<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Visual Odometry | Gelei Deng</title><link>https://geleideng.github.io/tags/visual-odometry/</link><atom:link href="https://geleideng.github.io/tags/visual-odometry/index.xml" rel="self" type="application/rss+xml"/><description>Visual Odometry</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 19 May 2025 00:00:00 +0000</lastBuildDate><image><url>https://geleideng.github.io/media/icon_hu7729264130191091259.png</url><title>Visual Odometry</title><link>https://geleideng.github.io/tags/visual-odometry/</link></image><item><title>Detecting Perception-Based Attacks using Visual Odometry: Inconsistency Modeling and Checking on Robotic States</title><link>https://geleideng.github.io/publication/visual-odometry-robotic-states/</link><pubDate>Mon, 19 May 2025 00:00:00 +0000</pubDate><guid>https://geleideng.github.io/publication/visual-odometry-robotic-states/</guid><description>&lt;p>The paper continues my robotics-security work by connecting perception attack detection with state inconsistency modeling, using visual odometry as a practical signal for identifying compromised robotic perception.&lt;/p></description></item></channel></rss>