<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Python on Rishika Bera</title><link>https://rishika2024.github.io/tags/python/</link><description>Recent content in Python on Rishika Bera</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>berarishika@gmail.com (Rishika Bera)</managingEditor><webMaster>berarishika@gmail.com (Rishika Bera)</webMaster><copyright>Rishika Bera</copyright><lastBuildDate>Mon, 10 Aug 2026 14:15:05 +0700</lastBuildDate><atom:link href="https://rishika2024.github.io/tags/python/index.xml" rel="self" type="application/rss+xml"/><item><title>Lattice Print Path Planning with Reinforcement Learning</title><link>https://rishika2024.github.io/posts/meca500_rl/</link><pubDate>Mon, 10 Aug 2026 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/meca500_rl/</guid><description>&lt;p&gt;This project tackles print path planning for lattice structures using reinforcement learning. Given a lattice (vertices + edges from LatticeQuery), the goal is to find the order to print every strut without the nozzle colliding with already printed material.&lt;/p&gt;</description></item><item><title>Robotic 3D Printing with a Meca500</title><link>https://rishika2024.github.io/posts/meca500_3d_printer/</link><pubDate>Fri, 10 Jul 2026 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/meca500_3d_printer/</guid><description>&lt;style&gt;
.video-row {
 display: flex;
 flex-wrap: wrap;
 justify-content: center;
 gap: 1rem;
 width: 100vw;
 margin-left: calc(50% - 50vw);
 margin-right: calc(50% - 50vw);
}
.video-row &gt; figure {
 margin: 0 !important;
 flex: 1 1 320px;
 max-width: 400px;
}
&lt;/style&gt;

&lt;h2 class="relative group"&gt;Overview
 &lt;div id="overview" class="anchor"&gt;&lt;/div&gt;
 
&lt;/h2&gt;
&lt;p&gt;I built a ROS 2 package that drives a Meca500 6-DOF arm (5 μm resolution) as a 3D printer through MoveIt 2. A custom &lt;code&gt;ros2_control&lt;/code&gt; hardware interface bridges the Meca500&amp;rsquo;s proprietary TCP API to MoveIt 2, so real trajectory planning and execution run on the physical arm. A mounted Ender3 extruder handles filament feed and heating over USB serial — the arm does all of the XYZ motion.&lt;/p&gt;</description></item><item><title>YOLO Distillation for Real-Time Inference on a Raspberry Pi Zero</title><link>https://rishika2024.github.io/posts/yolo_distillation/</link><pubDate>Wed, 10 Jun 2026 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/yolo_distillation/</guid><description>&lt;h4 class="relative group"&gt;Joint project with Theo Coulson, Northwestern University
 &lt;div id="joint-project-with-theo-coulson-northwestern-university" class="anchor"&gt;&lt;/div&gt;
 
&lt;/h4&gt;
&lt;p&gt;Distilling a fine-tuned YOLO detector into a custom architecture small enough to run in real time on a Raspberry Pi Zero 2W, so a drone can spot and land on a landing platform on its own — at about a tenth of the teacher&amp;rsquo;s parameter count. Read the &lt;a href="https://rishika2024.github.io/yolo_distillation/report.pdf" style="text-decoration: underline;"&gt;full report&lt;/a&gt; for the complete writeup.&lt;/p&gt;</description></item><item><title>Sketch2Real - Colored Sketch to Photorealistic Image Generation</title><link>https://rishika2024.github.io/posts/sketch2real/</link><pubDate>Sat, 09 May 2026 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/sketch2real/</guid><description>&lt;style&gt;
.side-by-side {
 display: flex;
 gap: 2rem;
 align-items: center;
 justify-content: center;
 margin: 2rem 0;
 flex-wrap: wrap;
}
.side-by-side figure {
 flex: 1;
 min-width: 300px;
 max-width: 45%;
}
&lt;/style&gt;
&lt;p&gt;Sketch2Real generates photorealistic images from colored sketches using a conditional diffusion model built on a U-Net architecture, trained on the COCO dataset.&lt;/p&gt;</description></item><item><title>Jack-in-the-Box</title><link>https://rishika2024.github.io/posts/jack-in-the-box/</link><pubDate>Fri, 12 Dec 2025 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/jack-in-the-box/</guid><description>&lt;h2 class="relative group"&gt;Outer Box Frames
 &lt;div id="outer-box-frames" class="anchor"&gt;&lt;/div&gt;
 
&lt;/h2&gt;

&lt;figure style="width: min(55%, 100%); margin-inline: auto;"&gt;
 &lt;img class="my-0 rounded-md" src="https://rishika2024.github.io/jack-in-box/Box%20Frame.png" alt="Box Frames" /&gt;
 
 
 &lt;/figure&gt;
&lt;p&gt;The frame at the center of the outer box is obtained by translating the world frame to the box center and then rotating it by the box orientation \(\theta_{\text{box}}\).&lt;/p&gt;</description></item><item><title>Mrs. Catfisher - The Bug Sorter</title><link>https://rishika2024.github.io/posts/mrs-catfisher/</link><pubDate>Fri, 12 Dec 2025 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/mrs-catfisher/</guid><description>&lt;figure style="width: min(60%, 100%); margin-inline: auto;"&gt;
 &lt;img class="my-0 rounded-md" src="https://rishika2024.github.io/mrs-catfisher/franka%20picking%20up%20a%20bug.png" alt="Franka picking up a bug" /&gt;
 
 
 &lt;/figure&gt;
&lt;p&gt;This was a group project by Halley Zhong, Nolan Knight, Miguel, and myself for &lt;strong&gt;Northwestern&amp;rsquo;s MECH_ENG 450: Embedded Systems in Robotics&lt;/strong&gt; course. We built an autonomous system to sort moving HexBugs using the Franka Arm. My role was to develop the vision system, which can detect, uniquely label, and track the moving bugs in real time.&lt;/p&gt;</description></item><item><title>RRT for 2D Path Planning</title><link>https://rishika2024.github.io/posts/rrt/</link><pubDate>Thu, 11 Sep 2025 14:15:05 +0700</pubDate><author>berarishika@gmail.com (Rishika Bera)</author><guid>https://rishika2024.github.io/posts/rrt/</guid><description>&lt;p&gt;An RRT is a set of vertices (configurations) and edges (connections between configurations). Each iteration samples a random point in the domain, finds the nearest existing vertex, and takes a small step of size \(\Delta\) toward the sample. If you run it for long enough, you get close to uniform coverage over the whole space.&lt;/p&gt;</description></item></channel></rss>