<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Robotics on Deep Dive</title><link>https://isaac0804.github.io/tags/robotics/</link><description>Recent content in Robotics on Deep Dive</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Tue, 26 May 2026 18:00:00 +0100</lastBuildDate><atom:link href="https://isaac0804.github.io/tags/robotics/index.xml" rel="self" type="application/rss+xml"/><item><title>Teaching a Robot Arm to See 100ms Into the Future</title><link>https://isaac0804.github.io/posts/2026-05-26-franka-ee-tracking/</link><pubDate>Tue, 26 May 2026 18:00:00 +0100</pubDate><guid>https://isaac0804.github.io/posts/2026-05-26-franka-ee-tracking/</guid><description>&lt;p&gt;Most robot controllers have a delay. Commands take time to travel through software stacks, buffers, and hardware. For the Franka Panda arm I was working with in MuJoCo, this delay is exactly 100ms — five control steps at 50Hz.&lt;/p&gt;
&lt;p&gt;That sounds small. It is not.&lt;/p&gt;
&lt;hr&gt;
&lt;h2 id="the-problem"&gt;The problem&lt;/h2&gt;
&lt;p&gt;A standard inverse kinematics (IK) controller does something simple: look at where the target is right now, compute the joint angles that would put the end-effector there, send those angles to the robot.&lt;/p&gt;</description></item></channel></rss>