https://rishika2024.github.io/tags/path-planning/Recent content in Path Planning on Rishika BeraHugo -- gohugo.ioenberarishika@gmail.com (Rishika Bera)berarishika@gmail.com (Rishika Bera)Rishika BeraMon, 10 Aug 2026 14:15:05 +0700https://rishika2024.github.io/posts/meca500_rl/Mon, 10 Aug 2026 14:15:05 +0700berarishika@gmail.com (Rishika Bera)https://rishika2024.github.io/posts/meca500_rl/<p>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.</p>https://rishika2024.github.io/posts/slam/Sun, 22 Mar 2026 14:15:05 +0700berarishika@gmail.com (Rishika Bera)https://rishika2024.github.io/posts/slam/<h2 class="relative group">Overview <div id="overview" class="anchor"></div> </h2> <p>Built a complete EKF SLAM pipeline from scratch in C++ using ROS 2, simulated on a TurtleBot3. The robot localizes itself and maps cylindrical landmarks simultaneously using wheel odometry and 2D LiDAR. Three robots are visualized: red (ground truth, known only to the simulator), blue (odometry estimate, which drifts over time), and green (SLAM corrected estimate). The video shows the robot driving a closed path with sensor noise and limited detection range. As odometry drifts, the EKF corrects it by fusing landmark observations, keeping the green path close to ground truth while blue diverges. Landmark estimates in green converge toward their true positions with repeated observations.</p>