pySLAM

code: https://github.com/luigifreda/pyslam

With over 1.5k stars on GitHub, pySLAM contains a Python implementation of a monocular Visual Odometry (VO) pipeline. It supports many classical and modern local features, and it offers a convenient interface for them. Moreover, it collects other common and useful VO and SLAM tools. I released its first version for educational purposes for a computer vision class I recently taught. I started developing it for fun as a Python programming exercise, during my free time. You can use this framework as a baseline to play with local features, VO techniques, and create your own (proof of concept) VO/SLAM pipeline in python. 

---

3dpatrolling 

code: https://github.com/luigifreda/3dpatrolling
webpage: https://sites.google.com/a/dis.uniroma1.it/3d-cc-patrolling/

This repository provides part of the C++ implementation behind our paper titled “3D Multi-Robot Patrolling with a Two-Level Coordination Strategy“. The software allows testing the proposed multi-robot strategy within a V-REP simulation environment. More information on this page. 

---

ROSIntegration for Unreal Engine 4.23

code: https://github.com/luigifreda/ROSIntegration  (fork)
new: now this fork has been merged into the original repo https://github.com/code-iai/ROSIntegration

I succeeded in porting the ROSIntegration plugin to the brand new version 4.23 of Unreal Engine (UE). The ROSIntegration plugin allows a cool integration between UE and ROS. The plugin was already available and tested up to UE 4.22. Unfortunately, some memory management bugs prevented the plugin from correctly working (getting continuous crashes) under the new version 4.23 (where more strict checks are performed on UObject and memory management). I successfully found and fixed the bugs in the ROSIntegration plugin. Now, it correctly works without crashes.