉安全认证

::: v-pre
> 原文链接：[From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion](https://arxiv.org/abs/2610.21374)（arXiv 2610.21374 · 发布日期：2026-10-15）

**From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion**

该文面向单目自主导航安全，利用光流编码的深度归一化相对运动构建RV-C^3BF，并在仿真和TurtleBot3实机上验证避障。

## 核心要点

- 单目视觉难以直接观测障碍物状态，安全自主导航仍具挑战。
- 方法不重建障碍物状态或度量世界模型，而用尺度无关相对运动认证碰撞风险。
- Concurrent Learning观测器估计归一化相对速度，并将误差界传播到碰撞锥中。
- 仿真中误差界覆盖98.3%样本实测误差，实机100次试验93次无碰撞。

**验证范围与局限**：验证范围为仿真及TurtleBot3在含静态和动态障碍的杂乱环境中导航。

## 英文摘要 (Abstract)

Safe autonomous navigation using monocular vision remains challenging because explicit obstacle states are not directly observable. This letter introduces a visual safety-certification paradigm that uses scale-free, depth-normalized relative motion encoded by monocular optical flow as the representation for collision-risk certification, without reconstructing obstacle position, velocity, geometry, or a metric world model. Unlike conventional optical-flow-based navigation approaches that rely on image motion to shape avoidance behavior, the proposed framework directly encodes collision-cone geometry and safety constraints in this relative-motion representation. An online Concurrent Learning observer estimates the normalized relative velocity and provides a computable estimation-error bound. This uncertainty is propagated into the collision cone through angular inflation and a monocular robot-footprint margin, yielding a Robust Vision-Based Collision Cone Control Barrier Function (RV-C$^3$BF). An optimal-decay CBF quadratic program minimally modifies the nominal control input to enforce the resulting robust safety constraint under the stated assumptions. Extensive simulation and real-world experiments on a TurtleBot3 in cluttered environments with static and dynamic obstacles demonstrate collision avoidance using only monocular vision and onboard proprioception, with the estimation-error bound containing the measured error in $98.3\%$ of simulation samples and the robot achieving collision-free navigation in $93$ of $100$ real-world trials.

作者：Bazeela Banday, Jishnu Keshavan
:::

## 原始参考来源 (Sources)

- [arXiv 2610.21374：From Optical Flow to Safety: Visual Safety Certification via Scale-Free Relative Motion](https://arxiv.org/abs/2610.21374)