<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RGB-D | Harshitha B R</title><link>https://harshithabr.github.io/tags/rgb-d/</link><atom:link href="https://harshithabr.github.io/tags/rgb-d/index.xml" rel="self" type="application/rss+xml"/><description>RGB-D</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 01 Apr 2025 00:00:00 +0000</lastBuildDate><image><url>https://harshithabr.github.io/media/icon_hu68170e94a17a2a43d6dcb45cf0e8e589_3079_512x512_fill_lanczos_center_3.png</url><title>RGB-D</title><link>https://harshithabr.github.io/tags/rgb-d/</link></image><item><title>Learning from Demonstration on Stretch &amp; Franka</title><link>https://harshithabr.github.io/project/robot-demonstration/</link><pubDate>Tue, 01 Apr 2025 00:00:00 +0000</pubDate><guid>https://harshithabr.github.io/project/robot-demonstration/</guid><description>&lt;p>Built an &lt;strong>RGB-D visual-servoing and gesture-based demonstration system&lt;/strong> for the Hello Robot Stretch using 3D hand tracking and reactive control, and extended the system to &lt;strong>Franka Research 3&lt;/strong>. Collected multimodal robot trajectories and developed preprocessing, replay, and policy-training pipelines for learning from demonstration.&lt;/p></description></item></channel></rss>